From 5d84b5483524f3ebe9014f6f96524bfc642966b5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Doruk=20=C3=96zgen?= Date: Mon, 21 Sep 2026 14:30:15 +0300 Subject: [PATCH 01/30] feat(catalog): add Claude Fable 5.1 to anthropic and claude-code Fable 5.1 (`claude-fable-5-1`) shipped 2026-09-01 and is the target of Claude Code's `fable` / `best` aliases from v2.1.257 on. Same $10 / $50 list price and 1M / 128K limits as Fable 5, but cache reads bill at 0.025x base input ($0.25) instead of the usual 0.1x. Opus 5 stays the default on both providers, matching Anthropic's own account defaults; Fable 5.1 slots directly beneath it. Fable 5 is still served (legacy, retirement not before 2027-06-09) and keeps its entry. Source: platform.claude.com models overview, pricing and Fable 5.1 pages; code.claude.com model-config. --- .../anthropic/models/claude-fable-5-1.toml | 28 +++++++++++++++++++ .../claude-code/models/claude-fable-5-1.toml | 12 ++++++++ 2 files changed, 40 insertions(+) create mode 100644 providers/anthropic/models/claude-fable-5-1.toml create mode 100644 providers/claude-code/models/claude-fable-5-1.toml diff --git a/providers/anthropic/models/claude-fable-5-1.toml b/providers/anthropic/models/claude-fable-5-1.toml new file mode 100644 index 0000000..e6b1497 --- /dev/null +++ b/providers/anthropic/models/claude-fable-5-1.toml @@ -0,0 +1,28 @@ +name = "Claude Fable 5.1" +family = "claude-fable" +release_date = "2026-09-01" +last_updated = "2026-09-01" +knowledge = "2026-06" +attachment = true +reasoning = true +tool_call = true +structured_output = true +temperature = false + +# Cache reads on Fable 5.1 bill at 0.025x base input, not the usual 0.1x. +[cost] +input = 10.00 +output = 50.00 +cache_read = 0.25 +cache_write = 12.50 + +[limit] +context = 1000000 +output = 128000 + +[modalities] +input = ["text", "image", "pdf"] +output = ["text"] + +[fleetify] +priority = 45 diff --git a/providers/claude-code/models/claude-fable-5-1.toml b/providers/claude-code/models/claude-fable-5-1.toml new file mode 100644 index 0000000..5cc13f7 --- /dev/null +++ b/providers/claude-code/models/claude-fable-5-1.toml @@ -0,0 +1,12 @@ +[extends] +from = "anthropic/claude-fable-5-1" + +# The `fable` / `best` aliases resolve here from Claude Code v2.1.257 on. +[fleetify] +priority = 65 +label = "Fable 5.1" + +[fleetify.effort] +kind = "levels" +levels = ["low", "medium", "high", "xhigh", "max"] +default = "high" From 065fdb0128271e721ae972e2869d8587b595e1c4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Doruk=20=C3=96zgen?= Date: Mon, 21 Sep 2026 14:30:15 +0300 Subject: [PATCH 02/30] fix(catalog): Sonnet 5 standard pricing is $2 / $10, not $3 / $15 Anthropic made the launch price permanent on 2026-08-10: the increase to $3 / $15 scheduled for 2026-09-01 was cancelled. Record $2 / $10 with the matching cache rates ($0.20 read, $2.50 write) and drop the "introductory pricing through 2026-08-31" note, which now says the opposite of what is true. claude-code inherits both through `extends`. Also fill in Fable 5's knowledge cutoff (2026-01), which the entry lacked. --- providers/anthropic/models/claude-fable-5.toml | 1 + providers/anthropic/models/claude-sonnet-5.toml | 9 ++++----- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/providers/anthropic/models/claude-fable-5.toml b/providers/anthropic/models/claude-fable-5.toml index cbe0905..33c57f3 100644 --- a/providers/anthropic/models/claude-fable-5.toml +++ b/providers/anthropic/models/claude-fable-5.toml @@ -2,6 +2,7 @@ name = "Claude Fable 5" family = "claude-fable" release_date = "2026-06-09" last_updated = "2026-06-09" +knowledge = "2026-01" attachment = true reasoning = true tool_call = true diff --git a/providers/anthropic/models/claude-sonnet-5.toml b/providers/anthropic/models/claude-sonnet-5.toml index ee0a5e2..da382cb 100644 --- a/providers/anthropic/models/claude-sonnet-5.toml +++ b/providers/anthropic/models/claude-sonnet-5.toml @@ -10,10 +10,10 @@ structured_output = true temperature = false [cost] -input = 3.00 -output = 15.00 -cache_read = 0.30 -cache_write = 3.75 +input = 2.00 +output = 10.00 +cache_read = 0.20 +cache_write = 2.50 [limit] context = 1000000 @@ -25,4 +25,3 @@ output = ["text"] [fleetify] priority = 40 -note = "Introductory pricing of $2 / $10 per MTok applies through 2026-08-31." From 72a2d7534be4d01530c8e02daa3f6a191405a8a3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Doruk=20=C3=96zgen?= Date: Mon, 21 Sep 2026 14:32:02 +0300 Subject: [PATCH 03/30] feat(catalog): add Grok 4.6 and Grok Build 0.1 to grok Grok 4.6 went live on the xAI API on 2026-08-12: 500K context, $2 / $6 with $0.50 cached input, knowledge cutoff 2026-02-01. It always reasons, so its effort levels run low -> xhigh (default high) with no `none`. xAI documents no text output limit for it, so `limit.output` is left unset rather than guessed. Grok Build 0.1 is xAI's coding model (256K, $1 / $2) and the redirect target of the retired `grok-code-fast-1` slugs, recorded here as aliases. It reasons but exposes no effort control, hence `effort.kind = "none"`. Grok 4.3 stays the default. Source: docs.x.ai models page and release notes. --- providers/grok/models/grok-4.6.toml | 33 +++++++++++++++++++++++ providers/grok/models/grok-build-0.1.toml | 31 +++++++++++++++++++++ 2 files changed, 64 insertions(+) create mode 100644 providers/grok/models/grok-4.6.toml create mode 100644 providers/grok/models/grok-build-0.1.toml diff --git a/providers/grok/models/grok-4.6.toml b/providers/grok/models/grok-4.6.toml new file mode 100644 index 0000000..475a7ed --- /dev/null +++ b/providers/grok/models/grok-4.6.toml @@ -0,0 +1,33 @@ +name = "Grok 4.6" +family = "grok" +release_date = "2026-08-12" +last_updated = "2026-08-12" +knowledge = "2026-02-01" +attachment = true +reasoning = true +tool_call = true +structured_output = true +temperature = true + +[cost] +input = 2.00 +output = 6.00 +cache_read = 0.50 + +# xAI documents no text output limit for Grok 4.6, so `output` is left unset. +[limit] +context = 500000 + +[modalities] +input = ["text", "image"] +output = ["text"] + +[fleetify] +priority = 50 +note = "Input/output pricing doubles for prompts at or above 200k tokens." + +# Grok 4.6 always reasons: `none` is not an accepted effort. +[fleetify.effort] +kind = "levels" +levels = ["low", "medium", "high", "xhigh"] +default = "high" diff --git a/providers/grok/models/grok-build-0.1.toml b/providers/grok/models/grok-build-0.1.toml new file mode 100644 index 0000000..df4b7f4 --- /dev/null +++ b/providers/grok/models/grok-build-0.1.toml @@ -0,0 +1,31 @@ +name = "Grok Build 0.1" +family = "grok-build" +release_date = "2026-05-19" +last_updated = "2026-05-19" +attachment = true +reasoning = true +tool_call = true +structured_output = true +temperature = true + +[cost] +input = 1.00 +output = 2.00 +cache_read = 0.20 + +[limit] +context = 256000 + +[modalities] +input = ["text", "image"] +output = ["text"] + +# xAI's coding model; the retired `grok-code-fast-1` slugs redirect here. +[fleetify] +priority = 35 +note = "Code" +aliases = ["grok-code-fast-1", "grok-code-fast", "grok-code-fast-1-0825"] + +# Reasons internally but exposes no `reasoning_effort` control. +[fleetify.effort] +kind = "none" From 82b94461e54b2d01a37098691c158ed000df2495 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Doruk=20=C3=96zgen?= Date: Mon, 21 Sep 2026 14:32:02 +0300 Subject: [PATCH 04/30] fix(catalog): align existing Grok entries with xAI's live model data - Grok 4.5 does not accept `reasoning_effort: none` and defaults to high, not low. The old level list let the picker offer an effort the API rejects. Levels are now low / medium / high / xhigh. Release date is 2026-07-08. - Grok 4.3 gained `xhigh`. - Grok 4.20 (both variants) has a 1M max prompt length, not 2M. - Grok 4.3 and 4.20 take text and jpg/png images only; drop the `pdf` input modality, which xAI does not list for any text model. - Record the `-latest` aliases for 4.3 and 4.5. --- .../grok/models/grok-4.20-0309-non-reasoning.toml | 4 ++-- providers/grok/models/grok-4.20-0309-reasoning.toml | 4 ++-- providers/grok/models/grok-4.3.toml | 5 +++-- providers/grok/models/grok-4.5.toml | 10 ++++++---- 4 files changed, 13 insertions(+), 10 deletions(-) diff --git a/providers/grok/models/grok-4.20-0309-non-reasoning.toml b/providers/grok/models/grok-4.20-0309-non-reasoning.toml index 65ee143..b90ee79 100644 --- a/providers/grok/models/grok-4.20-0309-non-reasoning.toml +++ b/providers/grok/models/grok-4.20-0309-non-reasoning.toml @@ -14,11 +14,11 @@ output = 2.50 cache_read = 0.20 [limit] -context = 2000000 +context = 1000000 output = 30000 [modalities] -input = ["text", "image", "pdf"] +input = ["text", "image"] output = ["text"] [fleetify] diff --git a/providers/grok/models/grok-4.20-0309-reasoning.toml b/providers/grok/models/grok-4.20-0309-reasoning.toml index 3f92a6c..405a45b 100644 --- a/providers/grok/models/grok-4.20-0309-reasoning.toml +++ b/providers/grok/models/grok-4.20-0309-reasoning.toml @@ -14,11 +14,11 @@ output = 2.50 cache_read = 0.20 [limit] -context = 2000000 +context = 1000000 output = 30000 [modalities] -input = ["text", "image", "pdf"] +input = ["text", "image"] output = ["text"] [fleetify] diff --git a/providers/grok/models/grok-4.3.toml b/providers/grok/models/grok-4.3.toml index 7331bbe..fefcf21 100644 --- a/providers/grok/models/grok-4.3.toml +++ b/providers/grok/models/grok-4.3.toml @@ -18,14 +18,15 @@ context = 1000000 output = 30000 [modalities] -input = ["text", "image", "pdf"] +input = ["text", "image"] output = ["text"] [fleetify] priority = 30 default = true +aliases = ["grok-4.3-latest"] [fleetify.effort] kind = "levels" -levels = ["none", "low", "medium", "high"] +levels = ["none", "low", "medium", "high", "xhigh"] default = "low" diff --git a/providers/grok/models/grok-4.5.toml b/providers/grok/models/grok-4.5.toml index 5d3d2dc..88c1e10 100644 --- a/providers/grok/models/grok-4.5.toml +++ b/providers/grok/models/grok-4.5.toml @@ -1,7 +1,7 @@ name = "Grok 4.5" family = "grok" -release_date = "2026-07-09" -last_updated = "2026-07-09" +release_date = "2026-07-08" +last_updated = "2026-07-08" attachment = true reasoning = true tool_call = true @@ -24,8 +24,10 @@ output = ["text"] [fleetify] priority = 40 note = "Input/output pricing doubles for prompts at or above 200k tokens." +aliases = ["grok-4.5-latest"] +# Grok 4.5 always reasons: `none` is not an accepted effort. [fleetify.effort] kind = "levels" -levels = ["none", "low", "medium", "high"] -default = "low" +levels = ["low", "medium", "high", "xhigh"] +default = "high" From cc0a7d86ee2a7004e6cbd367476faecf3ea99637 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Doruk=20=C3=96zgen?= Date: Mon, 21 Sep 2026 14:32:33 +0300 Subject: [PATCH 05/30] feat(catalog)!: DeepSeek V4.1 Flash replaces V4 Flash as `deepseek-flash` DeepSeek released V4.1 Flash on 2026-09-10 under a new canonical id, `deepseek-flash`, and retired V4 Flash and the short-lived V4 Flash Vision Exp the same day. The old slugs still resolve upstream, so they are kept as aliases rather than as separate entries. V4.1 Flash adds native image input and a `reasoning_effort` control (low / high / max, default high). V4 Pro is still served as the 0813 GA snapshot: DeepSeek announced it would reroute to V4.1 Flash on 2026-09-14, then reversed that in the changelog. Its pricing moved with GA, so refresh it and declare the same effort levels. DeepSeek now bills peak and off-peak rates. `cost` records the peak list price and a note carries the off-peak halving, since the schema has one price tier. The default moves to `deepseek-flash`: it is the model DeepSeek now recommends and V4 Pro is being phased out ahead of a V4.1 Pro. BREAKING CHANGE: the `deepseek-v4-flash` model id is gone from the deepseek provider. Sessions pinned to it heal to the provider default. Source: api-docs.deepseek.com pricing, news260910, updates, thinking_mode. --- providers/deepseek/models/deepseek-flash.toml | 38 +++++++++++++++++++ .../deepseek/models/deepseek-v4-flash.toml | 27 ------------- .../deepseek/models/deepseek-v4-pro.toml | 17 ++++++--- 3 files changed, 50 insertions(+), 32 deletions(-) create mode 100644 providers/deepseek/models/deepseek-flash.toml delete mode 100644 providers/deepseek/models/deepseek-v4-flash.toml diff --git a/providers/deepseek/models/deepseek-flash.toml b/providers/deepseek/models/deepseek-flash.toml new file mode 100644 index 0000000..969be1b --- /dev/null +++ b/providers/deepseek/models/deepseek-flash.toml @@ -0,0 +1,38 @@ +name = "DeepSeek V4.1 Flash" +family = "deepseek-flash" +release_date = "2026-09-10" +last_updated = "2026-09-10" +attachment = true +reasoning = true +tool_call = true +structured_output = true +temperature = true +open_weights = true + +# Peak-hour list price; see the note below. +[cost] +input = 0.30 +output = 1.20 +cache_read = 0.006 + +[limit] +context = 1000000 +output = 384000 + +[modalities] +input = ["text", "image"] +output = ["text"] + +# `deepseek-flash` is the canonical id since V4.1. The V4 Flash models were +# retired on 2026-09-10; their slugs still resolve here and bill at this rate. +[fleetify] +priority = 30 +default = true +note = "Peak-hour pricing. Rates halve off-peak (outside 01:00-04:00 and 06:00-10:00 UTC, Mon-Fri)." +aliases = ["deepseek-v4-flash", "deepseek-v4-flash-vision-exp"] + +# Thinking is on by default; `reasoning_effort` selects the depth. +[fleetify.effort] +kind = "levels" +levels = ["low", "high", "max"] +default = "high" diff --git a/providers/deepseek/models/deepseek-v4-flash.toml b/providers/deepseek/models/deepseek-v4-flash.toml deleted file mode 100644 index 0e73c82..0000000 --- a/providers/deepseek/models/deepseek-v4-flash.toml +++ /dev/null @@ -1,27 +0,0 @@ -name = "DeepSeek V4 Flash" -family = "deepseek-flash" -release_date = "2026-04-24" -last_updated = "2026-04-24" -knowledge = "2025-05" -attachment = false -reasoning = true -tool_call = true -structured_output = true -temperature = true -open_weights = true - -[cost] -input = 0.14 -output = 0.28 -cache_read = 0.0028 - -[limit] -context = 1000000 -output = 384000 - -[modalities] -input = ["text"] -output = ["text"] - -[fleetify] -priority = 10 diff --git a/providers/deepseek/models/deepseek-v4-pro.toml b/providers/deepseek/models/deepseek-v4-pro.toml index 6d448dc..04e7cf7 100644 --- a/providers/deepseek/models/deepseek-v4-pro.toml +++ b/providers/deepseek/models/deepseek-v4-pro.toml @@ -1,7 +1,7 @@ name = "DeepSeek V4 Pro" family = "deepseek-thinking" release_date = "2026-04-24" -last_updated = "2026-04-24" +last_updated = "2026-08-13" knowledge = "2025-05" attachment = false reasoning = true @@ -10,10 +10,11 @@ structured_output = true temperature = true open_weights = true +# Peak-hour list price, in effect since the 0813 GA snapshot. [cost] -input = 0.435 -output = 0.87 -cache_read = 0.003625 +input = 1.32 +output = 3.96 +cache_read = 0.044 [limit] context = 1000000 @@ -25,4 +26,10 @@ output = ["text"] [fleetify] priority = 20 -default = true +note = "Peak-hour pricing. Rates halve off-peak (outside 01:00-04:00 and 06:00-10:00 UTC, Mon-Fri)." + +# Thinking is on by default; `reasoning_effort` selects the depth. +[fleetify.effort] +kind = "levels" +levels = ["low", "high", "max"] +default = "high" From 303b117ce8efad61bd11951d5155c1dd289483a8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Doruk=20=C3=96zgen?= Date: Mon, 21 Sep 2026 14:34:58 +0300 Subject: [PATCH 06/30] feat(catalog): add GPT-6 Astra to codex-cli OpenAI released GPT-6 Astra on 2026-09-03: 1.05M context, 128K output, $10 / $50 with $1 cached input and $12.50 cache writes, knowledge cutoff 2026-04-30. It rejects the `none` effort and custom `temperature`. The Codex docs list it for the CLI (`codex -m gpt-6-astra`) but not for Codex cloud, and gate its Enterprise rollout, so GPT-5.6 Sol stays the default and Astra sits directly beneath it. Not added to the `openai` API provider yet: OpenAI's model guide states that "GPT-6 Astra supports Chat Completions, but tool calling requires Responses", and the app's OpenAI bridge speaks Chat Completions. Listing it there would offer a coding agent that cannot call tools. There is no `gpt-6-astra-pro` API id (the model page 404s); "Pro" is the `reasoning.mode = "pro"` setting on the same model. Source: developers.openai.com model page, model guide, changelog; Codex models. --- providers/codex-cli/models/gpt-6-astra.toml | 37 +++++++++++++++++++++ 1 file changed, 37 insertions(+) create mode 100644 providers/codex-cli/models/gpt-6-astra.toml diff --git a/providers/codex-cli/models/gpt-6-astra.toml b/providers/codex-cli/models/gpt-6-astra.toml new file mode 100644 index 0000000..cbc95e9 --- /dev/null +++ b/providers/codex-cli/models/gpt-6-astra.toml @@ -0,0 +1,37 @@ +name = "GPT-6 Astra" +family = "gpt" +release_date = "2026-09-03" +last_updated = "2026-09-03" +knowledge = "2026-04-30" +attachment = true +reasoning = true +tool_call = true +structured_output = true +temperature = false + +[cost] +input = 10.00 +output = 50.00 +cache_read = 1.00 +cache_write = 12.50 + +[limit] +context = 1050000 +output = 128000 + +[modalities] +input = ["text", "image"] +output = ["text"] + +# Runs in the Codex CLI (`codex -m gpt-6-astra`) but not in Codex cloud, so +# GPT-5.6 Sol stays the default. +[fleetify] +priority = 85 +note = "Most capable" + +# Astra has no `none` effort. `ultra` is Codex's top tier: max reasoning plus +# automatic task delegation. +[fleetify.effort] +kind = "levels" +levels = ["low", "medium", "high", "xhigh", "max", "ultra"] +default = "medium" From d902aabff843bbabaa916a25be6f58eba755874e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Doruk=20=C3=96zgen?= Date: Mon, 21 Sep 2026 14:34:58 +0300 Subject: [PATCH 07/30] fix(catalog): GPT-5.6 Sol price cut and OpenAI effort levels - GPT-5.6 Sol dropped to $4 / $20 ($0.40 cached) on 2026-08-21. OpenAI calls it promotional pricing guaranteed through 2026-11-21, so a note carries the expiry and the previous $5 / $30 rate. Applies to openai and codex-cli. - GPT-5.4, 5.4 mini, 5.4 nano and 5.5 do not accept `reasoning.effort: minimal`. Their documented levels are none / low / medium / high / xhigh. The picker default stays `medium`, which all four accept. - codex-cli's GPT-5.5 has the same 1.05M context window as the API model; the two entries disagreed (400K vs 1.05M). --- providers/codex-cli/models/gpt-5.5.toml | 2 +- providers/codex-cli/models/gpt-5.6-sol.toml | 9 +++++---- providers/openai/models/gpt-5.4-mini.toml | 2 +- providers/openai/models/gpt-5.4-nano.toml | 2 +- providers/openai/models/gpt-5.4.toml | 2 +- providers/openai/models/gpt-5.5.toml | 2 +- providers/openai/models/gpt-5.6-sol.toml | 9 +++++---- 7 files changed, 15 insertions(+), 13 deletions(-) diff --git a/providers/codex-cli/models/gpt-5.5.toml b/providers/codex-cli/models/gpt-5.5.toml index 405ee0b..717c340 100644 --- a/providers/codex-cli/models/gpt-5.5.toml +++ b/providers/codex-cli/models/gpt-5.5.toml @@ -15,7 +15,7 @@ output = 30.00 cache_read = 0.50 [limit] -context = 400000 +context = 1050000 output = 128000 [modalities] diff --git a/providers/codex-cli/models/gpt-5.6-sol.toml b/providers/codex-cli/models/gpt-5.6-sol.toml index 7d101c8..6626d11 100644 --- a/providers/codex-cli/models/gpt-5.6-sol.toml +++ b/providers/codex-cli/models/gpt-5.6-sol.toml @@ -1,7 +1,7 @@ name = "GPT-5.6 Sol" family = "gpt" release_date = "2026-07-09" -last_updated = "2026-07-09" +last_updated = "2026-08-21" knowledge = "2026-02-16" attachment = true reasoning = true @@ -10,9 +10,9 @@ structured_output = true temperature = false [cost] -input = 5.00 -output = 30.00 -cache_read = 0.50 +input = 4.00 +output = 20.00 +cache_read = 0.40 [limit] context = 1050000 @@ -24,6 +24,7 @@ output = ["text"] [fleetify] priority = 90 +note = "Promotional pricing, guaranteed through 2026-11-21 (was $5 / $30)." default = true aliases = ["gpt-5.6"] diff --git a/providers/openai/models/gpt-5.4-mini.toml b/providers/openai/models/gpt-5.4-mini.toml index 713f133..8dab4ca 100644 --- a/providers/openai/models/gpt-5.4-mini.toml +++ b/providers/openai/models/gpt-5.4-mini.toml @@ -27,5 +27,5 @@ priority = 40 [fleetify.effort] kind = "levels" -levels = ["minimal", "low", "medium", "high"] +levels = ["none", "low", "medium", "high", "xhigh"] default = "medium" diff --git a/providers/openai/models/gpt-5.4-nano.toml b/providers/openai/models/gpt-5.4-nano.toml index 8b8ed92..37fc737 100644 --- a/providers/openai/models/gpt-5.4-nano.toml +++ b/providers/openai/models/gpt-5.4-nano.toml @@ -27,5 +27,5 @@ priority = 20 [fleetify.effort] kind = "levels" -levels = ["minimal", "low", "medium", "high"] +levels = ["none", "low", "medium", "high", "xhigh"] default = "medium" diff --git a/providers/openai/models/gpt-5.4.toml b/providers/openai/models/gpt-5.4.toml index b7d9cc9..a334288 100644 --- a/providers/openai/models/gpt-5.4.toml +++ b/providers/openai/models/gpt-5.4.toml @@ -27,5 +27,5 @@ priority = 60 [fleetify.effort] kind = "levels" -levels = ["minimal", "low", "medium", "high"] +levels = ["none", "low", "medium", "high", "xhigh"] default = "medium" diff --git a/providers/openai/models/gpt-5.5.toml b/providers/openai/models/gpt-5.5.toml index de430e0..3115d82 100644 --- a/providers/openai/models/gpt-5.5.toml +++ b/providers/openai/models/gpt-5.5.toml @@ -28,5 +28,5 @@ default = true [fleetify.effort] kind = "levels" -levels = ["minimal", "low", "medium", "high"] +levels = ["none", "low", "medium", "high", "xhigh"] default = "medium" diff --git a/providers/openai/models/gpt-5.6-sol.toml b/providers/openai/models/gpt-5.6-sol.toml index ecd38aa..40acf3b 100644 --- a/providers/openai/models/gpt-5.6-sol.toml +++ b/providers/openai/models/gpt-5.6-sol.toml @@ -1,7 +1,7 @@ name = "GPT-5.6 Sol" family = "gpt" release_date = "2026-07-09" -last_updated = "2026-07-09" +last_updated = "2026-08-21" knowledge = "2026-02-16" attachment = true reasoning = true @@ -10,9 +10,9 @@ structured_output = true temperature = false [cost] -input = 5.00 -output = 30.00 -cache_read = 0.50 +input = 4.00 +output = 20.00 +cache_read = 0.40 [limit] context = 1050000 @@ -24,6 +24,7 @@ output = ["text"] [fleetify] priority = 100 +note = "Promotional pricing, guaranteed through 2026-11-21 (was $5 / $30)." aliases = ["gpt-5.6"] [fleetify.effort] From 61bef7c89f75504a22fd2343a673565636dcb3fe Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Doruk=20=C3=96zgen?= Date: Mon, 21 Sep 2026 14:34:58 +0300 Subject: [PATCH 08/30] feat(catalog)!: drop GPT-5.4 mini from codex-cli OpenAI retired GPT-5.4 and GPT-5.4 mini from Codex on 2026-08-31; GPT-5.6 Luna is the documented replacement and is already in the lineup. GPT-5.4 itself left this provider in the previous refresh. The model is still served on the API, so the `openai` entry is untouched. GPT-5.5 is scheduled to leave Codex on 2026-10-14 and stays until then. BREAKING CHANGE: `gpt-5.4-mini` is gone from the codex-cli provider. Sessions pinned to it heal to the provider default. --- providers/codex-cli/models/gpt-5.4-mini.toml | 31 -------------------- 1 file changed, 31 deletions(-) delete mode 100644 providers/codex-cli/models/gpt-5.4-mini.toml diff --git a/providers/codex-cli/models/gpt-5.4-mini.toml b/providers/codex-cli/models/gpt-5.4-mini.toml deleted file mode 100644 index 823f082..0000000 --- a/providers/codex-cli/models/gpt-5.4-mini.toml +++ /dev/null @@ -1,31 +0,0 @@ -name = "GPT-5.4 mini" -family = "gpt-mini" -release_date = "2026-03-17" -last_updated = "2026-03-17" -knowledge = "2025-08-31" -attachment = true -reasoning = true -tool_call = true -structured_output = true -temperature = false - -[cost] -input = 0.75 -output = 4.50 -cache_read = 0.075 - -[limit] -context = 400000 -output = 128000 - -[modalities] -input = ["text", "image"] -output = ["text"] - -[fleetify] -priority = 20 - -[fleetify.effort] -kind = "levels" -levels = ["low", "medium", "high", "xhigh"] -default = "medium" From 2f53f5b45dd526f238f617791c9576e28e381871 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Doruk=20=C3=96zgen?= Date: Mon, 21 Sep 2026 14:35:51 +0300 Subject: [PATCH 09/30] feat(catalog): add Gemini 3.7 Flash and 3.8 Flash to gemini-api and antigravity-sdk Both went GA on the Gemini API (3.7 on 2026-08-13, 3.8 on 2026-09-02) with a 1,048,576 / 65,536 token window and a March 2026 knowledge cutoff. They accept `thinking_level` low / medium / high, default medium; `minimal` is rejected. Antigravity's model picker offers each at Low, Medium and High, so antigravity-sdk gets the usual three tier-suffixed slugs per model. The `-high` and `-medium` slugs appear in the documented `agy models` output; the `-low` slugs follow the same pattern as the existing 3.6 Flash entries. `cost` records the $0.75 / $3.75 introductory rate that is billed today, with a note for the scheduled move to $1.50 / $7.50 on 2027-01-01. There is still no Pro model newer than 3.1 Pro Preview, which stays the default on both providers. Source: ai.google.dev models, pricing, changelog and thinking docs; DeepMind model cards; antigravity.google docs/models and CLI docs. --- .../models/gemini-3.7-flash-high.toml | 29 ++++++++++++++++ .../models/gemini-3.7-flash-low.toml | 29 ++++++++++++++++ .../models/gemini-3.7-flash-medium.toml | 29 ++++++++++++++++ .../models/gemini-3.8-flash-high.toml | 29 ++++++++++++++++ .../models/gemini-3.8-flash-low.toml | 29 ++++++++++++++++ .../models/gemini-3.8-flash-medium.toml | 29 ++++++++++++++++ .../gemini-api/models/gemini-3.7-flash.toml | 33 +++++++++++++++++++ .../gemini-api/models/gemini-3.8-flash.toml | 33 +++++++++++++++++++ 8 files changed, 240 insertions(+) create mode 100644 providers/antigravity-sdk/models/gemini-3.7-flash-high.toml create mode 100644 providers/antigravity-sdk/models/gemini-3.7-flash-low.toml create mode 100644 providers/antigravity-sdk/models/gemini-3.7-flash-medium.toml create mode 100644 providers/antigravity-sdk/models/gemini-3.8-flash-high.toml create mode 100644 providers/antigravity-sdk/models/gemini-3.8-flash-low.toml create mode 100644 providers/antigravity-sdk/models/gemini-3.8-flash-medium.toml create mode 100644 providers/gemini-api/models/gemini-3.7-flash.toml create mode 100644 providers/gemini-api/models/gemini-3.8-flash.toml diff --git a/providers/antigravity-sdk/models/gemini-3.7-flash-high.toml b/providers/antigravity-sdk/models/gemini-3.7-flash-high.toml new file mode 100644 index 0000000..edcc2d5 --- /dev/null +++ b/providers/antigravity-sdk/models/gemini-3.7-flash-high.toml @@ -0,0 +1,29 @@ +name = "Gemini 3.7 Flash" +family = "gemini-flash" +release_date = "2026-08-13" +last_updated = "2026-08-13" +knowledge = "2026-03" +attachment = true +reasoning = true +tool_call = true +structured_output = true +temperature = true + +[cost] +input = 0.75 +output = 3.75 +cache_read = 0.075 + +[limit] +context = 1048576 +output = 65536 + +[modalities] +input = ["text", "image", "video", "audio", "pdf"] +output = ["text"] + +[fleetify] +priority = 130 +label = "Gemini 3.7 Flash (High)" +supports_effort = false +note = "Introductory pricing through 2026-12-31; $1.50 / $7.50 per MTok from 2027-01-01." diff --git a/providers/antigravity-sdk/models/gemini-3.7-flash-low.toml b/providers/antigravity-sdk/models/gemini-3.7-flash-low.toml new file mode 100644 index 0000000..36424f1 --- /dev/null +++ b/providers/antigravity-sdk/models/gemini-3.7-flash-low.toml @@ -0,0 +1,29 @@ +name = "Gemini 3.7 Flash" +family = "gemini-flash" +release_date = "2026-08-13" +last_updated = "2026-08-13" +knowledge = "2026-03" +attachment = true +reasoning = true +tool_call = true +structured_output = true +temperature = true + +[cost] +input = 0.75 +output = 3.75 +cache_read = 0.075 + +[limit] +context = 1048576 +output = 65536 + +[modalities] +input = ["text", "image", "video", "audio", "pdf"] +output = ["text"] + +[fleetify] +priority = 110 +label = "Gemini 3.7 Flash (Low)" +supports_effort = false +note = "Introductory pricing through 2026-12-31; $1.50 / $7.50 per MTok from 2027-01-01." diff --git a/providers/antigravity-sdk/models/gemini-3.7-flash-medium.toml b/providers/antigravity-sdk/models/gemini-3.7-flash-medium.toml new file mode 100644 index 0000000..2ddac84 --- /dev/null +++ b/providers/antigravity-sdk/models/gemini-3.7-flash-medium.toml @@ -0,0 +1,29 @@ +name = "Gemini 3.7 Flash" +family = "gemini-flash" +release_date = "2026-08-13" +last_updated = "2026-08-13" +knowledge = "2026-03" +attachment = true +reasoning = true +tool_call = true +structured_output = true +temperature = true + +[cost] +input = 0.75 +output = 3.75 +cache_read = 0.075 + +[limit] +context = 1048576 +output = 65536 + +[modalities] +input = ["text", "image", "video", "audio", "pdf"] +output = ["text"] + +[fleetify] +priority = 120 +label = "Gemini 3.7 Flash (Medium)" +supports_effort = false +note = "Introductory pricing through 2026-12-31; $1.50 / $7.50 per MTok from 2027-01-01." diff --git a/providers/antigravity-sdk/models/gemini-3.8-flash-high.toml b/providers/antigravity-sdk/models/gemini-3.8-flash-high.toml new file mode 100644 index 0000000..f53a4f0 --- /dev/null +++ b/providers/antigravity-sdk/models/gemini-3.8-flash-high.toml @@ -0,0 +1,29 @@ +name = "Gemini 3.8 Flash" +family = "gemini-flash" +release_date = "2026-09-02" +last_updated = "2026-09-02" +knowledge = "2026-03" +attachment = true +reasoning = true +tool_call = true +structured_output = true +temperature = true + +[cost] +input = 0.75 +output = 3.75 +cache_read = 0.075 + +[limit] +context = 1048576 +output = 65536 + +[modalities] +input = ["text", "image", "video", "audio", "pdf"] +output = ["text"] + +[fleetify] +priority = 160 +label = "Gemini 3.8 Flash (High)" +supports_effort = false +note = "Introductory pricing through 2026-12-31; $1.50 / $7.50 per MTok from 2027-01-01." diff --git a/providers/antigravity-sdk/models/gemini-3.8-flash-low.toml b/providers/antigravity-sdk/models/gemini-3.8-flash-low.toml new file mode 100644 index 0000000..500bc1a --- /dev/null +++ b/providers/antigravity-sdk/models/gemini-3.8-flash-low.toml @@ -0,0 +1,29 @@ +name = "Gemini 3.8 Flash" +family = "gemini-flash" +release_date = "2026-09-02" +last_updated = "2026-09-02" +knowledge = "2026-03" +attachment = true +reasoning = true +tool_call = true +structured_output = true +temperature = true + +[cost] +input = 0.75 +output = 3.75 +cache_read = 0.075 + +[limit] +context = 1048576 +output = 65536 + +[modalities] +input = ["text", "image", "video", "audio", "pdf"] +output = ["text"] + +[fleetify] +priority = 140 +label = "Gemini 3.8 Flash (Low)" +supports_effort = false +note = "Introductory pricing through 2026-12-31; $1.50 / $7.50 per MTok from 2027-01-01." diff --git a/providers/antigravity-sdk/models/gemini-3.8-flash-medium.toml b/providers/antigravity-sdk/models/gemini-3.8-flash-medium.toml new file mode 100644 index 0000000..575e1ad --- /dev/null +++ b/providers/antigravity-sdk/models/gemini-3.8-flash-medium.toml @@ -0,0 +1,29 @@ +name = "Gemini 3.8 Flash" +family = "gemini-flash" +release_date = "2026-09-02" +last_updated = "2026-09-02" +knowledge = "2026-03" +attachment = true +reasoning = true +tool_call = true +structured_output = true +temperature = true + +[cost] +input = 0.75 +output = 3.75 +cache_read = 0.075 + +[limit] +context = 1048576 +output = 65536 + +[modalities] +input = ["text", "image", "video", "audio", "pdf"] +output = ["text"] + +[fleetify] +priority = 150 +label = "Gemini 3.8 Flash (Medium)" +supports_effort = false +note = "Introductory pricing through 2026-12-31; $1.50 / $7.50 per MTok from 2027-01-01." diff --git a/providers/gemini-api/models/gemini-3.7-flash.toml b/providers/gemini-api/models/gemini-3.7-flash.toml new file mode 100644 index 0000000..501a7f5 --- /dev/null +++ b/providers/gemini-api/models/gemini-3.7-flash.toml @@ -0,0 +1,33 @@ +name = "Gemini 3.7 Flash" +family = "gemini-flash" +release_date = "2026-08-13" +last_updated = "2026-08-13" +knowledge = "2026-03" +attachment = true +reasoning = true +tool_call = true +structured_output = true +temperature = true + +[cost] +input = 0.75 +output = 3.75 +cache_read = 0.075 + +[limit] +context = 1048576 +output = 65536 + +[modalities] +input = ["text", "image", "video", "audio", "pdf"] +output = ["text"] + +[fleetify] +priority = 90 +note = "Introductory pricing through 2026-12-31; $1.50 / $7.50 per MTok from 2027-01-01." + +# `minimal` is rejected on 3.7 Flash; thinking defaults to medium. +[fleetify.effort] +kind = "thinking_level" +levels = ["low", "medium", "high"] +default = "medium" diff --git a/providers/gemini-api/models/gemini-3.8-flash.toml b/providers/gemini-api/models/gemini-3.8-flash.toml new file mode 100644 index 0000000..054de17 --- /dev/null +++ b/providers/gemini-api/models/gemini-3.8-flash.toml @@ -0,0 +1,33 @@ +name = "Gemini 3.8 Flash" +family = "gemini-flash" +release_date = "2026-09-02" +last_updated = "2026-09-02" +knowledge = "2026-03" +attachment = true +reasoning = true +tool_call = true +structured_output = true +temperature = true + +[cost] +input = 0.75 +output = 3.75 +cache_read = 0.075 + +[limit] +context = 1048576 +output = 65536 + +[modalities] +input = ["text", "image", "video", "audio", "pdf"] +output = ["text"] + +[fleetify] +priority = 100 +note = "Introductory pricing through 2026-12-31; $1.50 / $7.50 per MTok from 2027-01-01." + +# `minimal` is rejected on 3.8 Flash; thinking defaults to medium. +[fleetify.effort] +kind = "thinking_level" +levels = ["low", "medium", "high"] +default = "medium" From 42647c81c5fce6bdd95c9ba4b3dcd6be1e9a8a2e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Doruk=20=C3=96zgen?= Date: Mon, 21 Sep 2026 14:36:00 +0300 Subject: [PATCH 10/30] fix(catalog): Gemini 3.6 Flash bills $0.75 / $3.75 through 2026-12-31 The catalog carried $1.50 / $7.50 / $0.15, which is the rate Google has scheduled for 2027-01-01. The pricing page bills half that until the end of the year. Record today's rate on gemini-api and the three antigravity-sdk tiers, with a note for the scheduled increase. Also fill in Gemini 3.5 Flash-Lite's knowledge cutoff (2026-03, per its model card), which the entry lacked. --- .../antigravity-sdk/models/gemini-3.6-flash-high.toml | 7 ++++--- providers/antigravity-sdk/models/gemini-3.6-flash-low.toml | 7 ++++--- .../antigravity-sdk/models/gemini-3.6-flash-medium.toml | 7 ++++--- providers/gemini-api/models/gemini-3.5-flash-lite.toml | 1 + providers/gemini-api/models/gemini-3.6-flash.toml | 7 ++++--- 5 files changed, 17 insertions(+), 12 deletions(-) diff --git a/providers/antigravity-sdk/models/gemini-3.6-flash-high.toml b/providers/antigravity-sdk/models/gemini-3.6-flash-high.toml index 9634b41..6996903 100644 --- a/providers/antigravity-sdk/models/gemini-3.6-flash-high.toml +++ b/providers/antigravity-sdk/models/gemini-3.6-flash-high.toml @@ -10,9 +10,9 @@ structured_output = true temperature = true [cost] -input = 1.50 -output = 7.50 -cache_read = 0.15 +input = 0.75 +output = 3.75 +cache_read = 0.075 [limit] context = 1048576 @@ -26,3 +26,4 @@ output = ["text"] priority = 100 label = "Gemini 3.6 Flash (High)" supports_effort = false +note = "Introductory pricing through 2026-12-31; $1.50 / $7.50 per MTok from 2027-01-01." diff --git a/providers/antigravity-sdk/models/gemini-3.6-flash-low.toml b/providers/antigravity-sdk/models/gemini-3.6-flash-low.toml index f23aea4..dd23058 100644 --- a/providers/antigravity-sdk/models/gemini-3.6-flash-low.toml +++ b/providers/antigravity-sdk/models/gemini-3.6-flash-low.toml @@ -10,9 +10,9 @@ structured_output = true temperature = true [cost] -input = 1.50 -output = 7.50 -cache_read = 0.15 +input = 0.75 +output = 3.75 +cache_read = 0.075 [limit] context = 1048576 @@ -26,3 +26,4 @@ output = ["text"] priority = 80 label = "Gemini 3.6 Flash (Low)" supports_effort = false +note = "Introductory pricing through 2026-12-31; $1.50 / $7.50 per MTok from 2027-01-01." diff --git a/providers/antigravity-sdk/models/gemini-3.6-flash-medium.toml b/providers/antigravity-sdk/models/gemini-3.6-flash-medium.toml index e06dbf3..4415511 100644 --- a/providers/antigravity-sdk/models/gemini-3.6-flash-medium.toml +++ b/providers/antigravity-sdk/models/gemini-3.6-flash-medium.toml @@ -10,9 +10,9 @@ structured_output = true temperature = true [cost] -input = 1.50 -output = 7.50 -cache_read = 0.15 +input = 0.75 +output = 3.75 +cache_read = 0.075 [limit] context = 1048576 @@ -26,3 +26,4 @@ output = ["text"] priority = 90 label = "Gemini 3.6 Flash (Medium)" supports_effort = false +note = "Introductory pricing through 2026-12-31; $1.50 / $7.50 per MTok from 2027-01-01." diff --git a/providers/gemini-api/models/gemini-3.5-flash-lite.toml b/providers/gemini-api/models/gemini-3.5-flash-lite.toml index fd0f24a..322f922 100644 --- a/providers/gemini-api/models/gemini-3.5-flash-lite.toml +++ b/providers/gemini-api/models/gemini-3.5-flash-lite.toml @@ -2,6 +2,7 @@ name = "Gemini 3.5 Flash Lite" family = "gemini-flash-lite" release_date = "2026-07-21" last_updated = "2026-07-21" +knowledge = "2026-03" attachment = true reasoning = true tool_call = true diff --git a/providers/gemini-api/models/gemini-3.6-flash.toml b/providers/gemini-api/models/gemini-3.6-flash.toml index 1e7b8f6..098455a 100644 --- a/providers/gemini-api/models/gemini-3.6-flash.toml +++ b/providers/gemini-api/models/gemini-3.6-flash.toml @@ -10,9 +10,9 @@ structured_output = true temperature = true [cost] -input = 1.50 -output = 7.50 -cache_read = 0.15 +input = 0.75 +output = 3.75 +cache_read = 0.075 [limit] context = 1048576 @@ -24,6 +24,7 @@ output = ["text"] [fleetify] priority = 80 +note = "Introductory pricing through 2026-12-31; $1.50 / $7.50 per MTok from 2027-01-01." [fleetify.effort] kind = "thinking_level" From eb9736befaa79002692ff066c68a70755ba06f25 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Doruk=20=C3=96zgen?= Date: Mon, 21 Sep 2026 14:36:00 +0300 Subject: [PATCH 11/30] feat(catalog)!: drop Gemini 3.5 Flash from antigravity-sdk Antigravity's model picker now lists Gemini 3.8, 3.7 and 3.6 Flash, Gemini 3.1 Pro, the two Claude 4.6 thinking models and GPT-OSS 120B. Gemini 3.5 Flash is absent from both the plan-availability table and the selector, so its three tier slugs go. The model is still served on the Gemini API and keeps its gemini-api entry. BREAKING CHANGE: `gemini-3.5-flash-high`, `-medium` and `-low` are gone from the antigravity-sdk provider. Sessions pinned to them heal to the default. --- .../models/gemini-3.5-flash-high.toml | 28 ------------------- .../models/gemini-3.5-flash-low.toml | 28 ------------------- .../models/gemini-3.5-flash-medium.toml | 28 ------------------- 3 files changed, 84 deletions(-) delete mode 100644 providers/antigravity-sdk/models/gemini-3.5-flash-high.toml delete mode 100644 providers/antigravity-sdk/models/gemini-3.5-flash-low.toml delete mode 100644 providers/antigravity-sdk/models/gemini-3.5-flash-medium.toml diff --git a/providers/antigravity-sdk/models/gemini-3.5-flash-high.toml b/providers/antigravity-sdk/models/gemini-3.5-flash-high.toml deleted file mode 100644 index d03d781..0000000 --- a/providers/antigravity-sdk/models/gemini-3.5-flash-high.toml +++ /dev/null @@ -1,28 +0,0 @@ -name = "Gemini 3.5 Flash" -family = "gemini-flash" -release_date = "2026-05-19" -last_updated = "2026-05-19" -knowledge = "2025-01" -attachment = true -reasoning = true -tool_call = true -structured_output = true -temperature = true - -[cost] -input = 1.50 -output = 9.00 -cache_read = 0.15 - -[limit] -context = 1048576 -output = 65536 - -[modalities] -input = ["text", "image", "video", "audio", "pdf"] -output = ["text"] - -[fleetify] -priority = 50 -label = "Gemini 3.5 Flash (High)" -supports_effort = false diff --git a/providers/antigravity-sdk/models/gemini-3.5-flash-low.toml b/providers/antigravity-sdk/models/gemini-3.5-flash-low.toml deleted file mode 100644 index 7939882..0000000 --- a/providers/antigravity-sdk/models/gemini-3.5-flash-low.toml +++ /dev/null @@ -1,28 +0,0 @@ -name = "Gemini 3.5 Flash" -family = "gemini-flash" -release_date = "2026-05-19" -last_updated = "2026-05-19" -knowledge = "2025-01" -attachment = true -reasoning = true -tool_call = true -structured_output = true -temperature = true - -[cost] -input = 1.50 -output = 9.00 -cache_read = 0.15 - -[limit] -context = 1048576 -output = 65536 - -[modalities] -input = ["text", "image", "video", "audio", "pdf"] -output = ["text"] - -[fleetify] -priority = 35 -label = "Gemini 3.5 Flash (Low)" -supports_effort = false diff --git a/providers/antigravity-sdk/models/gemini-3.5-flash-medium.toml b/providers/antigravity-sdk/models/gemini-3.5-flash-medium.toml deleted file mode 100644 index a9d9f3e..0000000 --- a/providers/antigravity-sdk/models/gemini-3.5-flash-medium.toml +++ /dev/null @@ -1,28 +0,0 @@ -name = "Gemini 3.5 Flash" -family = "gemini-flash" -release_date = "2026-05-19" -last_updated = "2026-05-19" -knowledge = "2025-01" -attachment = true -reasoning = true -tool_call = true -structured_output = true -temperature = true - -[cost] -input = 1.50 -output = 9.00 -cache_read = 0.15 - -[limit] -context = 1048576 -output = 65536 - -[modalities] -input = ["text", "image", "video", "audio", "pdf"] -output = ["text"] - -[fleetify] -priority = 40 -label = "Gemini 3.5 Flash (Medium)" -supports_effort = false From 24c139b158a98b2edcce798317c7ad88ba2cc162 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Doruk=20=C3=96zgen?= Date: Mon, 21 Sep 2026 14:37:45 +0300 Subject: [PATCH 12/30] feat(catalog): add Z.ai GLM 5.3 to mistral Mistral started hosting Z.ai's GLM 5.3 on 2026-09-15 as a third-party, open-weights model served without modification: 1M context, 128K output, $1.40 / $4.40 with $0.14 cached input, text only, function calling and structured outputs. It is in public preview, so the entry uses the pinned id `zai-glm-5-3` and records `zai-glm-5` / `zai-glm-latest` as aliases. Mistral documents no reasoning-effort control for it, hence `effort.kind = "none"`. Mistral has shipped no first-party frontier model since Medium 3.5 (2026-04-28), and the Devstral and Magistral families are fully retired. Source: docs.mistral.ai model pages, changelog and lifecycle policy. --- providers/mistral/models/zai-glm-5-3.toml | 34 +++++++++++++++++++++++ 1 file changed, 34 insertions(+) create mode 100644 providers/mistral/models/zai-glm-5-3.toml diff --git a/providers/mistral/models/zai-glm-5-3.toml b/providers/mistral/models/zai-glm-5-3.toml new file mode 100644 index 0000000..7f0a60a --- /dev/null +++ b/providers/mistral/models/zai-glm-5-3.toml @@ -0,0 +1,34 @@ +name = "GLM 5.3" +family = "glm" +release_date = "2026-09-15" +last_updated = "2026-09-15" +attachment = false +reasoning = true +tool_call = true +structured_output = true +temperature = true +open_weights = true + +[cost] +input = 1.40 +output = 4.40 +cache_read = 0.14 + +[limit] +context = 1048576 +output = 131072 + +[modalities] +input = ["text"] +output = ["text"] + +# Z.ai's open-weights coding model, hosted unmodified by Mistral (public +# preview). Pinned id; `zai-glm-latest` also resolves here. +[fleetify] +priority = 25 +note = "Code" +aliases = ["zai-glm-5", "zai-glm-latest"] + +# Mistral documents no reasoning-effort control for this model. +[fleetify.effort] +kind = "none" From 219b28904e45ebea463393a68aacf68bbb07754f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Doruk=20=C3=96zgen?= Date: Mon, 21 Sep 2026 14:37:45 +0300 Subject: [PATCH 13/30] fix(catalog): bring the Mistral entries up to the current snapshots - `mistral-large-latest` resolves to Mistral Large 3 (`mistral-large-2512`, released 2025-12-02). The entry still named the 2411 snapshot as an alias, which Mistral retired on 2026-05-31 and which now 404s. Drop the knowledge cutoff, which described 2411 and is not published for Large 3. - `codestral-latest` is Codestral 25.08 (2025-07-30): 128K context rather than 256K, and a Premier licence, so `open_weights = false`. - Mistral Small 4 takes image input. - `mistral-medium-3-5-26-04` is a docs-page slug, not an API id. The real ids are `mistral-medium-3-5` and `mistral-medium-3`. - Medium 3.5 and Small 4 accept `reasoning_effort` (none ... xhigh). Default to `high`, which Mistral recommends for agentic and code use. - Cached prompt tokens bill at 10% of input on every model; add `cache_read`. --- providers/mistral/models/codestral.toml | 12 ++++++------ providers/mistral/models/mistral-large.toml | 8 ++++---- providers/mistral/models/mistral-medium.toml | 10 +++++++++- providers/mistral/models/mistral-small.toml | 12 ++++++++++-- 4 files changed, 29 insertions(+), 13 deletions(-) diff --git a/providers/mistral/models/codestral.toml b/providers/mistral/models/codestral.toml index 3759fc6..906917c 100644 --- a/providers/mistral/models/codestral.toml +++ b/providers/mistral/models/codestral.toml @@ -1,21 +1,21 @@ name = "Codestral" family = "codestral" -release_date = "2024-05-29" -last_updated = "2025-01-04" -knowledge = "2024-10" +release_date = "2025-07-30" +last_updated = "2025-07-30" attachment = false reasoning = false tool_call = true structured_output = true temperature = true -open_weights = true +open_weights = false [cost] input = 0.30 output = 0.90 +cache_read = 0.03 [limit] -context = 256000 +context = 131072 output = 4096 [modalities] @@ -25,4 +25,4 @@ output = ["text"] [fleetify] priority = 10 note = "Code" -aliases = ["codestral-latest"] +aliases = ["codestral-latest", "codestral-2508"] diff --git a/providers/mistral/models/mistral-large.toml b/providers/mistral/models/mistral-large.toml index a204c1f..9d19b82 100644 --- a/providers/mistral/models/mistral-large.toml +++ b/providers/mistral/models/mistral-large.toml @@ -1,8 +1,7 @@ -name = "Mistral Large" +name = "Mistral Large 3" family = "mistral-large" -release_date = "2024-11-01" +release_date = "2025-12-02" last_updated = "2025-12-02" -knowledge = "2024-11" attachment = true reasoning = false tool_call = true @@ -13,6 +12,7 @@ open_weights = true [cost] input = 0.50 output = 1.50 +cache_read = 0.05 [limit] context = 262144 @@ -25,4 +25,4 @@ output = ["text"] [fleetify] priority = 20 default = true -aliases = ["mistral-large-latest", "mistral-large-2411"] +aliases = ["mistral-large-latest", "mistral-large-2512"] diff --git a/providers/mistral/models/mistral-medium.toml b/providers/mistral/models/mistral-medium.toml index 470788c..ffd96ce 100644 --- a/providers/mistral/models/mistral-medium.toml +++ b/providers/mistral/models/mistral-medium.toml @@ -12,6 +12,7 @@ open_weights = true [cost] input = 1.50 output = 7.50 +cache_read = 0.15 [limit] context = 262144 @@ -22,4 +23,11 @@ output = ["text"] [fleetify] priority = 30 -aliases = ["mistral-medium-latest", "mistral-medium-3-5-26-04"] +aliases = ["mistral-medium-latest", "mistral-medium-3-5", "mistral-medium-3"] + +# `reasoning_effort` is documented for this model; Mistral recommends `high` +# for agentic and code work. The API default is not documented. +[fleetify.effort] +kind = "levels" +levels = ["none", "minimal", "low", "medium", "high", "xhigh"] +default = "high" diff --git a/providers/mistral/models/mistral-small.toml b/providers/mistral/models/mistral-small.toml index db4f845..b251cf2 100644 --- a/providers/mistral/models/mistral-small.toml +++ b/providers/mistral/models/mistral-small.toml @@ -2,7 +2,7 @@ name = "Mistral Small 4" family = "mistral-small" release_date = "2026-03-16" last_updated = "2026-03-16" -attachment = false +attachment = true reasoning = true tool_call = true structured_output = true @@ -12,14 +12,22 @@ open_weights = true [cost] input = 0.15 output = 0.60 +cache_read = 0.015 [limit] context = 262144 [modalities] -input = ["text"] +input = ["text", "image"] output = ["text"] [fleetify] priority = 15 aliases = ["mistral-small-latest", "mistral-small-2603"] + +# `reasoning_effort` is documented for this model; Mistral recommends `high` +# for agentic and code work. The API default is not documented. +[fleetify.effort] +kind = "levels" +levels = ["none", "minimal", "low", "medium", "high", "xhigh"] +default = "high" From 4d446096798e9dc571467a565b21f9c1ccfc1f4e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Doruk=20=C3=96zgen?= Date: Mon, 21 Sep 2026 14:37:45 +0300 Subject: [PATCH 14/30] feat(catalog): add Kimi K2.7 Code HighSpeed to kimi-api `kimi-k2.7-code-highspeed` was recorded as an alias of `kimi-k2.7-code`, but it is a separately listed and separately priced model: the same weights served faster at $1.90 / $8.00 ($0.38 cached), twice the base rate. As an alias it would have been billed at half its real price. Give it its own entry and drop the alias. While in `kimi-k2.7-code`: record its release date (2026-06-12) and that the model rejects any `temperature` other than its fixed 1.0. Source: platform.kimi.ai pricing, models and models-overview pages. --- .../models/kimi-k2.7-code-highspeed.toml | 24 +++++++++++++++++++ providers/kimi-api/models/kimi-k2.7-code.toml | 5 ++-- 2 files changed, 27 insertions(+), 2 deletions(-) create mode 100644 providers/kimi-api/models/kimi-k2.7-code-highspeed.toml diff --git a/providers/kimi-api/models/kimi-k2.7-code-highspeed.toml b/providers/kimi-api/models/kimi-k2.7-code-highspeed.toml new file mode 100644 index 0000000..5a94945 --- /dev/null +++ b/providers/kimi-api/models/kimi-k2.7-code-highspeed.toml @@ -0,0 +1,24 @@ +name = "Kimi K2.7 Code HighSpeed" +family = "kimi-k2.7" +attachment = true +reasoning = true +tool_call = true +structured_output = true +temperature = false +open_weights = true + +# Same model as `kimi-k2.7-code` served faster, at twice the price. +[cost] +input = 1.90 +output = 8.00 +cache_read = 0.38 + +[limit] +context = 262144 + +[modalities] +input = ["text", "image", "video"] +output = ["text"] + +[fleetify] +priority = 22 diff --git a/providers/kimi-api/models/kimi-k2.7-code.toml b/providers/kimi-api/models/kimi-k2.7-code.toml index 0448089..7364518 100644 --- a/providers/kimi-api/models/kimi-k2.7-code.toml +++ b/providers/kimi-api/models/kimi-k2.7-code.toml @@ -1,10 +1,12 @@ name = "Kimi K2.7 Code" family = "kimi-k2.7" +release_date = "2026-06-12" +last_updated = "2026-06-12" attachment = true reasoning = true tool_call = true structured_output = true -temperature = true +temperature = false open_weights = true [cost] @@ -21,4 +23,3 @@ output = ["text"] [fleetify] priority = 25 -aliases = ["kimi-k2.7-code-highspeed"] From 40327538562d6b3b91e53ba592e13b8b5eef43ad Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Doruk=20=C3=96zgen?= Date: Mon, 21 Sep 2026 14:37:45 +0300 Subject: [PATCH 15/30] fix(catalog): Kimi K2.6 and K3 reject custom temperature Moonshot fixes `temperature` per model (K3 at 1.0; K2.6 at 1.0 thinking / 0.6 non-thinking) and returns an error for any other value, so `temperature` is false. kimi-code inherits this through `extends`. Also record K3's documented 1,048,576 max output (131,072 when unset). --- providers/kimi-api/models/kimi-k2.6.toml | 2 +- providers/kimi-api/models/kimi-k3.toml | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/providers/kimi-api/models/kimi-k2.6.toml b/providers/kimi-api/models/kimi-k2.6.toml index f4e39bb..649d1d2 100644 --- a/providers/kimi-api/models/kimi-k2.6.toml +++ b/providers/kimi-api/models/kimi-k2.6.toml @@ -7,7 +7,7 @@ attachment = true reasoning = true tool_call = true structured_output = true -temperature = true +temperature = false open_weights = true [cost] diff --git a/providers/kimi-api/models/kimi-k3.toml b/providers/kimi-api/models/kimi-k3.toml index 5d65c8b..7736acd 100644 --- a/providers/kimi-api/models/kimi-k3.toml +++ b/providers/kimi-api/models/kimi-k3.toml @@ -6,7 +6,7 @@ attachment = true reasoning = true tool_call = true structured_output = true -temperature = true +temperature = false open_weights = true [cost] @@ -16,6 +16,7 @@ cache_read = 0.30 [limit] context = 1048576 +output = 1048576 [modalities] input = ["text", "image", "video"] From 41e026ca4e7e895f1018aebb94f05f2dd1f9b96b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Doruk=20=C3=96zgen?= Date: Mon, 21 Sep 2026 14:38:02 +0300 Subject: [PATCH 16/30] feat(catalog)!: drop Kimi K2.5 from kimi-api and kimi-code Moonshot discontinued `kimi-k2.5` on 2026-08-31 together with the `moonshot-v1-*` family; calls now return 404 "model not found". K2.6 remains the default on both providers. BREAKING CHANGE: `kimi-k2.5` is gone from kimi-api and kimi-code. Sessions pinned to it heal to the provider default. --- providers/kimi-api/models/kimi-k2.5.toml | 25 ----------------------- providers/kimi-code/models/kimi-k2.5.toml | 6 ------ 2 files changed, 31 deletions(-) delete mode 100644 providers/kimi-api/models/kimi-k2.5.toml delete mode 100644 providers/kimi-code/models/kimi-k2.5.toml diff --git a/providers/kimi-api/models/kimi-k2.5.toml b/providers/kimi-api/models/kimi-k2.5.toml deleted file mode 100644 index 6c80445..0000000 --- a/providers/kimi-api/models/kimi-k2.5.toml +++ /dev/null @@ -1,25 +0,0 @@ -name = "Kimi K2.5" -family = "kimi-k2.5" -knowledge = "2025-01" -attachment = false -reasoning = true -tool_call = true -structured_output = true -temperature = false -open_weights = true - -[cost] -input = 0.60 -output = 3.00 -cache_read = 0.10 - -[limit] -context = 262144 -output = 262144 - -[modalities] -input = ["text", "image", "video"] -output = ["text"] - -[fleetify] -priority = 10 diff --git a/providers/kimi-code/models/kimi-k2.5.toml b/providers/kimi-code/models/kimi-k2.5.toml deleted file mode 100644 index cc7e065..0000000 --- a/providers/kimi-code/models/kimi-k2.5.toml +++ /dev/null @@ -1,6 +0,0 @@ -[extends] -from = "kimi-api/kimi-k2.5" - -[fleetify] -priority = 10 -label = "Kimi K2.5" From 64aa8e816e1478a97131c0340940497ad2343ebd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Doruk=20=C3=96zgen?= Date: Mon, 21 Sep 2026 14:38:50 +0300 Subject: [PATCH 17/30] feat(catalog): add the September 2026 flagships to openrouter Claude Fable 5.1, GPT-6 Astra, Gemini 3.8 Flash, Grok 4.6, DeepSeek V4.1 Flash and GLM 5.3, all listed on OpenRouter's public /api/v1/models today. Ids, prices, context and max output come from that endpoint; release dates and knowledge cutoffs come from each vendor's own docs where they publish them. The list stays curated to one or two current models per vendor, so Gemini 3.7 Flash (superseded by 3.8 three weeks later at the same price), the GPT-6 Astra Pro routing id and the dated DeepSeek snapshots are left out. GPT-6 Astra is fine here even though it is held back from the `openai` provider: OpenRouter lists `tools` among its supported parameters and translates to the upstream API itself. --- .../models/anthropic/claude-fable-5.1.toml | 28 +++++++++++++++++++ .../models/deepseek/deepseek-v4.1-flash.toml | 27 ++++++++++++++++++ .../models/google/gemini-3.8-flash.toml | 27 ++++++++++++++++++ .../openrouter/models/openai/gpt-6-astra.toml | 28 +++++++++++++++++++ .../openrouter/models/x-ai/grok-4.6.toml | 27 ++++++++++++++++++ providers/openrouter/models/z-ai/glm-5.3.toml | 27 ++++++++++++++++++ 6 files changed, 164 insertions(+) create mode 100644 providers/openrouter/models/anthropic/claude-fable-5.1.toml create mode 100644 providers/openrouter/models/deepseek/deepseek-v4.1-flash.toml create mode 100644 providers/openrouter/models/google/gemini-3.8-flash.toml create mode 100644 providers/openrouter/models/openai/gpt-6-astra.toml create mode 100644 providers/openrouter/models/x-ai/grok-4.6.toml create mode 100644 providers/openrouter/models/z-ai/glm-5.3.toml diff --git a/providers/openrouter/models/anthropic/claude-fable-5.1.toml b/providers/openrouter/models/anthropic/claude-fable-5.1.toml new file mode 100644 index 0000000..bd521aa --- /dev/null +++ b/providers/openrouter/models/anthropic/claude-fable-5.1.toml @@ -0,0 +1,28 @@ +name = "Claude Fable 5.1" +family = "claude-fable" +release_date = "2026-09-01" +last_updated = "2026-09-01" +knowledge = "2026-06" +attachment = true +reasoning = true +tool_call = true +structured_output = true +temperature = false + +[cost] +input = 10.00 +output = 50.00 +cache_read = 0.25 +cache_write = 12.50 + +[limit] +context = 1000000 +output = 128000 + +[modalities] +input = ["text", "image", "pdf"] +output = ["text"] + +[fleetify] +priority = 108 +group = "via OpenRouter" diff --git a/providers/openrouter/models/deepseek/deepseek-v4.1-flash.toml b/providers/openrouter/models/deepseek/deepseek-v4.1-flash.toml new file mode 100644 index 0000000..d572e5b --- /dev/null +++ b/providers/openrouter/models/deepseek/deepseek-v4.1-flash.toml @@ -0,0 +1,27 @@ +name = "DeepSeek V4.1 Flash" +family = "deepseek-flash" +release_date = "2026-09-10" +last_updated = "2026-09-10" +attachment = true +reasoning = true +tool_call = true +structured_output = true +temperature = true +open_weights = true + +[cost] +input = 0.15 +output = 0.60 +cache_read = 0.003 + +[limit] +context = 1048576 +output = 384000 + +[modalities] +input = ["text", "image"] +output = ["text"] + +[fleetify] +priority = 35 +group = "via OpenRouter" diff --git a/providers/openrouter/models/google/gemini-3.8-flash.toml b/providers/openrouter/models/google/gemini-3.8-flash.toml new file mode 100644 index 0000000..4d76902 --- /dev/null +++ b/providers/openrouter/models/google/gemini-3.8-flash.toml @@ -0,0 +1,27 @@ +name = "Gemini 3.8 Flash" +family = "gemini-flash" +release_date = "2026-09-02" +last_updated = "2026-09-02" +knowledge = "2026-03" +attachment = true +reasoning = true +tool_call = true +structured_output = true +temperature = true + +[cost] +input = 0.75 +output = 3.75 +cache_read = 0.075 + +[limit] +context = 1048576 +output = 65536 + +[modalities] +input = ["text", "image", "video", "pdf", "audio"] +output = ["text"] + +[fleetify] +priority = 58 +group = "via OpenRouter" diff --git a/providers/openrouter/models/openai/gpt-6-astra.toml b/providers/openrouter/models/openai/gpt-6-astra.toml new file mode 100644 index 0000000..05e85d5 --- /dev/null +++ b/providers/openrouter/models/openai/gpt-6-astra.toml @@ -0,0 +1,28 @@ +name = "GPT-6 Astra" +family = "gpt" +release_date = "2026-09-03" +last_updated = "2026-09-03" +knowledge = "2026-04-30" +attachment = true +reasoning = true +tool_call = true +structured_output = true +temperature = false + +[cost] +input = 10.00 +output = 50.00 +cache_read = 1.00 +cache_write = 12.50 + +[limit] +context = 1050000 +output = 128000 + +[modalities] +input = ["pdf", "image", "text"] +output = ["text"] + +[fleetify] +priority = 88 +group = "via OpenRouter" diff --git a/providers/openrouter/models/x-ai/grok-4.6.toml b/providers/openrouter/models/x-ai/grok-4.6.toml new file mode 100644 index 0000000..df83207 --- /dev/null +++ b/providers/openrouter/models/x-ai/grok-4.6.toml @@ -0,0 +1,27 @@ +name = "Grok 4.6" +family = "grok" +release_date = "2026-08-12" +last_updated = "2026-08-12" +knowledge = "2026-02-01" +attachment = true +reasoning = true +tool_call = true +structured_output = true +temperature = true + +[cost] +input = 2.00 +output = 6.00 +cache_read = 0.50 + +[limit] +context = 500000 +output = 450000 + +[modalities] +input = ["text", "image", "pdf"] +output = ["text"] + +[fleetify] +priority = 48 +group = "via OpenRouter" diff --git a/providers/openrouter/models/z-ai/glm-5.3.toml b/providers/openrouter/models/z-ai/glm-5.3.toml new file mode 100644 index 0000000..cf361c1 --- /dev/null +++ b/providers/openrouter/models/z-ai/glm-5.3.toml @@ -0,0 +1,27 @@ +name = "GLM 5.3" +family = "glm" +release_date = "2026-08-18" +last_updated = "2026-08-18" +attachment = false +reasoning = true +tool_call = true +structured_output = true +temperature = true +open_weights = true + +[cost] +input = 0.91 +output = 2.86 +cache_read = 0.169 + +[limit] +context = 1310720 +output = 131072 + +[modalities] +input = ["text"] +output = ["text"] + +[fleetify] +priority = 15 +group = "via OpenRouter" From 6d81eb0e5575fde5a39e7518a81f751aa470bb00 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Doruk=20=C3=96zgen?= Date: Mon, 21 Sep 2026 14:38:50 +0300 Subject: [PATCH 18/30] fix(catalog): sync stale openrouter prices with its live API Six entries had drifted from what OpenRouter's /api/v1/models reports on 2026-09-21: - anthropic/claude-sonnet-5 $3 / $15 -> $2 / $10 (now the standard rate) - google/gemini-3.6-flash $1.50 / $7.50 -> $0.75 / $3.75 - openai/gpt-5.6-sol $5 / $30 -> $2 / $10 - moonshotai/kimi-k3 $3 / $15 -> $1.70 / $8.50 - moonshotai/kimi-k2.6 $0.684 / $3.42 -> $0.95 / $4.00 - deepseek/deepseek-v4-pro $0.435 / $0.87 -> $0.9553 / $1.9105 Cached-input rates move with them. The other ten entries already match. --- .../openrouter/models/anthropic/claude-sonnet-5.toml | 8 ++++---- providers/openrouter/models/deepseek/deepseek-v4-pro.toml | 6 +++--- providers/openrouter/models/google/gemini-3.6-flash.toml | 6 +++--- providers/openrouter/models/moonshotai/kimi-k2.6.toml | 6 +++--- providers/openrouter/models/moonshotai/kimi-k3.toml | 6 +++--- providers/openrouter/models/openai/gpt-5.6-sol.toml | 6 +++--- 6 files changed, 19 insertions(+), 19 deletions(-) diff --git a/providers/openrouter/models/anthropic/claude-sonnet-5.toml b/providers/openrouter/models/anthropic/claude-sonnet-5.toml index 0f901e5..5ab3586 100644 --- a/providers/openrouter/models/anthropic/claude-sonnet-5.toml +++ b/providers/openrouter/models/anthropic/claude-sonnet-5.toml @@ -10,10 +10,10 @@ structured_output = true temperature = false [cost] -input = 3.00 -output = 15.00 -cache_read = 0.30 -cache_write = 3.75 +input = 2.00 +output = 10.00 +cache_read = 0.20 +cache_write = 2.50 [limit] context = 1000000 diff --git a/providers/openrouter/models/deepseek/deepseek-v4-pro.toml b/providers/openrouter/models/deepseek/deepseek-v4-pro.toml index 3ebedd7..022c71d 100644 --- a/providers/openrouter/models/deepseek/deepseek-v4-pro.toml +++ b/providers/openrouter/models/deepseek/deepseek-v4-pro.toml @@ -11,9 +11,9 @@ temperature = true open_weights = true [cost] -input = 0.435 -output = 0.87 -cache_read = 0.003625 +input = 0.9553 +output = 1.9105 +cache_read = 0.0796 [limit] context = 1048576 diff --git a/providers/openrouter/models/google/gemini-3.6-flash.toml b/providers/openrouter/models/google/gemini-3.6-flash.toml index 27be3b0..95a74d6 100644 --- a/providers/openrouter/models/google/gemini-3.6-flash.toml +++ b/providers/openrouter/models/google/gemini-3.6-flash.toml @@ -10,9 +10,9 @@ structured_output = true temperature = true [cost] -input = 1.50 -output = 7.50 -cache_read = 0.15 +input = 0.75 +output = 3.75 +cache_read = 0.075 [limit] context = 1048576 diff --git a/providers/openrouter/models/moonshotai/kimi-k2.6.toml b/providers/openrouter/models/moonshotai/kimi-k2.6.toml index fa3bb24..ffc3943 100644 --- a/providers/openrouter/models/moonshotai/kimi-k2.6.toml +++ b/providers/openrouter/models/moonshotai/kimi-k2.6.toml @@ -11,9 +11,9 @@ temperature = true open_weights = true [cost] -input = 0.684 -output = 3.42 -cache_read = 0.144 +input = 0.95 +output = 4.00 +cache_read = 0.16 [limit] context = 262144 diff --git a/providers/openrouter/models/moonshotai/kimi-k3.toml b/providers/openrouter/models/moonshotai/kimi-k3.toml index 968c51b..8f26c84 100644 --- a/providers/openrouter/models/moonshotai/kimi-k3.toml +++ b/providers/openrouter/models/moonshotai/kimi-k3.toml @@ -10,9 +10,9 @@ temperature = true open_weights = true [cost] -input = 3.00 -output = 15.00 -cache_read = 0.30 +input = 1.70 +output = 8.50 +cache_read = 0.17 [limit] context = 1048576 diff --git a/providers/openrouter/models/openai/gpt-5.6-sol.toml b/providers/openrouter/models/openai/gpt-5.6-sol.toml index 89a811d..4bf7a31 100644 --- a/providers/openrouter/models/openai/gpt-5.6-sol.toml +++ b/providers/openrouter/models/openai/gpt-5.6-sol.toml @@ -10,9 +10,9 @@ structured_output = true temperature = false [cost] -input = 5.00 -output = 30.00 -cache_read = 0.50 +input = 2.00 +output = 10.00 +cache_read = 0.20 [limit] context = 1050000 From a6896cdc32cd53c1507780655c1f846b8f7f9ccc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Doruk=20=C3=96zgen?= Date: Mon, 21 Sep 2026 14:40:17 +0300 Subject: [PATCH 19/30] feat(catalog): add seven models to github-copilot Claude Fable 5.1, Claude Fable 5, GPT-6 Astra, Gemini 3.8 Flash, Grok 4.6, Kimi K3 and MAI-Code-1.1-Flash. Each is GA in GitHub's supported-models table and marked "Included" in its Copilot CLI column. Ids follow the CLI's lowercased-display-name convention; `claude-fable-5.1` and `kimi-k3` are spelled out in the copilot-cli release notes. Prices are GitHub's own per-token rates. GitHub publishes no context or output limits, so Claude, GPT and Gemini reuse the windows already recorded for their siblings here, while Grok 4.6 and Kimi K3 carry their vendor's window. MAI-Code-1.1-Flash has pricing only. Skipped on purpose: Gemini 3.7 Flash and Grok 4.5 (GitHub retires both on 2026-10-19) and Kimi K2.7 Code (retires 2026-10-02). Source: docs.github.com supported-models and models-and-pricing; GitHub changelog; github/copilot-cli releases. --- .../models/claude-fable-5.1.toml | 32 +++++++++++++++++++ .../github-copilot/models/claude-fable-5.toml | 32 +++++++++++++++++++ .../models/gemini-3.8-flash.toml | 31 ++++++++++++++++++ .../github-copilot/models/gpt-6-astra.toml | 32 +++++++++++++++++++ providers/github-copilot/models/grok-4.6.toml | 31 ++++++++++++++++++ providers/github-copilot/models/kimi-k3.toml | 31 ++++++++++++++++++ .../models/mai-code-1.1-flash.toml | 16 ++++++++++ 7 files changed, 205 insertions(+) create mode 100644 providers/github-copilot/models/claude-fable-5.1.toml create mode 100644 providers/github-copilot/models/claude-fable-5.toml create mode 100644 providers/github-copilot/models/gemini-3.8-flash.toml create mode 100644 providers/github-copilot/models/gpt-6-astra.toml create mode 100644 providers/github-copilot/models/grok-4.6.toml create mode 100644 providers/github-copilot/models/kimi-k3.toml create mode 100644 providers/github-copilot/models/mai-code-1.1-flash.toml diff --git a/providers/github-copilot/models/claude-fable-5.1.toml b/providers/github-copilot/models/claude-fable-5.1.toml new file mode 100644 index 0000000..6fba85d --- /dev/null +++ b/providers/github-copilot/models/claude-fable-5.1.toml @@ -0,0 +1,32 @@ +name = "Claude Fable 5.1" +family = "claude-fable" +release_date = "2026-09-01" +last_updated = "2026-09-01" +knowledge = "2026-06" +attachment = true +reasoning = true +tool_call = true +structured_output = true +temperature = false + +[cost] +input = 10.00 +output = 50.00 +cache_read = 0.25 +cache_write = 12.50 + +[limit] +context = 200000 +output = 64000 + +[modalities] +input = ["text", "image", "pdf"] +output = ["text"] + +[fleetify] +priority = 228 + +[fleetify.effort] +kind = "levels" +levels = ["low", "medium", "high", "xhigh"] +default = "medium" diff --git a/providers/github-copilot/models/claude-fable-5.toml b/providers/github-copilot/models/claude-fable-5.toml new file mode 100644 index 0000000..416cda1 --- /dev/null +++ b/providers/github-copilot/models/claude-fable-5.toml @@ -0,0 +1,32 @@ +name = "Claude Fable 5" +family = "claude-fable" +release_date = "2026-06-09" +last_updated = "2026-06-09" +knowledge = "2026-01" +attachment = true +reasoning = true +tool_call = true +structured_output = true +temperature = false + +[cost] +input = 10.00 +output = 50.00 +cache_read = 1.00 +cache_write = 12.50 + +[limit] +context = 200000 +output = 64000 + +[modalities] +input = ["text", "image", "pdf"] +output = ["text"] + +[fleetify] +priority = 227 + +[fleetify.effort] +kind = "levels" +levels = ["low", "medium", "high", "xhigh"] +default = "medium" diff --git a/providers/github-copilot/models/gemini-3.8-flash.toml b/providers/github-copilot/models/gemini-3.8-flash.toml new file mode 100644 index 0000000..2362a52 --- /dev/null +++ b/providers/github-copilot/models/gemini-3.8-flash.toml @@ -0,0 +1,31 @@ +name = "Gemini 3.8 Flash" +family = "gemini-flash" +release_date = "2026-09-02" +last_updated = "2026-09-02" +knowledge = "2026-03" +attachment = true +reasoning = true +tool_call = true +structured_output = true +temperature = true + +[cost] +input = 0.75 +output = 3.75 +cache_read = 0.075 + +[limit] +context = 200000 +output = 64000 + +[modalities] +input = ["text", "image", "video", "audio", "pdf"] +output = ["text"] + +[fleetify] +priority = 108 + +[fleetify.effort] +kind = "levels" +levels = ["low", "medium", "high", "xhigh"] +default = "medium" diff --git a/providers/github-copilot/models/gpt-6-astra.toml b/providers/github-copilot/models/gpt-6-astra.toml new file mode 100644 index 0000000..ce7b064 --- /dev/null +++ b/providers/github-copilot/models/gpt-6-astra.toml @@ -0,0 +1,32 @@ +name = "GPT-6 Astra" +family = "gpt" +release_date = "2026-09-03" +last_updated = "2026-09-03" +knowledge = "2026-04-30" +attachment = true +reasoning = true +tool_call = true +structured_output = true +temperature = false + +[cost] +input = 10.00 +output = 50.00 +cache_read = 1.00 +cache_write = 12.50 + +[limit] +context = 400000 +output = 128000 + +[modalities] +input = ["text", "image"] +output = ["text"] + +[fleetify] +priority = 158 + +[fleetify.effort] +kind = "levels" +levels = ["low", "medium", "high", "xhigh"] +default = "medium" diff --git a/providers/github-copilot/models/grok-4.6.toml b/providers/github-copilot/models/grok-4.6.toml new file mode 100644 index 0000000..32bc692 --- /dev/null +++ b/providers/github-copilot/models/grok-4.6.toml @@ -0,0 +1,31 @@ +name = "Grok 4.6" +family = "grok" +release_date = "2026-08-12" +last_updated = "2026-08-12" +knowledge = "2026-02-01" +attachment = true +reasoning = true +tool_call = true +structured_output = true +temperature = true + +[cost] +input = 2.00 +output = 6.00 +cache_read = 0.50 + +# GitHub publishes no Copilot-specific window for Grok 4.6; this is xAI's. +[limit] +context = 500000 + +[modalities] +input = ["text", "image"] +output = ["text"] + +[fleetify] +priority = 109 + +[fleetify.effort] +kind = "levels" +levels = ["low", "medium", "high", "xhigh"] +default = "medium" diff --git a/providers/github-copilot/models/kimi-k3.toml b/providers/github-copilot/models/kimi-k3.toml new file mode 100644 index 0000000..f448e98 --- /dev/null +++ b/providers/github-copilot/models/kimi-k3.toml @@ -0,0 +1,31 @@ +name = "Kimi K3" +family = "kimi-k3" +release_date = "2026-07-16" +last_updated = "2026-07-16" +attachment = true +reasoning = true +tool_call = true +structured_output = true +temperature = false +open_weights = true + +[cost] +input = 3.00 +output = 15.00 +cache_read = 0.30 + +# GitHub publishes no Copilot-specific window for Kimi K3; this is Moonshot's. +[limit] +context = 1048576 + +[modalities] +input = ["text", "image", "video"] +output = ["text"] + +[fleetify] +priority = 65 + +[fleetify.effort] +kind = "levels" +levels = ["low", "medium", "high", "xhigh"] +default = "medium" diff --git a/providers/github-copilot/models/mai-code-1.1-flash.toml b/providers/github-copilot/models/mai-code-1.1-flash.toml new file mode 100644 index 0000000..5c3c3a0 --- /dev/null +++ b/providers/github-copilot/models/mai-code-1.1-flash.toml @@ -0,0 +1,16 @@ +name = "MAI-Code-1.1-Flash" +family = "mai-code" +release_date = "2026-08-11" +last_updated = "2026-08-11" +tool_call = true + +# Microsoft's fast coding model and GitHub's suggested replacement for Raptor +# mini. GitHub publishes pricing only; limits and capabilities are left unset. +[cost] +input = 0.20 +output = 1.20 +cache_read = 0.02 + +[fleetify] +priority = 12 +note = "Code" From 148c5226cd7ba0e0c48b4b11c134904a1540d686 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Doruk=20=C3=96zgen?= Date: Mon, 21 Sep 2026 14:40:17 +0300 Subject: [PATCH 20/30] fix(catalog): github-copilot prices for Sonnet 5, GPT-5.6 Sol, Gemini 3.6 Flash GitHub's per-token pricing table now lists Claude Sonnet 5 at $2 / $10, GPT-5.6 Sol at $4 / $20 and Gemini 3.6 Flash at $0.75 / $3.75, following the upstream vendors. Cached-input and cache-write rates move with them. --- providers/github-copilot/models/claude-sonnet-5.toml | 8 ++++---- providers/github-copilot/models/gemini-3.6-flash.toml | 6 +++--- providers/github-copilot/models/gpt-5.6-sol.toml | 6 +++--- 3 files changed, 10 insertions(+), 10 deletions(-) diff --git a/providers/github-copilot/models/claude-sonnet-5.toml b/providers/github-copilot/models/claude-sonnet-5.toml index c3499f7..740a951 100644 --- a/providers/github-copilot/models/claude-sonnet-5.toml +++ b/providers/github-copilot/models/claude-sonnet-5.toml @@ -10,10 +10,10 @@ structured_output = true temperature = false [cost] -input = 3.00 -output = 15.00 -cache_read = 0.30 -cache_write = 3.75 +input = 2.00 +output = 10.00 +cache_read = 0.20 +cache_write = 2.50 [limit] context = 200000 diff --git a/providers/github-copilot/models/gemini-3.6-flash.toml b/providers/github-copilot/models/gemini-3.6-flash.toml index 5e104da..e7d08a9 100644 --- a/providers/github-copilot/models/gemini-3.6-flash.toml +++ b/providers/github-copilot/models/gemini-3.6-flash.toml @@ -10,9 +10,9 @@ structured_output = true temperature = true [cost] -input = 1.50 -output = 7.50 -cache_read = 0.15 +input = 0.75 +output = 3.75 +cache_read = 0.075 [limit] context = 200000 diff --git a/providers/github-copilot/models/gpt-5.6-sol.toml b/providers/github-copilot/models/gpt-5.6-sol.toml index 7d6f36f..6ecf123 100644 --- a/providers/github-copilot/models/gpt-5.6-sol.toml +++ b/providers/github-copilot/models/gpt-5.6-sol.toml @@ -10,9 +10,9 @@ structured_output = true temperature = false [cost] -input = 5.00 -output = 30.00 -cache_read = 0.50 +input = 4.00 +output = 20.00 +cache_read = 0.40 [limit] context = 400000 From 8e5963bc53ab22c083907661cf8ecec88f3f111a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Doruk=20=C3=96zgen?= Date: Mon, 21 Sep 2026 14:40:17 +0300 Subject: [PATCH 21/30] feat(catalog)!: drop eleven retired models from github-copilot GitHub's model retirement history lists these as already retired: - 2026-09-01: Claude Opus 4.5, Claude Opus 4.6, Claude Sonnet 4.5, Gemini 3.1 Pro, Raptor mini - 2026-07-31: Gemini 2.5 Pro, Gemini 3 Flash - 2026-06-01: GPT-4.1 (now a non-selectable utility model), GPT-5.2, GPT-5.2-Codex GPT-5.4 nano was never selectable in Copilot CLI: every client column reads "Not included" and GitHub lists it as a utility model. Claude Sonnet 4.6 stays. It carries the same 2026-09-01 date but GitHub keeps it available to annual Pro and Pro+ subscribers and it is still in the supported table. Models with a future retirement date also stay for now: Claude Opus 4.7, Gemini 3.5 and 3.6 Flash (2026-10-02); GPT-5.5, GPT-5.4, GPT-5.4 mini and GPT-5 mini (2026-10-19). BREAKING CHANGE: eleven model ids are gone from the github-copilot provider. Sessions pinned to them heal to the provider default (`auto`). --- .../models/claude-opus-4.5.toml | 32 ------------------- .../models/claude-opus-4.6.toml | 32 ------------------- .../models/claude-sonnet-4.5.toml | 32 ------------------- .../github-copilot/models/gemini-2.5-pro.toml | 31 ------------------ .../models/gemini-3-flash-preview.toml | 31 ------------------ .../models/gemini-3.1-pro-preview.toml | 31 ------------------ providers/github-copilot/models/gpt-4.1.toml | 31 ------------------ .../github-copilot/models/gpt-5.2-codex.toml | 31 ------------------ providers/github-copilot/models/gpt-5.2.toml | 31 ------------------ .../github-copilot/models/gpt-5.4-nano.toml | 31 ------------------ .../github-copilot/models/raptor-mini.toml | 31 ------------------ 11 files changed, 344 deletions(-) delete mode 100644 providers/github-copilot/models/claude-opus-4.5.toml delete mode 100644 providers/github-copilot/models/claude-opus-4.6.toml delete mode 100644 providers/github-copilot/models/claude-sonnet-4.5.toml delete mode 100644 providers/github-copilot/models/gemini-2.5-pro.toml delete mode 100644 providers/github-copilot/models/gemini-3-flash-preview.toml delete mode 100644 providers/github-copilot/models/gemini-3.1-pro-preview.toml delete mode 100644 providers/github-copilot/models/gpt-4.1.toml delete mode 100644 providers/github-copilot/models/gpt-5.2-codex.toml delete mode 100644 providers/github-copilot/models/gpt-5.2.toml delete mode 100644 providers/github-copilot/models/gpt-5.4-nano.toml delete mode 100644 providers/github-copilot/models/raptor-mini.toml diff --git a/providers/github-copilot/models/claude-opus-4.5.toml b/providers/github-copilot/models/claude-opus-4.5.toml deleted file mode 100644 index 56c6543..0000000 --- a/providers/github-copilot/models/claude-opus-4.5.toml +++ /dev/null @@ -1,32 +0,0 @@ -name = "Claude Opus 4.5" -family = "claude-opus" -release_date = "2025-11-24" -last_updated = "2025-11-24" -knowledge = "2025-03-31" -attachment = true -reasoning = true -tool_call = true -structured_output = true -temperature = true - -[cost] -input = 5.00 -output = 25.00 -cache_read = 0.50 -cache_write = 6.25 - -[limit] -context = 200000 -output = 32000 - -[modalities] -input = ["text", "image", "pdf"] -output = ["text"] - -[fleetify] -priority = 190 - -[fleetify.effort] -kind = "levels" -levels = ["low", "medium", "high", "xhigh"] -default = "medium" diff --git a/providers/github-copilot/models/claude-opus-4.6.toml b/providers/github-copilot/models/claude-opus-4.6.toml deleted file mode 100644 index e902692..0000000 --- a/providers/github-copilot/models/claude-opus-4.6.toml +++ /dev/null @@ -1,32 +0,0 @@ -name = "Claude Opus 4.6" -family = "claude-opus" -release_date = "2026-02-05" -last_updated = "2026-03-13" -knowledge = "2025-05-31" -attachment = true -reasoning = true -tool_call = true -structured_output = true -temperature = true - -[cost] -input = 5.00 -output = 25.00 -cache_read = 0.50 -cache_write = 6.25 - -[limit] -context = 200000 -output = 32000 - -[modalities] -input = ["text", "image", "pdf"] -output = ["text"] - -[fleetify] -priority = 200 - -[fleetify.effort] -kind = "levels" -levels = ["low", "medium", "high", "xhigh"] -default = "medium" diff --git a/providers/github-copilot/models/claude-sonnet-4.5.toml b/providers/github-copilot/models/claude-sonnet-4.5.toml deleted file mode 100644 index dce9e2b..0000000 --- a/providers/github-copilot/models/claude-sonnet-4.5.toml +++ /dev/null @@ -1,32 +0,0 @@ -name = "Claude Sonnet 4.5" -family = "claude-sonnet" -release_date = "2025-09-29" -last_updated = "2025-09-29" -knowledge = "2025-07-31" -attachment = true -reasoning = true -tool_call = true -structured_output = true -temperature = true - -[cost] -input = 3.00 -output = 15.00 -cache_read = 0.30 -cache_write = 3.75 - -[limit] -context = 200000 -output = 32000 - -[modalities] -input = ["text", "image", "pdf"] -output = ["text"] - -[fleetify] -priority = 170 - -[fleetify.effort] -kind = "levels" -levels = ["low", "medium", "high", "xhigh"] -default = "medium" diff --git a/providers/github-copilot/models/gemini-2.5-pro.toml b/providers/github-copilot/models/gemini-2.5-pro.toml deleted file mode 100644 index 80ccc09..0000000 --- a/providers/github-copilot/models/gemini-2.5-pro.toml +++ /dev/null @@ -1,31 +0,0 @@ -name = "Gemini 2.5 Pro" -family = "gemini-pro" -release_date = "2025-03-20" -last_updated = "2025-06-05" -knowledge = "2025-01" -attachment = true -reasoning = true -tool_call = true -structured_output = true -temperature = true - -[cost] -input = 1.25 -output = 10.00 -cache_read = 0.125 - -[limit] -context = 128000 -output = 64000 - -[modalities] -input = ["text", "image", "audio", "video", "pdf"] -output = ["text"] - -[fleetify] -priority = 70 - -[fleetify.effort] -kind = "levels" -levels = ["low", "medium", "high", "xhigh"] -default = "medium" diff --git a/providers/github-copilot/models/gemini-3-flash-preview.toml b/providers/github-copilot/models/gemini-3-flash-preview.toml deleted file mode 100644 index c10c437..0000000 --- a/providers/github-copilot/models/gemini-3-flash-preview.toml +++ /dev/null @@ -1,31 +0,0 @@ -name = "Gemini 3 Flash Preview" -family = "gemini-flash" -release_date = "2025-12-17" -last_updated = "2025-12-17" -knowledge = "2025-01" -attachment = true -reasoning = true -tool_call = true -structured_output = true -temperature = true - -[cost] -input = 0.50 -output = 3.00 -cache_read = 0.05 - -[limit] -context = 128000 -output = 64000 - -[modalities] -input = ["text", "image", "video", "audio", "pdf"] -output = ["text"] - -[fleetify] -priority = 80 - -[fleetify.effort] -kind = "levels" -levels = ["low", "medium", "high", "xhigh"] -default = "medium" diff --git a/providers/github-copilot/models/gemini-3.1-pro-preview.toml b/providers/github-copilot/models/gemini-3.1-pro-preview.toml deleted file mode 100644 index f94529a..0000000 --- a/providers/github-copilot/models/gemini-3.1-pro-preview.toml +++ /dev/null @@ -1,31 +0,0 @@ -name = "Gemini 3.1 Pro Preview" -family = "gemini-pro" -release_date = "2026-02-19" -last_updated = "2026-02-19" -knowledge = "2025-01" -attachment = true -reasoning = true -tool_call = true -structured_output = true -temperature = true - -[cost] -input = 2.00 -output = 12.00 -cache_read = 0.20 - -[limit] -context = 200000 -output = 64000 - -[modalities] -input = ["text", "image", "video", "audio", "pdf"] -output = ["text"] - -[fleetify] -priority = 90 - -[fleetify.effort] -kind = "levels" -levels = ["low", "medium", "high", "xhigh"] -default = "medium" diff --git a/providers/github-copilot/models/gpt-4.1.toml b/providers/github-copilot/models/gpt-4.1.toml deleted file mode 100644 index b3bf756..0000000 --- a/providers/github-copilot/models/gpt-4.1.toml +++ /dev/null @@ -1,31 +0,0 @@ -name = "GPT-4.1" -family = "gpt" -release_date = "2025-04-14" -last_updated = "2025-04-14" -knowledge = "2024-04" -attachment = true -reasoning = false -tool_call = true -structured_output = true -temperature = true - -[cost] -input = 2.00 -output = 8.00 -cache_read = 0.50 - -[limit] -context = 128000 -output = 16384 - -[modalities] -input = ["text", "image", "pdf"] -output = ["text"] - -[fleetify] -priority = 60 - -[fleetify.effort] -kind = "levels" -levels = ["low", "medium", "high", "xhigh"] -default = "medium" diff --git a/providers/github-copilot/models/gpt-5.2-codex.toml b/providers/github-copilot/models/gpt-5.2-codex.toml deleted file mode 100644 index b783280..0000000 --- a/providers/github-copilot/models/gpt-5.2-codex.toml +++ /dev/null @@ -1,31 +0,0 @@ -name = "GPT-5.2 Codex" -family = "gpt-codex" -release_date = "2025-12-11" -last_updated = "2025-12-11" -knowledge = "2025-08-31" -attachment = true -reasoning = true -tool_call = true -structured_output = true -temperature = false - -[cost] -input = 1.75 -output = 14.00 -cache_read = 0.175 - -[limit] -context = 400000 -output = 128000 - -[modalities] -input = ["text", "image", "pdf"] -output = ["text"] - -[fleetify] -priority = 120 - -[fleetify.effort] -kind = "levels" -levels = ["low", "medium", "high", "xhigh"] -default = "medium" diff --git a/providers/github-copilot/models/gpt-5.2.toml b/providers/github-copilot/models/gpt-5.2.toml deleted file mode 100644 index 11812b5..0000000 --- a/providers/github-copilot/models/gpt-5.2.toml +++ /dev/null @@ -1,31 +0,0 @@ -name = "GPT-5.2" -family = "gpt" -release_date = "2025-12-11" -last_updated = "2025-12-11" -knowledge = "2025-08-31" -attachment = true -reasoning = true -tool_call = true -structured_output = true -temperature = false - -[cost] -input = 1.75 -output = 14.00 -cache_read = 0.175 - -[limit] -context = 400000 -output = 128000 - -[modalities] -input = ["text", "image"] -output = ["text"] - -[fleetify] -priority = 110 - -[fleetify.effort] -kind = "levels" -levels = ["low", "medium", "high", "xhigh"] -default = "medium" diff --git a/providers/github-copilot/models/gpt-5.4-nano.toml b/providers/github-copilot/models/gpt-5.4-nano.toml deleted file mode 100644 index fbd683e..0000000 --- a/providers/github-copilot/models/gpt-5.4-nano.toml +++ /dev/null @@ -1,31 +0,0 @@ -name = "GPT-5.4 nano" -family = "gpt-nano" -release_date = "2026-03-17" -last_updated = "2026-03-17" -knowledge = "2025-08-31" -attachment = true -reasoning = true -tool_call = true -structured_output = true -temperature = false - -[cost] -input = 0.20 -output = 1.25 -cache_read = 0.02 - -[limit] -context = 400000 -output = 128000 - -[modalities] -input = ["text", "image"] -output = ["text"] - -[fleetify] -priority = 40 - -[fleetify.effort] -kind = "levels" -levels = ["low", "medium", "high", "xhigh"] -default = "medium" diff --git a/providers/github-copilot/models/raptor-mini.toml b/providers/github-copilot/models/raptor-mini.toml deleted file mode 100644 index 433d86d..0000000 --- a/providers/github-copilot/models/raptor-mini.toml +++ /dev/null @@ -1,31 +0,0 @@ -name = "Raptor mini" -family = "gpt-mini" -release_date = "2025-08-07" -last_updated = "2026-06-22" -knowledge = "2024-05-30" -attachment = true -reasoning = true -tool_call = true -structured_output = true -temperature = false - -[cost] -input = 0.25 -output = 2.00 -cache_read = 0.025 - -[limit] -context = 264000 -output = 128000 - -[modalities] -input = ["text", "image"] -output = ["text"] - -[fleetify] -priority = 10 - -[fleetify.effort] -kind = "levels" -levels = ["low", "medium", "high", "xhigh"] -default = "medium" From 6b9ed17f304f37ae589f2a401d2c0a0bb48769a6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Doruk=20=C3=96zgen?= Date: Mon, 21 Sep 2026 14:41:14 +0300 Subject: [PATCH 22/30] feat(catalog): add seven Agent API models to perplexity Grok 4.6, Gemini 3.8 Flash, Gemini 3.6 Flash, Claude Fable 5, and three open-weights models Perplexity hosts itself under a `perplexity/` prefix: Kimi K3, GLM 5.3 and Nemotron 3 Ultra. Ids and per-token prices are copied from Perplexity's Agent API models page. Perplexity does not publish context or output limits, so entries carry the upstream vendor's window as the rest of this provider already does. Nemotron 3 Ultra has pricing only. Note that Perplexity bills Gemini 3.6 Flash at $1.50 / $7.50, without the promotion Google and OpenRouter apply. Perplexity does not offer GPT-6 Astra or Claude Fable 5.1. Source: docs.perplexity.ai agent-api/models and changelog. --- .../models/anthropic/claude-fable-5.toml | 28 +++++++++++++++++++ .../models/google/gemini-3.6-flash.toml | 28 +++++++++++++++++++ .../models/google/gemini-3.8-flash.toml | 28 +++++++++++++++++++ .../perplexity/models/perplexity/glm-5.3.toml | 28 +++++++++++++++++++ .../perplexity/models/perplexity/kimi-k3.toml | 27 ++++++++++++++++++ .../nemotron-3-ultra-550b-a55b.toml | 15 ++++++++++ providers/perplexity/models/xai/grok-4.6.toml | 28 +++++++++++++++++++ 7 files changed, 182 insertions(+) create mode 100644 providers/perplexity/models/anthropic/claude-fable-5.toml create mode 100644 providers/perplexity/models/google/gemini-3.6-flash.toml create mode 100644 providers/perplexity/models/google/gemini-3.8-flash.toml create mode 100644 providers/perplexity/models/perplexity/glm-5.3.toml create mode 100644 providers/perplexity/models/perplexity/kimi-k3.toml create mode 100644 providers/perplexity/models/perplexity/nemotron-3-ultra-550b-a55b.toml create mode 100644 providers/perplexity/models/xai/grok-4.6.toml diff --git a/providers/perplexity/models/anthropic/claude-fable-5.toml b/providers/perplexity/models/anthropic/claude-fable-5.toml new file mode 100644 index 0000000..e7b93d4 --- /dev/null +++ b/providers/perplexity/models/anthropic/claude-fable-5.toml @@ -0,0 +1,28 @@ +name = "Claude Fable 5" +family = "claude-fable" +release_date = "2026-06-09" +last_updated = "2026-06-09" +knowledge = "2026-01" +attachment = true +reasoning = true +tool_call = true +structured_output = true +temperature = false + +[cost] +input = 10.00 +output = 50.00 +cache_read = 1.00 + +[limit] +context = 1000000 +output = 128000 + +[modalities] +input = ["text", "image", "pdf"] +output = ["text"] + +[fleetify] +priority = 186 +group = "Agent API" +endpoint = "/v1/agent" diff --git a/providers/perplexity/models/google/gemini-3.6-flash.toml b/providers/perplexity/models/google/gemini-3.6-flash.toml new file mode 100644 index 0000000..2f6396b --- /dev/null +++ b/providers/perplexity/models/google/gemini-3.6-flash.toml @@ -0,0 +1,28 @@ +name = "Gemini 3.6 Flash" +family = "gemini-flash" +release_date = "2026-07-21" +last_updated = "2026-07-21" +knowledge = "2026-03" +attachment = true +reasoning = true +tool_call = true +structured_output = true +temperature = true + +[cost] +input = 1.50 +output = 7.50 +cache_read = 0.15 + +[limit] +context = 1048576 +output = 65536 + +[modalities] +input = ["text", "image", "video", "audio", "pdf"] +output = ["text"] + +[fleetify] +priority = 74 +group = "Agent API" +endpoint = "/v1/agent" diff --git a/providers/perplexity/models/google/gemini-3.8-flash.toml b/providers/perplexity/models/google/gemini-3.8-flash.toml new file mode 100644 index 0000000..436b58b --- /dev/null +++ b/providers/perplexity/models/google/gemini-3.8-flash.toml @@ -0,0 +1,28 @@ +name = "Gemini 3.8 Flash" +family = "gemini-flash" +release_date = "2026-09-02" +last_updated = "2026-09-02" +knowledge = "2026-03" +attachment = true +reasoning = true +tool_call = true +structured_output = true +temperature = true + +[cost] +input = 0.75 +output = 3.75 +cache_read = 0.075 + +[limit] +context = 1048576 +output = 65536 + +[modalities] +input = ["text", "image", "video", "audio", "pdf"] +output = ["text"] + +[fleetify] +priority = 78 +group = "Agent API" +endpoint = "/v1/agent" diff --git a/providers/perplexity/models/perplexity/glm-5.3.toml b/providers/perplexity/models/perplexity/glm-5.3.toml new file mode 100644 index 0000000..5d9b5f7 --- /dev/null +++ b/providers/perplexity/models/perplexity/glm-5.3.toml @@ -0,0 +1,28 @@ +name = "GLM 5.3" +family = "glm" +release_date = "2026-08-18" +last_updated = "2026-08-18" +attachment = false +reasoning = true +tool_call = true +structured_output = true +temperature = true +open_weights = true + +[cost] +input = 1.40 +output = 4.40 +cache_read = 0.26 + +[limit] +context = 1048576 +output = 131072 + +[modalities] +input = ["text"] +output = ["text"] + +[fleetify] +priority = 33 +group = "Agent API" +endpoint = "/v1/agent" diff --git a/providers/perplexity/models/perplexity/kimi-k3.toml b/providers/perplexity/models/perplexity/kimi-k3.toml new file mode 100644 index 0000000..46fc9a2 --- /dev/null +++ b/providers/perplexity/models/perplexity/kimi-k3.toml @@ -0,0 +1,27 @@ +name = "Kimi K3" +family = "kimi-k3" +release_date = "2026-07-16" +last_updated = "2026-07-16" +attachment = true +reasoning = true +tool_call = true +structured_output = true +temperature = false +open_weights = true + +[cost] +input = 3.00 +output = 15.00 +cache_read = 0.30 + +[limit] +context = 1048576 + +[modalities] +input = ["text", "image", "video"] +output = ["text"] + +[fleetify] +priority = 35 +group = "Agent API" +endpoint = "/v1/agent" diff --git a/providers/perplexity/models/perplexity/nemotron-3-ultra-550b-a55b.toml b/providers/perplexity/models/perplexity/nemotron-3-ultra-550b-a55b.toml new file mode 100644 index 0000000..a6d39ec --- /dev/null +++ b/providers/perplexity/models/perplexity/nemotron-3-ultra-550b-a55b.toml @@ -0,0 +1,15 @@ +name = "Nemotron 3 Ultra" +family = "nemotron" +tool_call = true +open_weights = true + +# Perplexity publishes pricing only for this model; limits are left unset. +[cost] +input = 0.25 +output = 2.50 +cache_read = 0.25 + +[fleetify] +priority = 31 +group = "Agent API" +endpoint = "/v1/agent" diff --git a/providers/perplexity/models/xai/grok-4.6.toml b/providers/perplexity/models/xai/grok-4.6.toml new file mode 100644 index 0000000..a2d2100 --- /dev/null +++ b/providers/perplexity/models/xai/grok-4.6.toml @@ -0,0 +1,28 @@ +name = "Grok 4.6" +family = "grok" +release_date = "2026-08-12" +last_updated = "2026-08-12" +knowledge = "2026-02-01" +attachment = true +reasoning = true +tool_call = true +structured_output = true +temperature = true + +[cost] +input = 2.00 +output = 6.00 +cache_read = 0.50 + +[limit] +context = 500000 + +[modalities] +input = ["text", "image"] +output = ["text"] + +[fleetify] +priority = 28 +group = "Agent API" +endpoint = "/v1/agent" +note = "Input/output pricing doubles for prompts above 200k tokens." From 9b2aa59641060a5983a3dd5f635f8a86787bfbb2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Doruk=20=C3=96zgen?= Date: Mon, 21 Sep 2026 14:41:25 +0300 Subject: [PATCH 23/30] fix(catalog): perplexity bills Claude Sonnet 5 at $2 / $10 Perplexity's Agent API table lists $2 / $10 / $0.20, matching Anthropic's now permanent rate. Drop the expired introductory-pricing note with it. --- providers/perplexity/models/anthropic/claude-sonnet-5.toml | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/providers/perplexity/models/anthropic/claude-sonnet-5.toml b/providers/perplexity/models/anthropic/claude-sonnet-5.toml index 2992ec9..b861fb8 100644 --- a/providers/perplexity/models/anthropic/claude-sonnet-5.toml +++ b/providers/perplexity/models/anthropic/claude-sonnet-5.toml @@ -10,9 +10,9 @@ structured_output = true temperature = false [cost] -input = 3.00 -output = 15.00 -cache_read = 0.30 +input = 2.00 +output = 10.00 +cache_read = 0.20 [limit] context = 1000000 @@ -26,4 +26,3 @@ output = ["text"] priority = 155 group = "Agent API" endpoint = "/v1/agent" -note = "Introductory pricing of $2 / $10 per MTok applies through 2026-08-31." From 6a723989f2011a54b7fc6f895fec1f43215aeaa5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Doruk=20=C3=96zgen?= Date: Mon, 21 Sep 2026 14:41:25 +0300 Subject: [PATCH 24/30] feat(catalog)!: drop four models perplexity no longer serves - google/gemini-2.5-flash: removed from the API on 2026-03-20 - google/gemini-2.5-pro: removed on 2026-04-01 - nvidia/nemotron-3-super-120b-a12b: gone from the Agent API list; the only Nemotron there now is perplexity/nemotron-3-ultra-550b-a55b - xai/grok-4-1-fast-non-reasoning: gone from the list, and xAI retired the model itself on 2026-05-15 The Sonar family is untouched even though Perplexity will stop supporting Sonar Chat Completions on 2026-09-27: it still works today, and replacing the provider default is a separate decision. BREAKING CHANGE: four model ids are gone from the perplexity provider. Sessions pinned to them heal to the provider default. --- .../models/google/gemini-2.5-flash.toml | 28 ------------------- .../models/google/gemini-2.5-pro.toml | 28 ------------------- .../nvidia/nemotron-3-super-120b-a12b.toml | 28 ------------------- .../xai/grok-4-1-fast-non-reasoning.toml | 28 ------------------- 4 files changed, 112 deletions(-) delete mode 100644 providers/perplexity/models/google/gemini-2.5-flash.toml delete mode 100644 providers/perplexity/models/google/gemini-2.5-pro.toml delete mode 100644 providers/perplexity/models/nvidia/nemotron-3-super-120b-a12b.toml delete mode 100644 providers/perplexity/models/xai/grok-4-1-fast-non-reasoning.toml diff --git a/providers/perplexity/models/google/gemini-2.5-flash.toml b/providers/perplexity/models/google/gemini-2.5-flash.toml deleted file mode 100644 index 4d18a0c..0000000 --- a/providers/perplexity/models/google/gemini-2.5-flash.toml +++ /dev/null @@ -1,28 +0,0 @@ -name = "Gemini 2.5 Flash" -family = "gemini-flash" -release_date = "2025-03-20" -last_updated = "2025-06-05" -knowledge = "2025-01" -attachment = true -reasoning = true -tool_call = true -structured_output = true -temperature = true - -[cost] -input = 0.30 -output = 2.50 -cache_read = 0.03 - -[limit] -context = 1048576 -output = 65536 - -[modalities] -input = ["text", "image", "audio", "video", "pdf"] -output = ["text"] - -[fleetify] -priority = 40 -group = "Agent API" -endpoint = "/v1/agent" diff --git a/providers/perplexity/models/google/gemini-2.5-pro.toml b/providers/perplexity/models/google/gemini-2.5-pro.toml deleted file mode 100644 index bd8017c..0000000 --- a/providers/perplexity/models/google/gemini-2.5-pro.toml +++ /dev/null @@ -1,28 +0,0 @@ -name = "Gemini 2.5 Pro" -family = "gemini-pro" -release_date = "2025-03-20" -last_updated = "2025-06-05" -knowledge = "2025-01" -attachment = true -reasoning = true -tool_call = true -structured_output = true -temperature = true - -[cost] -input = 1.25 -output = 10.00 -cache_read = 0.125 - -[limit] -context = 1048576 -output = 65536 - -[modalities] -input = ["text", "image", "audio", "video", "pdf"] -output = ["text"] - -[fleetify] -priority = 50 -group = "Agent API" -endpoint = "/v1/agent" diff --git a/providers/perplexity/models/nvidia/nemotron-3-super-120b-a12b.toml b/providers/perplexity/models/nvidia/nemotron-3-super-120b-a12b.toml deleted file mode 100644 index c7c9fb8..0000000 --- a/providers/perplexity/models/nvidia/nemotron-3-super-120b-a12b.toml +++ /dev/null @@ -1,28 +0,0 @@ -name = "Nemotron 3 Super 120B" -family = "nemotron" -release_date = "2026-03-11" -last_updated = "2026-03-11" -knowledge = "2026-02" -attachment = false -reasoning = true -tool_call = true -structured_output = true -temperature = true -open_weights = true - -[cost] -input = 0.25 -output = 2.50 - -[limit] -context = 1000000 -output = 32000 - -[modalities] -input = ["text"] -output = ["text"] - -[fleetify] -priority = 30 -group = "Agent API" -endpoint = "/v1/agent" diff --git a/providers/perplexity/models/xai/grok-4-1-fast-non-reasoning.toml b/providers/perplexity/models/xai/grok-4-1-fast-non-reasoning.toml deleted file mode 100644 index 6e22aa1..0000000 --- a/providers/perplexity/models/xai/grok-4-1-fast-non-reasoning.toml +++ /dev/null @@ -1,28 +0,0 @@ -name = "Grok 4.1 Fast (Non-Reasoning)" -family = "grok" -release_date = "2025-11-19" -last_updated = "2025-11-19" -knowledge = "2025-07" -attachment = true -reasoning = false -tool_call = true -structured_output = true -temperature = true - -[cost] -input = 0.20 -output = 0.50 -cache_read = 0.05 - -[limit] -context = 2000000 -output = 30000 - -[modalities] -input = ["text", "image"] -output = ["text"] - -[fleetify] -priority = 20 -group = "Agent API" -endpoint = "/v1/agent" From ae2c3ec611ba6f462c9bb624bdf3171374b96175 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Doruk=20=C3=96zgen?= Date: Mon, 21 Sep 2026 14:46:01 +0300 Subject: [PATCH 25/30] feat(catalog): add five models to cloudflare-workers-ai GLM 5.3 and GLM 5.3 Flash (1.31M context), DeepSeek V4 Pro 0813 and V4 Flash 0731 (Cloudflare's first 1M-context models) and Qwen 3.8 27B, all added to Workers AI between 2026-08-14 and 2026-08-28 with function calling and reasoning. GLM 5.3 Flash and Qwen 3.8 27B also take images. Ids, context windows and unit prices come from Cloudflare's model pages and pricing table. Four of the five need the Workers Paid plan, which a note records; Qwen 3.8 27B does not. Cloudflare publishes no output limit or JSON-mode row for these models, so both are left unset. Llama 3.3 70B stays the default. GLM 5.2 is skipped: 5.3 replaced it at the same price. Source: developers.cloudflare.com workers-ai models, pricing and changelog. --- .../deepseek-ai/deepseek-v4-flash-0731.toml | 25 +++++++++++++++++++ .../@cf/deepseek-ai/deepseek-v4-pro-0813.toml | 25 +++++++++++++++++++ .../models/@cf/qwen/qwen3.8-27b.toml | 23 +++++++++++++++++ .../models/@cf/zai-org/glm-5.3-flash.toml | 25 +++++++++++++++++++ .../models/@cf/zai-org/glm-5.3.toml | 25 +++++++++++++++++++ 5 files changed, 123 insertions(+) create mode 100644 providers/cloudflare-workers-ai/models/@cf/deepseek-ai/deepseek-v4-flash-0731.toml create mode 100644 providers/cloudflare-workers-ai/models/@cf/deepseek-ai/deepseek-v4-pro-0813.toml create mode 100644 providers/cloudflare-workers-ai/models/@cf/qwen/qwen3.8-27b.toml create mode 100644 providers/cloudflare-workers-ai/models/@cf/zai-org/glm-5.3-flash.toml create mode 100644 providers/cloudflare-workers-ai/models/@cf/zai-org/glm-5.3.toml diff --git a/providers/cloudflare-workers-ai/models/@cf/deepseek-ai/deepseek-v4-flash-0731.toml b/providers/cloudflare-workers-ai/models/@cf/deepseek-ai/deepseek-v4-flash-0731.toml new file mode 100644 index 0000000..0f595c6 --- /dev/null +++ b/providers/cloudflare-workers-ai/models/@cf/deepseek-ai/deepseek-v4-flash-0731.toml @@ -0,0 +1,25 @@ +name = "DeepSeek V4 Flash" +family = "deepseek-flash" +release_date = "2026-04-24" +last_updated = "2026-07-31" +attachment = false +reasoning = true +tool_call = true +temperature = true +open_weights = true + +[cost] +input = 0.44 +output = 1.32 +cache_read = 0.014 + +[limit] +context = 1048576 + +[modalities] +input = ["text"] +output = ["text"] + +[fleetify] +priority = 154 +note = "Requires the Workers Paid plan." diff --git a/providers/cloudflare-workers-ai/models/@cf/deepseek-ai/deepseek-v4-pro-0813.toml b/providers/cloudflare-workers-ai/models/@cf/deepseek-ai/deepseek-v4-pro-0813.toml new file mode 100644 index 0000000..6bcf32e --- /dev/null +++ b/providers/cloudflare-workers-ai/models/@cf/deepseek-ai/deepseek-v4-pro-0813.toml @@ -0,0 +1,25 @@ +name = "DeepSeek V4 Pro" +family = "deepseek-thinking" +release_date = "2026-04-24" +last_updated = "2026-08-13" +attachment = false +reasoning = true +tool_call = true +temperature = true +open_weights = true + +[cost] +input = 1.32 +output = 3.96 +cache_read = 0.044 + +[limit] +context = 1048576 + +[modalities] +input = ["text"] +output = ["text"] + +[fleetify] +priority = 174 +note = "Requires the Workers Paid plan." diff --git a/providers/cloudflare-workers-ai/models/@cf/qwen/qwen3.8-27b.toml b/providers/cloudflare-workers-ai/models/@cf/qwen/qwen3.8-27b.toml new file mode 100644 index 0000000..b1d9a92 --- /dev/null +++ b/providers/cloudflare-workers-ai/models/@cf/qwen/qwen3.8-27b.toml @@ -0,0 +1,23 @@ +name = "Qwen 3.8 27B" +family = "qwen" +release_date = "2026-08-14" +last_updated = "2026-08-17" +attachment = true +reasoning = true +tool_call = true +temperature = true + +[cost] +input = 0.45 +output = 3.20 +cache_read = 0.05 + +[limit] +context = 262144 + +[modalities] +input = ["text", "image"] +output = ["text"] + +[fleetify] +priority = 152 diff --git a/providers/cloudflare-workers-ai/models/@cf/zai-org/glm-5.3-flash.toml b/providers/cloudflare-workers-ai/models/@cf/zai-org/glm-5.3-flash.toml new file mode 100644 index 0000000..845d7b2 --- /dev/null +++ b/providers/cloudflare-workers-ai/models/@cf/zai-org/glm-5.3-flash.toml @@ -0,0 +1,25 @@ +name = "GLM 5.3 Flash" +family = "glm-flash" +release_date = "2026-08-25" +last_updated = "2026-08-26" +attachment = true +reasoning = true +tool_call = true +temperature = true +open_weights = true + +[cost] +input = 0.15 +output = 0.50 +cache_read = 0.03 + +[limit] +context = 1310720 + +[modalities] +input = ["text", "image"] +output = ["text"] + +[fleetify] +priority = 156 +note = "Requires the Workers Paid plan." diff --git a/providers/cloudflare-workers-ai/models/@cf/zai-org/glm-5.3.toml b/providers/cloudflare-workers-ai/models/@cf/zai-org/glm-5.3.toml new file mode 100644 index 0000000..539914c --- /dev/null +++ b/providers/cloudflare-workers-ai/models/@cf/zai-org/glm-5.3.toml @@ -0,0 +1,25 @@ +name = "GLM 5.3" +family = "glm" +release_date = "2026-08-18" +last_updated = "2026-08-28" +attachment = false +reasoning = true +tool_call = true +temperature = true +open_weights = true + +[cost] +input = 1.40 +output = 4.40 +cache_read = 0.26 + +[limit] +context = 1310720 + +[modalities] +input = ["text"] +output = ["text"] + +[fleetify] +priority = 176 +note = "Requires the Workers Paid plan." From 1fd43925df8b37ad1b94b73e340454b96b7b5cb7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Doruk=20=C3=96zgen?= Date: Mon, 21 Sep 2026 14:46:01 +0300 Subject: [PATCH 26/30] fix(catalog): cloudflare-workers-ai paid-plan notes and small corrections - Kimi K2.6 and Kimi K2.7 Code have required the Workers Paid plan since 2026-07-28; on the Free plan they return 403. Note it on both. - Kimi K2.7 Code reached Workers AI on 2026-06-12; the entry had no dates. - GLM-4.7-Flash input is $0.060 per MTok, not $0.0605. All 19 existing ids are still in Cloudflare's live model index. --- .../cloudflare-workers-ai/models/@cf/moonshotai/kimi-k2.6.toml | 1 + .../models/@cf/moonshotai/kimi-k2.7-code.toml | 3 +++ .../models/@cf/zai-org/glm-4.7-flash.toml | 2 +- 3 files changed, 5 insertions(+), 1 deletion(-) diff --git a/providers/cloudflare-workers-ai/models/@cf/moonshotai/kimi-k2.6.toml b/providers/cloudflare-workers-ai/models/@cf/moonshotai/kimi-k2.6.toml index 5d79984..66e8abc 100644 --- a/providers/cloudflare-workers-ai/models/@cf/moonshotai/kimi-k2.6.toml +++ b/providers/cloudflare-workers-ai/models/@cf/moonshotai/kimi-k2.6.toml @@ -25,3 +25,4 @@ output = ["text"] [fleetify] priority = 140 +note = "Requires the Workers Paid plan." diff --git a/providers/cloudflare-workers-ai/models/@cf/moonshotai/kimi-k2.7-code.toml b/providers/cloudflare-workers-ai/models/@cf/moonshotai/kimi-k2.7-code.toml index 38f9664..a49f5c7 100644 --- a/providers/cloudflare-workers-ai/models/@cf/moonshotai/kimi-k2.7-code.toml +++ b/providers/cloudflare-workers-ai/models/@cf/moonshotai/kimi-k2.7-code.toml @@ -1,5 +1,7 @@ name = "Kimi K2.7 Code" family = "kimi" +release_date = "2026-06-12" +last_updated = "2026-06-12" attachment = true reasoning = true tool_call = true @@ -21,3 +23,4 @@ output = ["text"] [fleetify] priority = 145 +note = "Requires the Workers Paid plan." diff --git a/providers/cloudflare-workers-ai/models/@cf/zai-org/glm-4.7-flash.toml b/providers/cloudflare-workers-ai/models/@cf/zai-org/glm-4.7-flash.toml index 5788143..576b1f9 100644 --- a/providers/cloudflare-workers-ai/models/@cf/zai-org/glm-4.7-flash.toml +++ b/providers/cloudflare-workers-ai/models/@cf/zai-org/glm-4.7-flash.toml @@ -11,7 +11,7 @@ temperature = true open_weights = true [cost] -input = 0.0605 +input = 0.06 output = 0.40 [limit] From d6392b0de4e274d09a19ee86b3bab0a6314bb611 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Doruk=20=C3=96zgen?= Date: Mon, 21 Sep 2026 14:46:01 +0300 Subject: [PATCH 27/30] feat(catalog): add five models to nvidia-nim Kimi K3, GLM 5.3, GLM 5.3 Flash, Nemotron 3 Ultra 550B and Nemotron 3.5 Lightning 30B. All five are in NVIDIA's public /v1/models listing today, with 1,048,576-token context windows per their build.nvidia.com cards. Kimi K3's card documents low / high / max reasoning effort and a 65,536 `max_tokens` cap. NVIDIA publishes no per-token pricing for the hosted API, so `cost` follows the 0.00 convention the other free-tier entries here already use. Nemotron 3 Super stays the default. Source: integrate.api.nvidia.com/v1/models; build.nvidia.com model cards. --- .../nvidia-nim/models/moonshotai/kimi-k3.toml | 31 +++++++++++++++++++ .../nvidia/nemotron-3-ultra-550b-a55b.toml | 24 ++++++++++++++ .../nemotron-3.5-lightning-30b-a3b.toml | 24 ++++++++++++++ .../nvidia-nim/models/z-ai/glm-5.3-flash.toml | 24 ++++++++++++++ providers/nvidia-nim/models/z-ai/glm-5.3.toml | 24 ++++++++++++++ 5 files changed, 127 insertions(+) create mode 100644 providers/nvidia-nim/models/moonshotai/kimi-k3.toml create mode 100644 providers/nvidia-nim/models/nvidia/nemotron-3-ultra-550b-a55b.toml create mode 100644 providers/nvidia-nim/models/nvidia/nemotron-3.5-lightning-30b-a3b.toml create mode 100644 providers/nvidia-nim/models/z-ai/glm-5.3-flash.toml create mode 100644 providers/nvidia-nim/models/z-ai/glm-5.3.toml diff --git a/providers/nvidia-nim/models/moonshotai/kimi-k3.toml b/providers/nvidia-nim/models/moonshotai/kimi-k3.toml new file mode 100644 index 0000000..4713697 --- /dev/null +++ b/providers/nvidia-nim/models/moonshotai/kimi-k3.toml @@ -0,0 +1,31 @@ +name = "Kimi K3" +family = "kimi-k3" +release_date = "2026-07-16" +last_updated = "2026-07-16" +attachment = true +reasoning = true +tool_call = true +structured_output = true +temperature = true +open_weights = true + +[cost] +input = 0.00 +output = 0.00 + +[limit] +context = 1048576 +output = 65536 + +[modalities] +input = ["text", "image"] +output = ["text"] + +[fleetify] +priority = 98 + +# NIM caps `max_tokens` at 65,536 for K3. It always reasons; effort picks the depth. +[fleetify.effort] +kind = "levels" +levels = ["low", "high", "max"] +default = "high" diff --git a/providers/nvidia-nim/models/nvidia/nemotron-3-ultra-550b-a55b.toml b/providers/nvidia-nim/models/nvidia/nemotron-3-ultra-550b-a55b.toml new file mode 100644 index 0000000..843e5d6 --- /dev/null +++ b/providers/nvidia-nim/models/nvidia/nemotron-3-ultra-550b-a55b.toml @@ -0,0 +1,24 @@ +name = "Nemotron 3 Ultra" +family = "nemotron" +release_date = "2026-06-04" +last_updated = "2026-06-04" +attachment = false +reasoning = true +tool_call = true +structured_output = true +temperature = true +open_weights = true + +[cost] +input = 0.00 +output = 0.00 + +[limit] +context = 1048576 + +[modalities] +input = ["text"] +output = ["text"] + +[fleetify] +priority = 94 diff --git a/providers/nvidia-nim/models/nvidia/nemotron-3.5-lightning-30b-a3b.toml b/providers/nvidia-nim/models/nvidia/nemotron-3.5-lightning-30b-a3b.toml new file mode 100644 index 0000000..579a2d0 --- /dev/null +++ b/providers/nvidia-nim/models/nvidia/nemotron-3.5-lightning-30b-a3b.toml @@ -0,0 +1,24 @@ +name = "Nemotron 3.5 Lightning" +family = "nemotron" +release_date = "2026-08-11" +last_updated = "2026-08-11" +attachment = false +reasoning = true +tool_call = true +structured_output = true +temperature = true +open_weights = true + +[cost] +input = 0.00 +output = 0.00 + +[limit] +context = 1048576 + +[modalities] +input = ["text"] +output = ["text"] + +[fleetify] +priority = 86 diff --git a/providers/nvidia-nim/models/z-ai/glm-5.3-flash.toml b/providers/nvidia-nim/models/z-ai/glm-5.3-flash.toml new file mode 100644 index 0000000..46bdba4 --- /dev/null +++ b/providers/nvidia-nim/models/z-ai/glm-5.3-flash.toml @@ -0,0 +1,24 @@ +name = "GLM 5.3 Flash" +family = "glm-flash" +release_date = "2026-08-25" +last_updated = "2026-08-25" +attachment = true +reasoning = true +tool_call = true +structured_output = true +temperature = true +open_weights = true + +[cost] +input = 0.00 +output = 0.00 + +[limit] +context = 1048576 + +[modalities] +input = ["text", "image"] +output = ["text"] + +[fleetify] +priority = 88 diff --git a/providers/nvidia-nim/models/z-ai/glm-5.3.toml b/providers/nvidia-nim/models/z-ai/glm-5.3.toml new file mode 100644 index 0000000..c0272f5 --- /dev/null +++ b/providers/nvidia-nim/models/z-ai/glm-5.3.toml @@ -0,0 +1,24 @@ +name = "GLM 5.3" +family = "glm" +release_date = "2026-08-18" +last_updated = "2026-08-18" +attachment = false +reasoning = true +tool_call = true +structured_output = true +temperature = true +open_weights = true + +[cost] +input = 0.00 +output = 0.00 + +[limit] +context = 1048576 + +[modalities] +input = ["text"] +output = ["text"] + +[fleetify] +priority = 96 From 5d0ad31073649d9beb3688e1766fdc6e8741d461 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Doruk=20=C3=96zgen?= Date: Mon, 21 Sep 2026 14:46:01 +0300 Subject: [PATCH 28/30] fix(catalog): Nemotron 3 Super has a 1M context window on nvidia-nim build.nvidia.com reports `contextLength: 1048576` for nvidia/nemotron-3-super-120b-a12b. The entry said 262,144, and it is the provider default. Cloudflare's copy of the model legitimately stays at 256K, which is Cloudflare's own serving limit. --- .../nvidia-nim/models/nvidia/nemotron-3-super-120b-a12b.toml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/providers/nvidia-nim/models/nvidia/nemotron-3-super-120b-a12b.toml b/providers/nvidia-nim/models/nvidia/nemotron-3-super-120b-a12b.toml index 8ed5e5c..0008d6a 100644 --- a/providers/nvidia-nim/models/nvidia/nemotron-3-super-120b-a12b.toml +++ b/providers/nvidia-nim/models/nvidia/nemotron-3-super-120b-a12b.toml @@ -15,7 +15,7 @@ input = 0.20 output = 0.80 [limit] -context = 262144 +context = 1048576 output = 262144 [modalities] From 28896dadeadbd20b0d81d8554fa05fc70b207665 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Doruk=20=C3=96zgen?= Date: Mon, 21 Sep 2026 14:46:01 +0300 Subject: [PATCH 29/30] feat(catalog)!: drop six models nvidia-nim no longer lists None of these ids is in NVIDIA's public /v1/models listing any more. Deprecated with a dated notice on build.nvidia.com: - openai/gpt-oss-120b 2026-09-02 - minimaxai/minimax-m2.7 2026-07-27 - z-ai/glm-5.1 2026-07-02 Absent without a notice: - deepseek-ai/deepseek-v4-flash, deepseek-ai/deepseek-v4-pro (no DeepSeek V4 id of any spelling is served) - meta/llama-4-maverick-17b-128e-instruct The provider uses live discovery, so anything NVIDIA brings back will still surface in the picker. BREAKING CHANGE: six model ids are gone from the nvidia-nim provider. Sessions pinned to them heal to the provider default. --- .../models/deepseek-ai/deepseek-v4-flash.toml | 27 ------------------- .../models/deepseek-ai/deepseek-v4-pro.toml | 27 ------------------- .../llama-4-maverick-17b-128e-instruct.toml | 25 ----------------- .../models/minimaxai/minimax-m2.7.toml | 25 ----------------- .../models/openai/gpt-oss-120b.toml | 25 ----------------- providers/nvidia-nim/models/z-ai/glm-5.1.toml | 25 ----------------- 6 files changed, 154 deletions(-) delete mode 100644 providers/nvidia-nim/models/deepseek-ai/deepseek-v4-flash.toml delete mode 100644 providers/nvidia-nim/models/deepseek-ai/deepseek-v4-pro.toml delete mode 100644 providers/nvidia-nim/models/meta/llama-4-maverick-17b-128e-instruct.toml delete mode 100644 providers/nvidia-nim/models/minimaxai/minimax-m2.7.toml delete mode 100644 providers/nvidia-nim/models/openai/gpt-oss-120b.toml delete mode 100644 providers/nvidia-nim/models/z-ai/glm-5.1.toml diff --git a/providers/nvidia-nim/models/deepseek-ai/deepseek-v4-flash.toml b/providers/nvidia-nim/models/deepseek-ai/deepseek-v4-flash.toml deleted file mode 100644 index 49bb2ee..0000000 --- a/providers/nvidia-nim/models/deepseek-ai/deepseek-v4-flash.toml +++ /dev/null @@ -1,27 +0,0 @@ -name = "DeepSeek V4 Flash" -family = "deepseek-flash" -release_date = "2026-04-24" -last_updated = "2026-04-24" -knowledge = "2025-05" -attachment = false -reasoning = true -tool_call = true -structured_output = true -temperature = true -open_weights = true - -[cost] -input = 0.14 -output = 0.28 -cache_read = 0.0028 - -[limit] -context = 1048576 -output = 393216 - -[modalities] -input = ["text"] -output = ["text"] - -[fleetify] -priority = 60 diff --git a/providers/nvidia-nim/models/deepseek-ai/deepseek-v4-pro.toml b/providers/nvidia-nim/models/deepseek-ai/deepseek-v4-pro.toml deleted file mode 100644 index e81094e..0000000 --- a/providers/nvidia-nim/models/deepseek-ai/deepseek-v4-pro.toml +++ /dev/null @@ -1,27 +0,0 @@ -name = "DeepSeek V4 Pro" -family = "deepseek-thinking" -release_date = "2026-04-24" -last_updated = "2026-04-24" -knowledge = "2025-05" -attachment = false -reasoning = true -tool_call = true -structured_output = true -temperature = true -open_weights = true - -[cost] -input = 0.435 -output = 0.87 -cache_read = 0.003625 - -[limit] -context = 1048576 -output = 393216 - -[modalities] -input = ["text"] -output = ["text"] - -[fleetify] -priority = 70 diff --git a/providers/nvidia-nim/models/meta/llama-4-maverick-17b-128e-instruct.toml b/providers/nvidia-nim/models/meta/llama-4-maverick-17b-128e-instruct.toml deleted file mode 100644 index 4b9049c..0000000 --- a/providers/nvidia-nim/models/meta/llama-4-maverick-17b-128e-instruct.toml +++ /dev/null @@ -1,25 +0,0 @@ -name = "Llama 4 Maverick 17b 128e Instruct" -release_date = "2025-04-01" -last_updated = "2025-04-01" -knowledge = "2024-02" -attachment = true -reasoning = false -tool_call = true -structured_output = true -temperature = true -open_weights = true - -[cost] -input = 0.00 -output = 0.00 - -[limit] -context = 128000 -output = 4096 - -[modalities] -input = ["text", "image"] -output = ["text"] - -[fleetify] -priority = 40 diff --git a/providers/nvidia-nim/models/minimaxai/minimax-m2.7.toml b/providers/nvidia-nim/models/minimaxai/minimax-m2.7.toml deleted file mode 100644 index 3c86d5d..0000000 --- a/providers/nvidia-nim/models/minimaxai/minimax-m2.7.toml +++ /dev/null @@ -1,25 +0,0 @@ -name = "MiniMax-M2.7" -family = "minimax" -release_date = "2026-03-18" -last_updated = "2026-04-11" -attachment = false -reasoning = true -tool_call = true -structured_output = true -temperature = true -open_weights = true - -[cost] -input = 0.00 -output = 0.00 - -[limit] -context = 204800 -output = 131072 - -[modalities] -input = ["text"] -output = ["text"] - -[fleetify] -priority = 80 diff --git a/providers/nvidia-nim/models/openai/gpt-oss-120b.toml b/providers/nvidia-nim/models/openai/gpt-oss-120b.toml deleted file mode 100644 index b615cb5..0000000 --- a/providers/nvidia-nim/models/openai/gpt-oss-120b.toml +++ /dev/null @@ -1,25 +0,0 @@ -name = "GPT-OSS-120B" -family = "gpt-oss" -release_date = "2025-08-04" -last_updated = "2025-08-14" -knowledge = "2025-08" -attachment = true -reasoning = true -tool_call = false -structured_output = false -temperature = true - -[cost] -input = 0.00 -output = 0.00 - -[limit] -context = 128000 -output = 8192 - -[modalities] -input = ["text"] -output = ["text"] - -[fleetify] -priority = 30 diff --git a/providers/nvidia-nim/models/z-ai/glm-5.1.toml b/providers/nvidia-nim/models/z-ai/glm-5.1.toml deleted file mode 100644 index 3dc75ef..0000000 --- a/providers/nvidia-nim/models/z-ai/glm-5.1.toml +++ /dev/null @@ -1,25 +0,0 @@ -name = "GLM-5.1" -family = "glm" -release_date = "2026-03-27" -last_updated = "2026-03-27" -attachment = false -reasoning = true -tool_call = true -structured_output = true -temperature = true -open_weights = true - -[cost] -input = 0.00 -output = 0.00 - -[limit] -context = 131072 -output = 131072 - -[modalities] -input = ["text"] -output = ["text"] - -[fleetify] -priority = 90 From 2cf0e9e442bca67cf41c41cc2ed1b0b44663453d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Doruk=20=C3=96zgen?= Date: Mon, 21 Sep 2026 14:46:19 +0300 Subject: [PATCH 30/30] chore: rebuild dist/ Regenerated with `bun run build` after the September 2026 catalog refresh: 17 providers, 184 models. --- dist/index.json | 28 +- dist/models.json | 2898 +++++++++++++-------- dist/providers/anthropic.json | 60 +- dist/providers/antigravity-cli.json | 4 +- dist/providers/antigravity-sdk.json | 253 +- dist/providers/claude-code.json | 68 +- dist/providers/cloudflare-workers-ai.json | 221 +- dist/providers/codex-cli.json | 117 +- dist/providers/deepseek.json | 64 +- dist/providers/gemini-api.json | 116 +- dist/providers/github-copilot.json | 588 ++--- dist/providers/grok.json | 131 +- dist/providers/kimi-api.json | 70 +- dist/providers/kimi-code.json | 63 +- dist/providers/mistral.json | 111 +- dist/providers/nvidia-nim.json | 257 +- dist/providers/openai.json | 34 +- dist/providers/openrouter.json | 301 ++- dist/providers/perplexity.json | 352 ++- 19 files changed, 3690 insertions(+), 2046 deletions(-) diff --git a/dist/index.json b/dist/index.json index 72de88d..6134133 100644 --- a/dist/index.json +++ b/dist/index.json @@ -1,13 +1,13 @@ { "schemaVersion": 1, - "generatedAt": "2026-08-01T15:53:14.483Z", - "commit": "4f94308", + "generatedAt": "2026-09-21T11:46:14.774Z", + "commit": "28896da", "providers": [ { "id": "anthropic", "name": "Anthropic", "kind": "api", - "modelCount": 4 + "modelCount": 5 }, { "id": "antigravity-cli", @@ -19,19 +19,19 @@ "id": "antigravity-sdk", "name": "Antigravity SDK", "kind": "cli", - "modelCount": 11 + "modelCount": 14 }, { "id": "claude-code", "name": "Claude Code", "kind": "cli", - "modelCount": 5 + "modelCount": 6 }, { "id": "cloudflare-workers-ai", "name": "Cloudflare Workers AI", "kind": "api", - "modelCount": 19 + "modelCount": 24 }, { "id": "codex-cli", @@ -49,19 +49,19 @@ "id": "gemini-api", "name": "Google", "kind": "api", - "modelCount": 9 + "modelCount": 11 }, { "id": "github-copilot", "name": "GitHub Copilot CLI", "kind": "cli", - "modelCount": 28 + "modelCount": 24 }, { "id": "grok", "name": "xAI", "kind": "api", - "modelCount": 4 + "modelCount": 6 }, { "id": "kimi-api", @@ -73,19 +73,19 @@ "id": "kimi-code", "name": "Kimi Code CLI", "kind": "cli", - "modelCount": 4 + "modelCount": 3 }, { "id": "mistral", "name": "Mistral", "kind": "api", - "modelCount": 4 + "modelCount": 5 }, { "id": "nvidia-nim", "name": "NVIDIA NIM", "kind": "api", - "modelCount": 10 + "modelCount": 9 }, { "id": "openai", @@ -97,13 +97,13 @@ "id": "openrouter", "name": "OpenRouter", "kind": "api", - "modelCount": 16 + "modelCount": 22 }, { "id": "perplexity", "name": "Perplexity", "kind": "api", - "modelCount": 30 + "modelCount": 33 } ] } diff --git a/dist/models.json b/dist/models.json index 5a3d965..1d76131 100644 --- a/dist/models.json +++ b/dist/models.json @@ -1,7 +1,7 @@ { "schemaVersion": 1, - "generatedAt": "2026-08-01T15:53:14.483Z", - "commit": "4f94308", + "generatedAt": "2026-09-21T11:46:14.774Z", + "commit": "28896da", "providers": { "anthropic": { "id": "anthropic", @@ -57,7 +57,51 @@ "aliases": [], "release_date": "2026-06-09", "last_updated": "2026-06-09", - "knowledge": null + "knowledge": "2026-01" + }, + { + "id": "claude-fable-5-1", + "label": "Claude Fable 5.1", + "family": "claude-fable", + "context": 1000000, + "output_limit": 128000, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": true, + "structured_output": true, + "temperature": false, + "open_weights": false, + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 10, + "output": 50, + "cache_read": 0.25, + "cache_write": 12.5 + }, + "group": null, + "note": null, + "endpoint": null, + "hidden": false, + "active": true, + "priority": 45, + "default": false, + "aliases": [], + "release_date": "2026-09-01", + "last_updated": "2026-09-01", + "knowledge": "2026-06" }, { "id": "claude-haiku-4-5", @@ -174,13 +218,13 @@ ] }, "cost": { - "input": 3, - "output": 15, - "cache_read": 0.3, - "cache_write": 3.75 + "input": 2, + "output": 10, + "cache_read": 0.2, + "cache_write": 2.5 }, "group": null, - "note": "Introductory pricing of $2 / $10 per MTok applies through 2026-08-31.", + "note": null, "endpoint": null, "hidden": false, "active": true, @@ -433,8 +477,8 @@ "knowledge": "2025-01" }, { - "id": "gemini-3.5-flash-high", - "label": "Gemini 3.5 Flash (High)", + "id": "gemini-3.6-flash-high", + "label": "Gemini 3.6 Flash (High)", "family": "gemini-flash", "context": 1048576, "output_limit": 65536, @@ -461,25 +505,25 @@ ] }, "cost": { - "input": 1.5, - "output": 9, - "cache_read": 0.15 + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 }, "group": null, - "note": null, + "note": "Introductory pricing through 2026-12-31; $1.50 / $7.50 per MTok from 2027-01-01.", "endpoint": null, "hidden": false, "active": true, - "priority": 50, + "priority": 100, "default": false, "aliases": [], - "release_date": "2026-05-19", - "last_updated": "2026-05-19", - "knowledge": "2025-01" + "release_date": "2026-07-21", + "last_updated": "2026-07-21", + "knowledge": "2026-03" }, { - "id": "gemini-3.5-flash-low", - "label": "Gemini 3.5 Flash (Low)", + "id": "gemini-3.6-flash-low", + "label": "Gemini 3.6 Flash (Low)", "family": "gemini-flash", "context": 1048576, "output_limit": 65536, @@ -506,25 +550,25 @@ ] }, "cost": { - "input": 1.5, - "output": 9, - "cache_read": 0.15 + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 }, "group": null, - "note": null, + "note": "Introductory pricing through 2026-12-31; $1.50 / $7.50 per MTok from 2027-01-01.", "endpoint": null, "hidden": false, "active": true, - "priority": 35, + "priority": 80, "default": false, "aliases": [], - "release_date": "2026-05-19", - "last_updated": "2026-05-19", - "knowledge": "2025-01" + "release_date": "2026-07-21", + "last_updated": "2026-07-21", + "knowledge": "2026-03" }, { - "id": "gemini-3.5-flash-medium", - "label": "Gemini 3.5 Flash (Medium)", + "id": "gemini-3.6-flash-medium", + "label": "Gemini 3.6 Flash (Medium)", "family": "gemini-flash", "context": 1048576, "output_limit": 65536, @@ -551,25 +595,25 @@ ] }, "cost": { - "input": 1.5, - "output": 9, - "cache_read": 0.15 + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 }, "group": null, - "note": null, + "note": "Introductory pricing through 2026-12-31; $1.50 / $7.50 per MTok from 2027-01-01.", "endpoint": null, "hidden": false, "active": true, - "priority": 40, + "priority": 90, "default": false, "aliases": [], - "release_date": "2026-05-19", - "last_updated": "2026-05-19", - "knowledge": "2025-01" + "release_date": "2026-07-21", + "last_updated": "2026-07-21", + "knowledge": "2026-03" }, { - "id": "gemini-3.6-flash-high", - "label": "Gemini 3.6 Flash (High)", + "id": "gemini-3.7-flash-high", + "label": "Gemini 3.7 Flash (High)", "family": "gemini-flash", "context": 1048576, "output_limit": 65536, @@ -596,25 +640,25 @@ ] }, "cost": { - "input": 1.5, - "output": 7.5, - "cache_read": 0.15 + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 }, "group": null, - "note": null, + "note": "Introductory pricing through 2026-12-31; $1.50 / $7.50 per MTok from 2027-01-01.", "endpoint": null, "hidden": false, "active": true, - "priority": 100, + "priority": 130, "default": false, "aliases": [], - "release_date": "2026-07-21", - "last_updated": "2026-07-21", + "release_date": "2026-08-13", + "last_updated": "2026-08-13", "knowledge": "2026-03" }, { - "id": "gemini-3.6-flash-low", - "label": "Gemini 3.6 Flash (Low)", + "id": "gemini-3.7-flash-low", + "label": "Gemini 3.7 Flash (Low)", "family": "gemini-flash", "context": 1048576, "output_limit": 65536, @@ -641,25 +685,25 @@ ] }, "cost": { - "input": 1.5, - "output": 7.5, - "cache_read": 0.15 + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 }, "group": null, - "note": null, + "note": "Introductory pricing through 2026-12-31; $1.50 / $7.50 per MTok from 2027-01-01.", "endpoint": null, "hidden": false, "active": true, - "priority": 80, + "priority": 110, "default": false, "aliases": [], - "release_date": "2026-07-21", - "last_updated": "2026-07-21", + "release_date": "2026-08-13", + "last_updated": "2026-08-13", "knowledge": "2026-03" }, { - "id": "gemini-3.6-flash-medium", - "label": "Gemini 3.6 Flash (Medium)", + "id": "gemini-3.7-flash-medium", + "label": "Gemini 3.7 Flash (Medium)", "family": "gemini-flash", "context": 1048576, "output_limit": 65536, @@ -686,20 +730,155 @@ ] }, "cost": { - "input": 1.5, - "output": 7.5, - "cache_read": 0.15 + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 }, "group": null, - "note": null, + "note": "Introductory pricing through 2026-12-31; $1.50 / $7.50 per MTok from 2027-01-01.", "endpoint": null, "hidden": false, "active": true, - "priority": 90, + "priority": 120, "default": false, "aliases": [], - "release_date": "2026-07-21", - "last_updated": "2026-07-21", + "release_date": "2026-08-13", + "last_updated": "2026-08-13", + "knowledge": "2026-03" + }, + { + "id": "gemini-3.8-flash-high", + "label": "Gemini 3.8 Flash (High)", + "family": "gemini-flash", + "context": 1048576, + "output_limit": 65536, + "reasoning": true, + "supports_effort": false, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": true, + "structured_output": true, + "temperature": true, + "open_weights": false, + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 + }, + "group": null, + "note": "Introductory pricing through 2026-12-31; $1.50 / $7.50 per MTok from 2027-01-01.", + "endpoint": null, + "hidden": false, + "active": true, + "priority": 160, + "default": false, + "aliases": [], + "release_date": "2026-09-02", + "last_updated": "2026-09-02", + "knowledge": "2026-03" + }, + { + "id": "gemini-3.8-flash-low", + "label": "Gemini 3.8 Flash (Low)", + "family": "gemini-flash", + "context": 1048576, + "output_limit": 65536, + "reasoning": true, + "supports_effort": false, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": true, + "structured_output": true, + "temperature": true, + "open_weights": false, + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 + }, + "group": null, + "note": "Introductory pricing through 2026-12-31; $1.50 / $7.50 per MTok from 2027-01-01.", + "endpoint": null, + "hidden": false, + "active": true, + "priority": 140, + "default": false, + "aliases": [], + "release_date": "2026-09-02", + "last_updated": "2026-09-02", + "knowledge": "2026-03" + }, + { + "id": "gemini-3.8-flash-medium", + "label": "Gemini 3.8 Flash (Medium)", + "family": "gemini-flash", + "context": 1048576, + "output_limit": 65536, + "reasoning": true, + "supports_effort": false, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": true, + "structured_output": true, + "temperature": true, + "open_weights": false, + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 + }, + "group": null, + "note": "Introductory pricing through 2026-12-31; $1.50 / $7.50 per MTok from 2027-01-01.", + "endpoint": null, + "hidden": false, + "active": true, + "priority": 150, + "default": false, + "aliases": [], + "release_date": "2026-09-02", + "last_updated": "2026-09-02", "knowledge": "2026-03" }, { @@ -804,14 +983,66 @@ "aliases": [], "release_date": "2026-06-09", "last_updated": "2026-06-09", - "knowledge": null + "knowledge": "2026-01" }, { - "id": "claude-haiku-4-5-20251001", - "label": "Haiku 4.5", - "family": "claude-haiku", - "context": 200000, - "output_limit": 64000, + "id": "claude-fable-5-1", + "label": "Fable 5.1", + "family": "claude-fable", + "context": 1000000, + "output_limit": 128000, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "levels", + "levels": [ + "low", + "medium", + "high", + "xhigh", + "max" + ], + "default": "high" + }, + "tool_call": true, + "attachment": true, + "structured_output": true, + "temperature": false, + "open_weights": false, + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 10, + "output": 50, + "cache_read": 0.25, + "cache_write": 12.5 + }, + "group": null, + "note": null, + "endpoint": null, + "hidden": false, + "active": true, + "priority": 65, + "default": false, + "aliases": [], + "release_date": "2026-09-01", + "last_updated": "2026-09-01", + "knowledge": "2026-06" + }, + { + "id": "claude-haiku-4-5-20251001", + "label": "Haiku 4.5", + "family": "claude-haiku", + "context": 200000, + "output_limit": 64000, "reasoning": true, "supports_effort": false, "effort": { @@ -991,13 +1222,13 @@ ] }, "cost": { - "input": 3, - "output": 15, - "cache_read": 0.3, - "cache_write": 3.75 + "input": 2, + "output": 10, + "cache_read": 0.2, + "cache_write": 2.5 }, "group": null, - "note": "Introductory pricing of $2 / $10 per MTok applies through 2026-08-31.", + "note": null, "endpoint": null, "hidden": false, "active": true, @@ -1102,6 +1333,88 @@ "last_updated": "2025-01-22", "knowledge": null }, + { + "id": "@cf/deepseek-ai/deepseek-v4-flash-0731", + "label": "DeepSeek V4 Flash", + "family": "deepseek-flash", + "context": 1048576, + "output_limit": null, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": false, + "structured_output": false, + "temperature": true, + "open_weights": true, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 0.44, + "output": 1.32, + "cache_read": 0.014 + }, + "group": null, + "note": "Requires the Workers Paid plan.", + "endpoint": null, + "hidden": false, + "active": true, + "priority": 154, + "default": false, + "aliases": [], + "release_date": "2026-04-24", + "last_updated": "2026-07-31", + "knowledge": null + }, + { + "id": "@cf/deepseek-ai/deepseek-v4-pro-0813", + "label": "DeepSeek V4 Pro", + "family": "deepseek-thinking", + "context": 1048576, + "output_limit": null, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": false, + "structured_output": false, + "temperature": true, + "open_weights": true, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 1.32, + "output": 3.96, + "cache_read": 0.044 + }, + "group": null, + "note": "Requires the Workers Paid plan.", + "endpoint": null, + "hidden": false, + "active": true, + "priority": 174, + "default": false, + "aliases": [], + "release_date": "2026-04-24", + "last_updated": "2026-08-13", + "knowledge": null + }, { "id": "@cf/google/gemma-4-26b-a4b-it", "label": "Gemma 4 26B A4B IT", @@ -1455,7 +1768,7 @@ "cache_read": 0.16 }, "group": null, - "note": null, + "note": "Requires the Workers Paid plan.", "endpoint": null, "hidden": false, "active": true, @@ -1497,15 +1810,15 @@ "cache_read": 0.19 }, "group": null, - "note": null, + "note": "Requires the Workers Paid plan.", "endpoint": null, "hidden": false, "active": true, "priority": 145, "default": false, "aliases": [], - "release_date": null, - "last_updated": null, + "release_date": "2026-06-12", + "last_updated": "2026-06-12", "knowledge": null }, { @@ -1708,6 +2021,48 @@ "last_updated": "2025-04-30", "knowledge": null }, + { + "id": "@cf/qwen/qwen3.8-27b", + "label": "Qwen 3.8 27B", + "family": "qwen", + "context": 262144, + "output_limit": null, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": true, + "structured_output": false, + "temperature": true, + "open_weights": false, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 0.45, + "output": 3.2, + "cache_read": 0.05 + }, + "group": null, + "note": null, + "endpoint": null, + "hidden": false, + "active": true, + "priority": 152, + "default": false, + "aliases": [], + "release_date": "2026-08-14", + "last_updated": "2026-08-17", + "knowledge": null + }, { "id": "@cf/qwen/qwq-32b", "label": "Qwq 32B", @@ -1773,7 +2128,7 @@ ] }, "cost": { - "input": 0.0605, + "input": 0.06, "output": 0.4 }, "group": null, @@ -1787,6 +2142,89 @@ "release_date": "2026-01-19", "last_updated": "2026-01-19", "knowledge": "2025-04" + }, + { + "id": "@cf/zai-org/glm-5.3", + "label": "GLM 5.3", + "family": "glm", + "context": 1310720, + "output_limit": null, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": false, + "structured_output": false, + "temperature": true, + "open_weights": true, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 1.4, + "output": 4.4, + "cache_read": 0.26 + }, + "group": null, + "note": "Requires the Workers Paid plan.", + "endpoint": null, + "hidden": false, + "active": true, + "priority": 176, + "default": false, + "aliases": [], + "release_date": "2026-08-18", + "last_updated": "2026-08-28", + "knowledge": null + }, + { + "id": "@cf/zai-org/glm-5.3-flash", + "label": "GLM 5.3 Flash", + "family": "glm-flash", + "context": 1310720, + "output_limit": null, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": true, + "structured_output": false, + "temperature": true, + "open_weights": true, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 0.15, + "output": 0.5, + "cache_read": 0.03 + }, + "group": null, + "note": "Requires the Workers Paid plan.", + "endpoint": null, + "hidden": false, + "active": true, + "priority": 156, + "default": false, + "aliases": [], + "release_date": "2026-08-25", + "last_updated": "2026-08-26", + "knowledge": null } ] }, @@ -1801,10 +2239,10 @@ "supports_live": false, "models": [ { - "id": "gpt-5.4-mini", - "label": "GPT-5.4 mini", - "family": "gpt-mini", - "context": 400000, + "id": "gpt-5.5", + "label": "GPT-5.5", + "family": "gpt", + "context": 1050000, "output_limit": 128000, "reasoning": true, "supports_effort": true, @@ -1826,34 +2264,35 @@ "modalities": { "input": [ "text", - "image" + "image", + "pdf" ], "output": [ "text" ] }, "cost": { - "input": 0.75, - "output": 4.5, - "cache_read": 0.075 + "input": 5, + "output": 30, + "cache_read": 0.5 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 20, + "priority": 50, "default": false, "aliases": [], - "release_date": "2026-03-17", - "last_updated": "2026-03-17", - "knowledge": "2025-08-31" + "release_date": "2026-04-23", + "last_updated": "2026-06-22", + "knowledge": "2025-12-01" }, { - "id": "gpt-5.5", - "label": "GPT-5.5", + "id": "gpt-5.6-luna", + "label": "GPT-5.6 Luna", "family": "gpt", - "context": 400000, + "context": 1050000, "output_limit": 128000, "reasoning": true, "supports_effort": true, @@ -1863,7 +2302,9 @@ "low", "medium", "high", - "xhigh" + "xhigh", + "max", + "ultra" ], "default": "medium" }, @@ -1883,25 +2324,25 @@ ] }, "cost": { - "input": 5, - "output": 30, - "cache_read": 0.5 + "input": 0.2, + "output": 1.2, + "cache_read": 0.02 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 50, + "priority": 70, "default": false, "aliases": [], - "release_date": "2026-04-23", - "last_updated": "2026-06-22", - "knowledge": "2025-12-01" + "release_date": "2026-07-09", + "last_updated": "2026-07-09", + "knowledge": "2026-02-16" }, { - "id": "gpt-5.6-luna", - "label": "GPT-5.6 Luna", + "id": "gpt-5.6-sol", + "label": "GPT-5.6 Sol", "family": "gpt", "context": 1050000, "output_limit": 128000, @@ -1935,25 +2376,27 @@ ] }, "cost": { - "input": 0.2, - "output": 1.2, - "cache_read": 0.02 + "input": 4, + "output": 20, + "cache_read": 0.4 }, "group": null, - "note": null, + "note": "Promotional pricing, guaranteed through 2026-11-21 (was $5 / $30).", "endpoint": null, "hidden": false, "active": true, - "priority": 70, - "default": false, - "aliases": [], + "priority": 90, + "default": true, + "aliases": [ + "gpt-5.6" + ], "release_date": "2026-07-09", - "last_updated": "2026-07-09", + "last_updated": "2026-08-21", "knowledge": "2026-02-16" }, { - "id": "gpt-5.6-sol", - "label": "GPT-5.6 Sol", + "id": "gpt-5.6-terra", + "label": "GPT-5.6 Terra", "family": "gpt", "context": 1050000, "output_limit": 128000, @@ -1987,27 +2430,25 @@ ] }, "cost": { - "input": 5, - "output": 30, - "cache_read": 0.5 + "input": 2, + "output": 12, + "cache_read": 0.2 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 90, - "default": true, - "aliases": [ - "gpt-5.6" - ], + "priority": 80, + "default": false, + "aliases": [], "release_date": "2026-07-09", "last_updated": "2026-07-09", "knowledge": "2026-02-16" }, { - "id": "gpt-5.6-terra", - "label": "GPT-5.6 Terra", + "id": "gpt-6-astra", + "label": "GPT-6 Astra", "family": "gpt", "context": 1050000, "output_limit": 128000, @@ -2033,29 +2474,29 @@ "modalities": { "input": [ "text", - "image", - "pdf" + "image" ], "output": [ "text" ] }, "cost": { - "input": 2, - "output": 12, - "cache_read": 0.2 + "input": 10, + "output": 50, + "cache_read": 1, + "cache_write": 12.5 }, "group": null, - "note": null, + "note": "Most capable", "endpoint": null, "hidden": false, "active": true, - "priority": 80, + "priority": 85, "default": false, "aliases": [], - "release_date": "2026-07-09", - "last_updated": "2026-07-09", - "knowledge": "2026-02-16" + "release_date": "2026-09-03", + "last_updated": "2026-09-03", + "knowledge": "2026-04-30" } ] }, @@ -2072,45 +2513,55 @@ "supports_live": true, "models": [ { - "id": "deepseek-v4-flash", - "label": "DeepSeek V4 Flash", + "id": "deepseek-flash", + "label": "DeepSeek V4.1 Flash", "family": "deepseek-flash", "context": 1000000, "output_limit": 384000, "reasoning": true, "supports_effort": true, "effort": { - "kind": "none" + "kind": "levels", + "levels": [ + "low", + "high", + "max" + ], + "default": "high" }, "tool_call": true, - "attachment": false, + "attachment": true, "structured_output": true, "temperature": true, "open_weights": true, "modalities": { "input": [ - "text" + "text", + "image" ], "output": [ "text" ] }, "cost": { - "input": 0.14, - "output": 0.28, - "cache_read": 0.0028 + "input": 0.3, + "output": 1.2, + "cache_read": 0.006 }, "group": null, - "note": null, + "note": "Peak-hour pricing. Rates halve off-peak (outside 01:00-04:00 and 06:00-10:00 UTC, Mon-Fri).", "endpoint": null, "hidden": false, "active": true, - "priority": 10, - "default": false, - "aliases": [], - "release_date": "2026-04-24", - "last_updated": "2026-04-24", - "knowledge": "2025-05" + "priority": 30, + "default": true, + "aliases": [ + "deepseek-v4-flash", + "deepseek-v4-flash-vision-exp" + ], + "release_date": "2026-09-10", + "last_updated": "2026-09-10", + "knowledge": null }, { "id": "deepseek-v4-pro", @@ -2121,7 +2572,13 @@ "reasoning": true, "supports_effort": true, "effort": { - "kind": "none" + "kind": "levels", + "levels": [ + "low", + "high", + "max" + ], + "default": "high" }, "tool_call": true, "attachment": false, @@ -2137,20 +2594,20 @@ ] }, "cost": { - "input": 0.435, - "output": 0.87, - "cache_read": 0.003625 + "input": 1.32, + "output": 3.96, + "cache_read": 0.044 }, "group": null, - "note": null, + "note": "Peak-hour pricing. Rates halve off-peak (outside 01:00-04:00 and 06:00-10:00 UTC, Mon-Fri).", "endpoint": null, "hidden": false, "active": true, "priority": 20, - "default": true, + "default": false, "aliases": [], "release_date": "2026-04-24", - "last_updated": "2026-04-24", + "last_updated": "2026-08-13", "knowledge": "2025-05" } ] @@ -2563,7 +3020,7 @@ "aliases": [], "release_date": "2026-07-21", "last_updated": "2026-07-21", - "knowledge": null + "knowledge": "2026-03" }, { "id": "gemini-3.6-flash", @@ -2599,12 +3056,12 @@ ] }, "cost": { - "input": 1.5, - "output": 7.5, - "cache_read": 0.15 + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 }, "group": null, - "note": null, + "note": "Introductory pricing through 2026-12-31; $1.50 / $7.50 per MTok from 2027-01-01.", "endpoint": null, "hidden": false, "active": true, @@ -2614,6 +3071,108 @@ "release_date": "2026-07-21", "last_updated": "2026-07-21", "knowledge": "2026-03" + }, + { + "id": "gemini-3.7-flash", + "label": "Gemini 3.7 Flash", + "family": "gemini-flash", + "context": 1048576, + "output_limit": 65536, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "thinking_level", + "levels": [ + "low", + "medium", + "high" + ], + "default": "medium" + }, + "tool_call": true, + "attachment": true, + "structured_output": true, + "temperature": true, + "open_weights": false, + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 + }, + "group": null, + "note": "Introductory pricing through 2026-12-31; $1.50 / $7.50 per MTok from 2027-01-01.", + "endpoint": null, + "hidden": false, + "active": true, + "priority": 90, + "default": false, + "aliases": [], + "release_date": "2026-08-13", + "last_updated": "2026-08-13", + "knowledge": "2026-03" + }, + { + "id": "gemini-3.8-flash", + "label": "Gemini 3.8 Flash", + "family": "gemini-flash", + "context": 1048576, + "output_limit": 65536, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "thinking_level", + "levels": [ + "low", + "medium", + "high" + ], + "default": "medium" + }, + "tool_call": true, + "attachment": true, + "structured_output": true, + "temperature": true, + "open_weights": false, + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 + }, + "group": null, + "note": "Introductory pricing through 2026-12-31; $1.50 / $7.50 per MTok from 2027-01-01.", + "endpoint": null, + "hidden": false, + "active": true, + "priority": 100, + "default": false, + "aliases": [], + "release_date": "2026-09-02", + "last_updated": "2026-09-02", + "knowledge": "2026-03" } ] }, @@ -2672,9 +3231,9 @@ "knowledge": null }, { - "id": "claude-haiku-4.5", - "label": "Claude Haiku 4.5", - "family": "claude-haiku", + "id": "claude-fable-5", + "label": "Claude Fable 5", + "family": "claude-fable", "context": 200000, "output_limit": 64000, "reasoning": true, @@ -2692,7 +3251,7 @@ "tool_call": true, "attachment": true, "structured_output": true, - "temperature": true, + "temperature": false, "open_weights": false, "modalities": { "input": [ @@ -2705,29 +3264,29 @@ ] }, "cost": { - "input": 1, - "output": 5, - "cache_read": 0.1, - "cache_write": 1.25 + "input": 10, + "output": 50, + "cache_read": 1, + "cache_write": 12.5 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 20, + "priority": 227, "default": false, "aliases": [], - "release_date": "2025-10-15", - "last_updated": "2025-10-15", - "knowledge": "2025-02-28" + "release_date": "2026-06-09", + "last_updated": "2026-06-09", + "knowledge": "2026-01" }, { - "id": "claude-opus-4.5", - "label": "Claude Opus 4.5", - "family": "claude-opus", + "id": "claude-fable-5.1", + "label": "Claude Fable 5.1", + "family": "claude-fable", "context": 200000, - "output_limit": 32000, + "output_limit": 64000, "reasoning": true, "supports_effort": true, "effort": { @@ -2743,7 +3302,7 @@ "tool_call": true, "attachment": true, "structured_output": true, - "temperature": true, + "temperature": false, "open_weights": false, "modalities": { "input": [ @@ -2756,29 +3315,29 @@ ] }, "cost": { - "input": 5, - "output": 25, - "cache_read": 0.5, - "cache_write": 6.25 - }, - "group": null, + "input": 10, + "output": 50, + "cache_read": 0.25, + "cache_write": 12.5 + }, + "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 190, + "priority": 228, "default": false, "aliases": [], - "release_date": "2025-11-24", - "last_updated": "2025-11-24", - "knowledge": "2025-03-31" + "release_date": "2026-09-01", + "last_updated": "2026-09-01", + "knowledge": "2026-06" }, { - "id": "claude-opus-4.6", - "label": "Claude Opus 4.6", - "family": "claude-opus", + "id": "claude-haiku-4.5", + "label": "Claude Haiku 4.5", + "family": "claude-haiku", "context": 200000, - "output_limit": 32000, + "output_limit": 64000, "reasoning": true, "supports_effort": true, "effort": { @@ -2807,22 +3366,22 @@ ] }, "cost": { - "input": 5, - "output": 25, - "cache_read": 0.5, - "cache_write": 6.25 + "input": 1, + "output": 5, + "cache_read": 0.1, + "cache_write": 1.25 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 200, + "priority": 20, "default": false, "aliases": [], - "release_date": "2026-02-05", - "last_updated": "2026-03-13", - "knowledge": "2025-05-31" + "release_date": "2025-10-15", + "last_updated": "2025-10-15", + "knowledge": "2025-02-28" }, { "id": "claude-opus-4.7", @@ -2977,57 +3536,6 @@ "last_updated": "2026-07-24", "knowledge": "2026-05" }, - { - "id": "claude-sonnet-4.5", - "label": "Claude Sonnet 4.5", - "family": "claude-sonnet", - "context": 200000, - "output_limit": 32000, - "reasoning": true, - "supports_effort": true, - "effort": { - "kind": "levels", - "levels": [ - "low", - "medium", - "high", - "xhigh" - ], - "default": "medium" - }, - "tool_call": true, - "attachment": true, - "structured_output": true, - "temperature": true, - "open_weights": false, - "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text" - ] - }, - "cost": { - "input": 3, - "output": 15, - "cache_read": 0.3, - "cache_write": 3.75 - }, - "group": null, - "note": null, - "endpoint": null, - "hidden": false, - "active": true, - "priority": 170, - "default": false, - "aliases": [], - "release_date": "2025-09-29", - "last_updated": "2025-09-29", - "knowledge": "2025-07-31" - }, { "id": "claude-sonnet-4.6", "label": "Claude Sonnet 4.6", @@ -3113,10 +3621,10 @@ ] }, "cost": { - "input": 3, - "output": 15, - "cache_read": 0.3, - "cache_write": 3.75 + "input": 2, + "output": 10, + "cache_read": 0.2, + "cache_write": 2.5 }, "group": null, "note": null, @@ -3131,10 +3639,10 @@ "knowledge": "2026-01" }, { - "id": "gemini-2.5-pro", - "label": "Gemini 2.5 Pro", - "family": "gemini-pro", - "context": 128000, + "id": "gemini-3.5-flash", + "label": "Gemini 3.5 Flash", + "family": "gemini-flash", + "context": 200000, "output_limit": 64000, "reasoning": true, "supports_effort": true, @@ -3157,8 +3665,8 @@ "input": [ "text", "image", - "audio", "video", + "audio", "pdf" ], "output": [ @@ -3166,27 +3674,27 @@ ] }, "cost": { - "input": 1.25, - "output": 10, - "cache_read": 0.125 + "input": 1.5, + "output": 9, + "cache_read": 0.15 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 70, + "priority": 100, "default": false, "aliases": [], - "release_date": "2025-03-20", - "last_updated": "2025-06-05", + "release_date": "2026-05-19", + "last_updated": "2026-05-19", "knowledge": "2025-01" }, { - "id": "gemini-3-flash-preview", - "label": "Gemini 3 Flash Preview", + "id": "gemini-3.6-flash", + "label": "Gemini 3.6 Flash", "family": "gemini-flash", - "context": 128000, + "context": 200000, "output_limit": 64000, "reasoning": true, "supports_effort": true, @@ -3218,26 +3726,26 @@ ] }, "cost": { - "input": 0.5, - "output": 3, - "cache_read": 0.05 + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 80, + "priority": 105, "default": false, "aliases": [], - "release_date": "2025-12-17", - "last_updated": "2025-12-17", - "knowledge": "2025-01" + "release_date": "2026-07-21", + "last_updated": "2026-07-21", + "knowledge": "2026-03" }, { - "id": "gemini-3.1-pro-preview", - "label": "Gemini 3.1 Pro Preview", - "family": "gemini-pro", + "id": "gemini-3.8-flash", + "label": "Gemini 3.8 Flash", + "family": "gemini-flash", "context": 200000, "output_limit": 64000, "reasoning": true, @@ -3270,27 +3778,27 @@ ] }, "cost": { - "input": 2, - "output": 12, - "cache_read": 0.2 + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 90, + "priority": 108, "default": false, "aliases": [], - "release_date": "2026-02-19", - "last_updated": "2026-02-19", - "knowledge": "2025-01" + "release_date": "2026-09-02", + "last_updated": "2026-09-02", + "knowledge": "2026-03" }, { - "id": "gemini-3.5-flash", - "label": "Gemini 3.5 Flash", - "family": "gemini-flash", - "context": 200000, + "id": "gpt-5-mini", + "label": "GPT-5 Mini", + "family": "gpt-mini", + "context": 264000, "output_limit": 64000, "reasoning": true, "supports_effort": true, @@ -3307,43 +3815,40 @@ "tool_call": true, "attachment": true, "structured_output": true, - "temperature": true, + "temperature": false, "open_weights": false, "modalities": { "input": [ "text", - "image", - "video", - "audio", - "pdf" + "image" ], "output": [ "text" ] }, "cost": { - "input": 1.5, - "output": 9, - "cache_read": 0.15 + "input": 0.25, + "output": 2, + "cache_read": 0.025 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 100, + "priority": 30, "default": false, "aliases": [], - "release_date": "2026-05-19", - "last_updated": "2026-05-19", - "knowledge": "2025-01" + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "knowledge": "2024-05-30" }, { - "id": "gemini-3.6-flash", - "label": "Gemini 3.6 Flash", - "family": "gemini-flash", - "context": 200000, - "output_limit": 64000, + "id": "gpt-5.3-codex", + "label": "GPT-5.3 Codex", + "family": "gpt-codex", + "context": 400000, + "output_limit": 128000, "reasoning": true, "supports_effort": true, "effort": { @@ -3359,14 +3864,12 @@ "tool_call": true, "attachment": true, "structured_output": true, - "temperature": true, + "temperature": false, "open_weights": false, "modalities": { "input": [ "text", "image", - "video", - "audio", "pdf" ], "output": [ @@ -3374,29 +3877,29 @@ ] }, "cost": { - "input": 1.5, - "output": 7.5, - "cache_read": 0.15 + "input": 1.75, + "output": 14, + "cache_read": 0.175 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 105, + "priority": 130, "default": false, "aliases": [], - "release_date": "2026-07-21", - "last_updated": "2026-07-21", - "knowledge": "2026-03" + "release_date": "2026-02-05", + "last_updated": "2026-02-05", + "knowledge": "2025-08-31" }, { - "id": "gpt-4.1", - "label": "GPT-4.1", + "id": "gpt-5.4", + "label": "GPT-5.4", "family": "gpt", - "context": 128000, - "output_limit": 16384, - "reasoning": false, + "context": 400000, + "output_limit": 128000, + "reasoning": true, "supports_effort": true, "effort": { "kind": "levels", @@ -3411,7 +3914,7 @@ "tool_call": true, "attachment": true, "structured_output": true, - "temperature": true, + "temperature": false, "open_weights": false, "modalities": { "input": [ @@ -3424,28 +3927,28 @@ ] }, "cost": { - "input": 2, - "output": 8, - "cache_read": 0.5 + "input": 2.5, + "output": 15, + "cache_read": 0.25 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 60, + "priority": 140, "default": false, "aliases": [], - "release_date": "2025-04-14", - "last_updated": "2025-04-14", - "knowledge": "2024-04" + "release_date": "2026-03-05", + "last_updated": "2026-03-05", + "knowledge": "2025-08-31" }, { - "id": "gpt-5-mini", - "label": "GPT-5 Mini", + "id": "gpt-5.4-mini", + "label": "GPT-5.4 mini", "family": "gpt-mini", - "context": 264000, - "output_limit": 64000, + "context": 400000, + "output_limit": 128000, "reasoning": true, "supports_effort": true, "effort": { @@ -3473,25 +3976,25 @@ ] }, "cost": { - "input": 0.25, - "output": 2, - "cache_read": 0.025 + "input": 0.75, + "output": 4.5, + "cache_read": 0.075 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 30, + "priority": 50, "default": false, "aliases": [], - "release_date": "2025-08-07", - "last_updated": "2025-08-07", - "knowledge": "2024-05-30" + "release_date": "2026-03-17", + "last_updated": "2026-03-17", + "knowledge": "2025-08-31" }, { - "id": "gpt-5.2", - "label": "GPT-5.2", + "id": "gpt-5.5", + "label": "GPT-5.5", "family": "gpt", "context": 400000, "output_limit": 128000, @@ -3515,33 +4018,34 @@ "modalities": { "input": [ "text", - "image" + "image", + "pdf" ], "output": [ "text" ] }, "cost": { - "input": 1.75, - "output": 14, - "cache_read": 0.175 + "input": 5, + "output": 30, + "cache_read": 0.5 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 110, + "priority": 150, "default": false, "aliases": [], - "release_date": "2025-12-11", - "last_updated": "2025-12-11", - "knowledge": "2025-08-31" + "release_date": "2026-04-23", + "last_updated": "2026-04-23", + "knowledge": "2025-12-01" }, { - "id": "gpt-5.2-codex", - "label": "GPT-5.2 Codex", - "family": "gpt-codex", + "id": "gpt-5.6-luna", + "label": "GPT-5.6 Luna", + "family": "gpt", "context": 400000, "output_limit": 128000, "reasoning": true, @@ -3572,26 +4076,26 @@ ] }, "cost": { - "input": 1.75, - "output": 14, - "cache_read": 0.175 + "input": 0.2, + "output": 1.2, + "cache_read": 0.02 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 120, + "priority": 152, "default": false, "aliases": [], - "release_date": "2025-12-11", - "last_updated": "2025-12-11", - "knowledge": "2025-08-31" + "release_date": "2026-07-09", + "last_updated": "2026-07-09", + "knowledge": "2026-02-16" }, { - "id": "gpt-5.3-codex", - "label": "GPT-5.3 Codex", - "family": "gpt-codex", + "id": "gpt-5.6-sol", + "label": "GPT-5.6 Sol", + "family": "gpt", "context": 400000, "output_limit": 128000, "reasoning": true, @@ -3622,25 +4126,25 @@ ] }, "cost": { - "input": 1.75, - "output": 14, - "cache_read": 0.175 + "input": 4, + "output": 20, + "cache_read": 0.4 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 130, + "priority": 156, "default": false, "aliases": [], - "release_date": "2026-02-05", - "last_updated": "2026-02-05", - "knowledge": "2025-08-31" + "release_date": "2026-07-09", + "last_updated": "2026-07-09", + "knowledge": "2026-02-16" }, { - "id": "gpt-5.4", - "label": "GPT-5.4", + "id": "gpt-5.6-terra", + "label": "GPT-5.6 Terra", "family": "gpt", "context": 400000, "output_limit": 128000, @@ -3672,26 +4176,26 @@ ] }, "cost": { - "input": 2.5, - "output": 15, - "cache_read": 0.25 + "input": 2, + "output": 12, + "cache_read": 0.2 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 140, + "priority": 154, "default": false, "aliases": [], - "release_date": "2026-03-05", - "last_updated": "2026-03-05", - "knowledge": "2025-08-31" + "release_date": "2026-07-09", + "last_updated": "2026-07-09", + "knowledge": "2026-02-16" }, { - "id": "gpt-5.4-mini", - "label": "GPT-5.4 mini", - "family": "gpt-mini", + "id": "gpt-6-astra", + "label": "GPT-6 Astra", + "family": "gpt", "context": 400000, "output_limit": 128000, "reasoning": true, @@ -3721,28 +4225,29 @@ ] }, "cost": { - "input": 0.75, - "output": 4.5, - "cache_read": 0.075 + "input": 10, + "output": 50, + "cache_read": 1, + "cache_write": 12.5 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 50, + "priority": 158, "default": false, "aliases": [], - "release_date": "2026-03-17", - "last_updated": "2026-03-17", - "knowledge": "2025-08-31" + "release_date": "2026-09-03", + "last_updated": "2026-09-03", + "knowledge": "2026-04-30" }, { - "id": "gpt-5.4-nano", - "label": "GPT-5.4 nano", - "family": "gpt-nano", - "context": 400000, - "output_limit": 128000, + "id": "grok-4.6", + "label": "Grok 4.6", + "family": "grok", + "context": 500000, + "output_limit": null, "reasoning": true, "supports_effort": true, "effort": { @@ -3758,7 +4263,7 @@ "tool_call": true, "attachment": true, "structured_output": true, - "temperature": false, + "temperature": true, "open_weights": false, "modalities": { "input": [ @@ -3770,28 +4275,28 @@ ] }, "cost": { - "input": 0.2, - "output": 1.25, - "cache_read": 0.02 + "input": 2, + "output": 6, + "cache_read": 0.5 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 40, + "priority": 109, "default": false, "aliases": [], - "release_date": "2026-03-17", - "last_updated": "2026-03-17", - "knowledge": "2025-08-31" + "release_date": "2026-08-12", + "last_updated": "2026-08-12", + "knowledge": "2026-02-01" }, { - "id": "gpt-5.5", - "label": "GPT-5.5", - "family": "gpt", - "context": 400000, - "output_limit": 128000, + "id": "kimi-k3", + "label": "Kimi K3", + "family": "kimi-k3", + "context": 1048576, + "output_limit": null, "reasoning": true, "supports_effort": true, "effort": { @@ -3808,62 +4313,53 @@ "attachment": true, "structured_output": true, "temperature": false, - "open_weights": false, + "open_weights": true, "modalities": { "input": [ "text", "image", - "pdf" + "video" ], "output": [ "text" ] }, "cost": { - "input": 5, - "output": 30, - "cache_read": 0.5 + "input": 3, + "output": 15, + "cache_read": 0.3 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 150, + "priority": 65, "default": false, "aliases": [], - "release_date": "2026-04-23", - "last_updated": "2026-04-23", - "knowledge": "2025-12-01" + "release_date": "2026-07-16", + "last_updated": "2026-07-16", + "knowledge": null }, { - "id": "gpt-5.6-luna", - "label": "GPT-5.6 Luna", - "family": "gpt", - "context": 400000, - "output_limit": 128000, - "reasoning": true, - "supports_effort": true, + "id": "mai-code-1.1-flash", + "label": "MAI-Code-1.1-Flash", + "family": "mai-code", + "context": null, + "output_limit": null, + "reasoning": false, + "supports_effort": false, "effort": { - "kind": "levels", - "levels": [ - "low", - "medium", - "high", - "xhigh" - ], - "default": "medium" + "kind": "none" }, "tool_call": true, - "attachment": true, - "structured_output": true, - "temperature": false, + "attachment": false, + "structured_output": false, + "temperature": true, "open_weights": false, "modalities": { "input": [ - "text", - "image", - "pdf" + "text" ], "output": [ "text" @@ -3875,165 +4371,16 @@ "cache_read": 0.02 }, "group": null, - "note": null, - "endpoint": null, - "hidden": false, - "active": true, - "priority": 152, - "default": false, - "aliases": [], - "release_date": "2026-07-09", - "last_updated": "2026-07-09", - "knowledge": "2026-02-16" - }, - { - "id": "gpt-5.6-sol", - "label": "GPT-5.6 Sol", - "family": "gpt", - "context": 400000, - "output_limit": 128000, - "reasoning": true, - "supports_effort": true, - "effort": { - "kind": "levels", - "levels": [ - "low", - "medium", - "high", - "xhigh" - ], - "default": "medium" - }, - "tool_call": true, - "attachment": true, - "structured_output": true, - "temperature": false, - "open_weights": false, - "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text" - ] - }, - "cost": { - "input": 5, - "output": 30, - "cache_read": 0.5 - }, - "group": null, - "note": null, - "endpoint": null, - "hidden": false, - "active": true, - "priority": 156, - "default": false, - "aliases": [], - "release_date": "2026-07-09", - "last_updated": "2026-07-09", - "knowledge": "2026-02-16" - }, - { - "id": "gpt-5.6-terra", - "label": "GPT-5.6 Terra", - "family": "gpt", - "context": 400000, - "output_limit": 128000, - "reasoning": true, - "supports_effort": true, - "effort": { - "kind": "levels", - "levels": [ - "low", - "medium", - "high", - "xhigh" - ], - "default": "medium" - }, - "tool_call": true, - "attachment": true, - "structured_output": true, - "temperature": false, - "open_weights": false, - "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text" - ] - }, - "cost": { - "input": 2, - "output": 12, - "cache_read": 0.2 - }, - "group": null, - "note": null, - "endpoint": null, - "hidden": false, - "active": true, - "priority": 154, - "default": false, - "aliases": [], - "release_date": "2026-07-09", - "last_updated": "2026-07-09", - "knowledge": "2026-02-16" - }, - { - "id": "raptor-mini", - "label": "Raptor mini", - "family": "gpt-mini", - "context": 264000, - "output_limit": 128000, - "reasoning": true, - "supports_effort": true, - "effort": { - "kind": "levels", - "levels": [ - "low", - "medium", - "high", - "xhigh" - ], - "default": "medium" - }, - "tool_call": true, - "attachment": true, - "structured_output": true, - "temperature": false, - "open_weights": false, - "modalities": { - "input": [ - "text", - "image" - ], - "output": [ - "text" - ] - }, - "cost": { - "input": 0.25, - "output": 2, - "cache_read": 0.025 - }, - "group": null, - "note": null, + "note": "Code", "endpoint": null, "hidden": false, "active": true, - "priority": 10, + "priority": 12, "default": false, "aliases": [], - "release_date": "2025-08-07", - "last_updated": "2026-06-22", - "knowledge": "2024-05-30" + "release_date": "2026-08-11", + "last_updated": "2026-08-11", + "knowledge": null } ] }, @@ -4053,7 +4400,7 @@ "id": "grok-4.20-0309-non-reasoning", "label": "Grok 4.20 (Non-Reasoning)", "family": "grok", - "context": 2000000, + "context": 1000000, "output_limit": 30000, "reasoning": false, "supports_effort": false, @@ -4068,8 +4415,7 @@ "modalities": { "input": [ "text", - "image", - "pdf" + "image" ], "output": [ "text" @@ -4096,7 +4442,7 @@ "id": "grok-4.20-0309-reasoning", "label": "Grok 4.20 (Reasoning)", "family": "grok", - "context": 2000000, + "context": 1000000, "output_limit": 30000, "reasoning": true, "supports_effort": true, @@ -4111,8 +4457,7 @@ "modalities": { "input": [ "text", - "image", - "pdf" + "image" ], "output": [ "text" @@ -4149,7 +4494,8 @@ "none", "low", "medium", - "high" + "high", + "xhigh" ], "default": "low" }, @@ -4161,8 +4507,7 @@ "modalities": { "input": [ "text", - "image", - "pdf" + "image" ], "output": [ "text" @@ -4180,7 +4525,9 @@ "active": true, "priority": 30, "default": true, - "aliases": [], + "aliases": [ + "grok-4.3-latest" + ], "release_date": "2026-04-17", "last_updated": "2026-04-17", "knowledge": null @@ -4196,12 +4543,12 @@ "effort": { "kind": "levels", "levels": [ - "none", "low", "medium", - "high" + "high", + "xhigh" ], - "default": "low" + "default": "high" }, "tool_call": true, "attachment": true, @@ -4229,9 +4576,106 @@ "active": true, "priority": 40, "default": false, + "aliases": [ + "grok-4.5-latest" + ], + "release_date": "2026-07-08", + "last_updated": "2026-07-08", + "knowledge": null + }, + { + "id": "grok-4.6", + "label": "Grok 4.6", + "family": "grok", + "context": 500000, + "output_limit": null, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "levels", + "levels": [ + "low", + "medium", + "high", + "xhigh" + ], + "default": "high" + }, + "tool_call": true, + "attachment": true, + "structured_output": true, + "temperature": true, + "open_weights": false, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 2, + "output": 6, + "cache_read": 0.5 + }, + "group": null, + "note": "Input/output pricing doubles for prompts at or above 200k tokens.", + "endpoint": null, + "hidden": false, + "active": true, + "priority": 50, + "default": false, "aliases": [], - "release_date": "2026-07-09", - "last_updated": "2026-07-09", + "release_date": "2026-08-12", + "last_updated": "2026-08-12", + "knowledge": "2026-02-01" + }, + { + "id": "grok-build-0.1", + "label": "Grok Build 0.1", + "family": "grok-build", + "context": 256000, + "output_limit": null, + "reasoning": true, + "supports_effort": false, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": true, + "structured_output": true, + "temperature": true, + "open_weights": false, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 1, + "output": 2, + "cache_read": 0.2 + }, + "group": null, + "note": "Code", + "endpoint": null, + "hidden": false, + "active": true, + "priority": 35, + "default": false, + "aliases": [ + "grok-code-fast-1", + "grok-code-fast", + "grok-code-fast-1-0825" + ], + "release_date": "2026-05-19", + "last_updated": "2026-05-19", "knowledge": null } ] @@ -4249,9 +4693,9 @@ "supports_live": true, "models": [ { - "id": "kimi-k2.5", - "label": "Kimi K2.5", - "family": "kimi-k2.5", + "id": "kimi-k2.6", + "label": "Kimi K2.6", + "family": "kimi-k2.6", "context": 262144, "output_limit": 262144, "reasoning": true, @@ -4260,7 +4704,7 @@ "kind": "none" }, "tool_call": true, - "attachment": false, + "attachment": true, "structured_output": true, "temperature": false, "open_weights": true, @@ -4275,28 +4719,28 @@ ] }, "cost": { - "input": 0.6, - "output": 3, - "cache_read": 0.1 + "input": 0.95, + "output": 4, + "cache_read": 0.16 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 10, - "default": false, + "priority": 20, + "default": true, "aliases": [], - "release_date": null, - "last_updated": null, + "release_date": "2026-04-21", + "last_updated": "2026-04-21", "knowledge": "2025-01" }, { - "id": "kimi-k2.6", - "label": "Kimi K2.6", - "family": "kimi-k2.6", + "id": "kimi-k2.7-code", + "label": "Kimi K2.7 Code", + "family": "kimi-k2.7", "context": 262144, - "output_limit": 262144, + "output_limit": null, "reasoning": true, "supports_effort": true, "effort": { @@ -4305,7 +4749,7 @@ "tool_call": true, "attachment": true, "structured_output": true, - "temperature": true, + "temperature": false, "open_weights": true, "modalities": { "input": [ @@ -4320,23 +4764,23 @@ "cost": { "input": 0.95, "output": 4, - "cache_read": 0.16 + "cache_read": 0.19 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 20, - "default": true, + "priority": 25, + "default": false, "aliases": [], - "release_date": "2026-04-21", - "last_updated": "2026-04-21", - "knowledge": "2025-01" + "release_date": "2026-06-12", + "last_updated": "2026-06-12", + "knowledge": null }, { - "id": "kimi-k2.7-code", - "label": "Kimi K2.7 Code", + "id": "kimi-k2.7-code-highspeed", + "label": "Kimi K2.7 Code HighSpeed", "family": "kimi-k2.7", "context": 262144, "output_limit": null, @@ -4348,7 +4792,7 @@ "tool_call": true, "attachment": true, "structured_output": true, - "temperature": true, + "temperature": false, "open_weights": true, "modalities": { "input": [ @@ -4361,20 +4805,18 @@ ] }, "cost": { - "input": 0.95, - "output": 4, - "cache_read": 0.19 + "input": 1.9, + "output": 8, + "cache_read": 0.38 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 25, + "priority": 22, "default": false, - "aliases": [ - "kimi-k2.7-code-highspeed" - ], + "aliases": [], "release_date": null, "last_updated": null, "knowledge": null @@ -4384,7 +4826,7 @@ "label": "Kimi K3", "family": "kimi-k3", "context": 1048576, - "output_limit": null, + "output_limit": 1048576, "reasoning": true, "supports_effort": true, "effort": { @@ -4399,7 +4841,7 @@ "tool_call": true, "attachment": true, "structured_output": true, - "temperature": true, + "temperature": false, "open_weights": true, "modalities": { "input": [ @@ -4440,49 +4882,6 @@ "models_endpoint": null, "supports_live": false, "models": [ - { - "id": "kimi-k2.5", - "label": "Kimi K2.5", - "family": "kimi-k2.5", - "context": 262144, - "output_limit": 262144, - "reasoning": true, - "supports_effort": true, - "effort": { - "kind": "none" - }, - "tool_call": true, - "attachment": false, - "structured_output": true, - "temperature": false, - "open_weights": true, - "modalities": { - "input": [ - "text", - "image", - "video" - ], - "output": [ - "text" - ] - }, - "cost": { - "input": 0.6, - "output": 3, - "cache_read": 0.1 - }, - "group": null, - "note": null, - "endpoint": null, - "hidden": false, - "active": true, - "priority": 10, - "default": false, - "aliases": [], - "release_date": null, - "last_updated": null, - "knowledge": "2025-01" - }, { "id": "kimi-k2.6", "label": "Kimi K2.6", @@ -4497,7 +4896,7 @@ "tool_call": true, "attachment": true, "structured_output": true, - "temperature": true, + "temperature": false, "open_weights": true, "modalities": { "input": [ @@ -4540,7 +4939,7 @@ "tool_call": true, "attachment": true, "structured_output": true, - "temperature": true, + "temperature": false, "open_weights": true, "modalities": { "input": [ @@ -4564,11 +4963,9 @@ "active": true, "priority": 25, "default": false, - "aliases": [ - "kimi-k2.7-code-highspeed" - ], - "release_date": null, - "last_updated": null, + "aliases": [], + "release_date": "2026-06-12", + "last_updated": "2026-06-12", "knowledge": null }, { @@ -4576,7 +4973,7 @@ "label": "Kimi K3", "family": "kimi-k3", "context": 1048576, - "output_limit": null, + "output_limit": 1048576, "reasoning": true, "supports_effort": true, "effort": { @@ -4591,7 +4988,7 @@ "tool_call": true, "attachment": true, "structured_output": true, - "temperature": true, + "temperature": false, "open_weights": true, "modalities": { "input": [ @@ -4638,7 +5035,7 @@ "id": "codestral", "label": "Codestral", "family": "codestral", - "context": 256000, + "context": 131072, "output_limit": 4096, "reasoning": false, "supports_effort": false, @@ -4649,7 +5046,7 @@ "attachment": false, "structured_output": true, "temperature": true, - "open_weights": true, + "open_weights": false, "modalities": { "input": [ "text" @@ -4660,7 +5057,8 @@ }, "cost": { "input": 0.3, - "output": 0.9 + "output": 0.9, + "cache_read": 0.03 }, "group": null, "note": "Code", @@ -4670,15 +5068,16 @@ "priority": 10, "default": false, "aliases": [ - "codestral-latest" + "codestral-latest", + "codestral-2508" ], - "release_date": "2024-05-29", - "last_updated": "2025-01-04", - "knowledge": "2024-10" + "release_date": "2025-07-30", + "last_updated": "2025-07-30", + "knowledge": null }, { "id": "mistral-large", - "label": "Mistral Large", + "label": "Mistral Large 3", "family": "mistral-large", "context": 262144, "output_limit": 262144, @@ -4703,7 +5102,8 @@ }, "cost": { "input": 0.5, - "output": 1.5 + "output": 1.5, + "cache_read": 0.05 }, "group": null, "note": null, @@ -4714,11 +5114,11 @@ "default": true, "aliases": [ "mistral-large-latest", - "mistral-large-2411" + "mistral-large-2512" ], - "release_date": "2024-11-01", + "release_date": "2025-12-02", "last_updated": "2025-12-02", - "knowledge": "2024-11" + "knowledge": null }, { "id": "mistral-medium", @@ -4729,7 +5129,16 @@ "reasoning": true, "supports_effort": true, "effort": { - "kind": "none" + "kind": "levels", + "levels": [ + "none", + "minimal", + "low", + "medium", + "high", + "xhigh" + ], + "default": "high" }, "tool_call": true, "attachment": true, @@ -4747,7 +5156,8 @@ }, "cost": { "input": 1.5, - "output": 7.5 + "output": 7.5, + "cache_read": 0.15 }, "group": null, "note": null, @@ -4758,7 +5168,8 @@ "default": false, "aliases": [ "mistral-medium-latest", - "mistral-medium-3-5-26-04" + "mistral-medium-3-5", + "mistral-medium-3" ], "release_date": "2026-04-28", "last_updated": "2026-04-28", @@ -4773,16 +5184,26 @@ "reasoning": true, "supports_effort": true, "effort": { - "kind": "none" + "kind": "levels", + "levels": [ + "none", + "minimal", + "low", + "medium", + "high", + "xhigh" + ], + "default": "high" }, "tool_call": true, - "attachment": false, + "attachment": true, "structured_output": true, "temperature": true, "open_weights": true, "modalities": { "input": [ - "text" + "text", + "image" ], "output": [ "text" @@ -4790,7 +5211,8 @@ }, "cost": { "input": 0.15, - "output": 0.6 + "output": 0.6, + "cache_read": 0.015 }, "group": null, "note": null, @@ -4806,29 +5228,15 @@ "release_date": "2026-03-16", "last_updated": "2026-03-16", "knowledge": null - } - ] - }, - "nvidia-nim": { - "id": "nvidia-nim", - "name": "NVIDIA NIM", - "kind": "api", - "doc": "https://build.nvidia.com/models", - "env": [ - "NVIDIA_API_KEY" - ], - "api": "https://integrate.api.nvidia.com/v1", - "models_endpoint": "/models", - "supports_live": true, - "models": [ + }, { - "id": "deepseek-ai/deepseek-v4-flash", - "label": "DeepSeek V4 Flash", - "family": "deepseek-flash", + "id": "zai-glm-5-3", + "label": "GLM 5.3", + "family": "glm", "context": 1048576, - "output_limit": 393216, + "output_limit": 131072, "reasoning": true, - "supports_effort": true, + "supports_effort": false, "effort": { "kind": "none" }, @@ -4846,30 +5254,47 @@ ] }, "cost": { - "input": 0.14, - "output": 0.28, - "cache_read": 0.0028 + "input": 1.4, + "output": 4.4, + "cache_read": 0.14 }, "group": null, - "note": null, + "note": "Code", "endpoint": null, "hidden": false, "active": true, - "priority": 60, + "priority": 25, "default": false, - "aliases": [], - "release_date": "2026-04-24", - "last_updated": "2026-04-24", - "knowledge": "2025-05" - }, + "aliases": [ + "zai-glm-5", + "zai-glm-latest" + ], + "release_date": "2026-09-15", + "last_updated": "2026-09-15", + "knowledge": null + } + ] + }, + "nvidia-nim": { + "id": "nvidia-nim", + "name": "NVIDIA NIM", + "kind": "api", + "doc": "https://build.nvidia.com/models", + "env": [ + "NVIDIA_API_KEY" + ], + "api": "https://integrate.api.nvidia.com/v1", + "models_endpoint": "/models", + "supports_live": true, + "models": [ { - "id": "deepseek-ai/deepseek-v4-pro", - "label": "DeepSeek V4 Pro", - "family": "deepseek-thinking", - "context": 1048576, - "output_limit": 393216, - "reasoning": true, - "supports_effort": true, + "id": "mistralai/mistral-nemotron", + "label": "mistral-nemotron", + "family": null, + "context": 128000, + "output_limit": 8192, + "reasoning": false, + "supports_effort": false, "effort": { "kind": "none" }, @@ -4887,30 +5312,29 @@ ] }, "cost": { - "input": 0.435, - "output": 0.87, - "cache_read": 0.003625 + "input": 0, + "output": 0 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 70, + "priority": 10, "default": false, "aliases": [], - "release_date": "2026-04-24", - "last_updated": "2026-04-24", - "knowledge": "2025-05" + "release_date": "2025-06-11", + "last_updated": "2025-06-12", + "knowledge": null }, { - "id": "meta/llama-4-maverick-17b-128e-instruct", - "label": "Llama 4 Maverick 17b 128e Instruct", - "family": null, - "context": 128000, - "output_limit": 4096, - "reasoning": false, - "supports_effort": false, + "id": "moonshotai/kimi-k2.6", + "label": "Kimi K2.6", + "family": "kimi-k2.6", + "context": 262144, + "output_limit": 262144, + "reasoning": true, + "supports_effort": true, "effort": { "kind": "none" }, @@ -4922,7 +5346,8 @@ "modalities": { "input": [ "text", - "image" + "image", + "video" ], "output": [ "text" @@ -4937,32 +5362,39 @@ "endpoint": null, "hidden": false, "active": true, - "priority": 40, + "priority": 50, "default": false, "aliases": [], - "release_date": "2025-04-01", - "last_updated": "2025-04-01", - "knowledge": "2024-02" + "release_date": "2026-04-21", + "last_updated": "2026-04-21", + "knowledge": "2025-01" }, { - "id": "minimaxai/minimax-m2.7", - "label": "MiniMax-M2.7", - "family": "minimax", - "context": 204800, - "output_limit": 131072, + "id": "moonshotai/kimi-k3", + "label": "Kimi K3", + "family": "kimi-k3", + "context": 1048576, + "output_limit": 65536, "reasoning": true, "supports_effort": true, "effort": { - "kind": "none" + "kind": "levels", + "levels": [ + "low", + "high", + "max" + ], + "default": "high" }, "tool_call": true, - "attachment": false, + "attachment": true, "structured_output": true, "temperature": true, "open_weights": true, "modalities": { "input": [ - "text" + "text", + "image" ], "output": [ "text" @@ -4977,21 +5409,21 @@ "endpoint": null, "hidden": false, "active": true, - "priority": 80, + "priority": 98, "default": false, "aliases": [], - "release_date": "2026-03-18", - "last_updated": "2026-04-11", - "knowledge": null - }, - { - "id": "mistralai/mistral-nemotron", - "label": "mistral-nemotron", - "family": null, - "context": 128000, - "output_limit": 8192, - "reasoning": false, - "supports_effort": false, + "release_date": "2026-07-16", + "last_updated": "2026-07-16", + "knowledge": null + }, + { + "id": "nvidia/nemotron-3-super-120b-a12b", + "label": "Nemotron 3 Super", + "family": "nemotron", + "context": 1048576, + "output_limit": 262144, + "reasoning": true, + "supports_effort": true, "effort": { "kind": "none" }, @@ -5009,42 +5441,40 @@ ] }, "cost": { - "input": 0, - "output": 0 + "input": 0.2, + "output": 0.8 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 10, - "default": false, + "priority": 100, + "default": true, "aliases": [], - "release_date": "2025-06-11", - "last_updated": "2025-06-12", - "knowledge": null + "release_date": "2026-03-11", + "last_updated": "2026-03-11", + "knowledge": "2024-04" }, { - "id": "moonshotai/kimi-k2.6", - "label": "Kimi K2.6", - "family": "kimi-k2.6", - "context": 262144, - "output_limit": 262144, + "id": "nvidia/nemotron-3-ultra-550b-a55b", + "label": "Nemotron 3 Ultra", + "family": "nemotron", + "context": 1048576, + "output_limit": null, "reasoning": true, "supports_effort": true, "effort": { "kind": "none" }, "tool_call": true, - "attachment": true, + "attachment": false, "structured_output": true, "temperature": true, "open_weights": true, "modalities": { "input": [ - "text", - "image", - "video" + "text" ], "output": [ "text" @@ -5059,19 +5489,19 @@ "endpoint": null, "hidden": false, "active": true, - "priority": 50, + "priority": 94, "default": false, "aliases": [], - "release_date": "2026-04-21", - "last_updated": "2026-04-21", - "knowledge": "2025-01" + "release_date": "2026-06-04", + "last_updated": "2026-06-04", + "knowledge": null }, { - "id": "nvidia/nemotron-3-super-120b-a12b", - "label": "Nemotron 3 Super", + "id": "nvidia/nemotron-3.5-lightning-30b-a3b", + "label": "Nemotron 3.5 Lightning", "family": "nemotron", - "context": 262144, - "output_limit": 262144, + "context": 1048576, + "output_limit": null, "reasoning": true, "supports_effort": true, "effort": { @@ -5091,37 +5521,37 @@ ] }, "cost": { - "input": 0.2, - "output": 0.8 + "input": 0, + "output": 0 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 100, - "default": true, + "priority": 86, + "default": false, "aliases": [], - "release_date": "2026-03-11", - "last_updated": "2026-03-11", - "knowledge": "2024-04" + "release_date": "2026-08-11", + "last_updated": "2026-08-11", + "knowledge": null }, { - "id": "openai/gpt-oss-120b", - "label": "GPT-OSS-120B", + "id": "openai/gpt-oss-20b", + "label": "GPT OSS 20B", "family": "gpt-oss", - "context": 128000, - "output_limit": 8192, + "context": 131072, + "output_limit": 32768, "reasoning": true, - "supports_effort": true, + "supports_effort": false, "effort": { "kind": "none" }, - "tool_call": false, - "attachment": true, - "structured_output": false, + "tool_call": true, + "attachment": false, + "structured_output": true, "temperature": true, - "open_weights": false, + "open_weights": true, "modalities": { "input": [ "text" @@ -5139,21 +5569,21 @@ "endpoint": null, "hidden": false, "active": true, - "priority": 30, + "priority": 20, "default": false, "aliases": [], - "release_date": "2025-08-04", - "last_updated": "2025-08-14", - "knowledge": "2025-08" + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "knowledge": null }, { - "id": "openai/gpt-oss-20b", - "label": "GPT OSS 20B", - "family": "gpt-oss", - "context": 131072, - "output_limit": 32768, + "id": "z-ai/glm-5.3", + "label": "GLM 5.3", + "family": "glm", + "context": 1048576, + "output_limit": null, "reasoning": true, - "supports_effort": false, + "supports_effort": true, "effort": { "kind": "none" }, @@ -5179,32 +5609,33 @@ "endpoint": null, "hidden": false, "active": true, - "priority": 20, + "priority": 96, "default": false, "aliases": [], - "release_date": "2025-08-05", - "last_updated": "2025-08-05", + "release_date": "2026-08-18", + "last_updated": "2026-08-18", "knowledge": null }, { - "id": "z-ai/glm-5.1", - "label": "GLM-5.1", - "family": "glm", - "context": 131072, - "output_limit": 131072, + "id": "z-ai/glm-5.3-flash", + "label": "GLM 5.3 Flash", + "family": "glm-flash", + "context": 1048576, + "output_limit": null, "reasoning": true, "supports_effort": true, "effort": { "kind": "none" }, "tool_call": true, - "attachment": false, + "attachment": true, "structured_output": true, "temperature": true, "open_weights": true, "modalities": { "input": [ - "text" + "text", + "image" ], "output": [ "text" @@ -5219,11 +5650,11 @@ "endpoint": null, "hidden": false, "active": true, - "priority": 90, + "priority": 88, "default": false, "aliases": [], - "release_date": "2026-03-27", - "last_updated": "2026-03-27", + "release_date": "2026-08-25", + "last_updated": "2026-08-25", "knowledge": null } ] @@ -5392,10 +5823,11 @@ "effort": { "kind": "levels", "levels": [ - "minimal", + "none", "low", "medium", - "high" + "high", + "xhigh" ], "default": "medium" }, @@ -5442,10 +5874,11 @@ "effort": { "kind": "levels", "levels": [ - "minimal", + "none", "low", "medium", - "high" + "high", + "xhigh" ], "default": "medium" }, @@ -5491,10 +5924,11 @@ "effort": { "kind": "levels", "levels": [ - "minimal", + "none", "low", "medium", - "high" + "high", + "xhigh" ], "default": "medium" }, @@ -5540,10 +5974,11 @@ "effort": { "kind": "levels", "levels": [ - "minimal", + "none", "low", "medium", - "high" + "high", + "xhigh" ], "default": "medium" }, @@ -5667,12 +6102,12 @@ ] }, "cost": { - "input": 5, - "output": 30, - "cache_read": 0.5 + "input": 4, + "output": 20, + "cache_read": 0.4 }, "group": null, - "note": null, + "note": "Promotional pricing, guaranteed through 2026-11-21 (was $5 / $30).", "endpoint": null, "hidden": false, "active": true, @@ -5682,7 +6117,7 @@ "gpt-5.6" ], "release_date": "2026-07-09", - "last_updated": "2026-07-09", + "last_updated": "2026-08-21", "knowledge": "2026-02-16" }, { @@ -5751,6 +6186,50 @@ "models_endpoint": "/models", "supports_live": true, "models": [ + { + "id": "anthropic/claude-fable-5.1", + "label": "Claude Fable 5.1", + "family": "claude-fable", + "context": 1000000, + "output_limit": 128000, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": true, + "structured_output": true, + "temperature": false, + "open_weights": false, + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 10, + "output": 50, + "cache_read": 0.25, + "cache_write": 12.5 + }, + "group": "via OpenRouter", + "note": null, + "endpoint": null, + "hidden": false, + "active": true, + "priority": 108, + "default": false, + "aliases": [], + "release_date": "2026-09-01", + "last_updated": "2026-09-01", + "knowledge": "2026-06" + }, { "id": "anthropic/claude-opus-4.8", "label": "Claude Opus 4.8", @@ -5910,10 +6389,10 @@ ] }, "cost": { - "input": 3, - "output": 15, - "cache_read": 0.3, - "cache_write": 3.75 + "input": 2, + "output": 10, + "cache_read": 0.2, + "cache_write": 2.5 }, "group": "via OpenRouter", "note": null, @@ -5952,9 +6431,9 @@ ] }, "cost": { - "input": 0.435, - "output": 0.87, - "cache_read": 0.003625 + "input": 0.9553, + "output": 1.9105, + "cache_read": 0.0796 }, "group": "via OpenRouter", "note": null, @@ -5968,6 +6447,48 @@ "last_updated": "2026-04-24", "knowledge": "2025-05" }, + { + "id": "deepseek/deepseek-v4.1-flash", + "label": "DeepSeek V4.1 Flash", + "family": "deepseek-flash", + "context": 1048576, + "output_limit": 384000, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": true, + "structured_output": true, + "temperature": true, + "open_weights": true, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 0.15, + "output": 0.6, + "cache_read": 0.003 + }, + "group": "via OpenRouter", + "note": null, + "endpoint": null, + "hidden": false, + "active": true, + "priority": 35, + "default": false, + "aliases": [], + "release_date": "2026-09-10", + "last_updated": "2026-09-10", + "knowledge": null + }, { "id": "google/gemini-3.1-pro-preview", "label": "Gemini 3.1 Pro Preview", @@ -6089,20 +6610,65 @@ ] }, "cost": { - "input": 1.5, - "output": 7.5, - "cache_read": 0.15 + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 + }, + "group": "via OpenRouter", + "note": null, + "endpoint": null, + "hidden": false, + "active": true, + "priority": 55, + "default": false, + "aliases": [], + "release_date": "2026-07-21", + "last_updated": "2026-07-21", + "knowledge": "2026-03" + }, + { + "id": "google/gemini-3.8-flash", + "label": "Gemini 3.8 Flash", + "family": "gemini-flash", + "context": 1048576, + "output_limit": 65536, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": true, + "structured_output": true, + "temperature": true, + "open_weights": false, + "modalities": { + "input": [ + "text", + "image", + "video", + "pdf", + "audio" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 }, "group": "via OpenRouter", "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 55, + "priority": 58, "default": false, "aliases": [], - "release_date": "2026-07-21", - "last_updated": "2026-07-21", + "release_date": "2026-09-02", + "last_updated": "2026-09-02", "knowledge": "2026-03" }, { @@ -6131,9 +6697,9 @@ ] }, "cost": { - "input": 0.684, - "output": 3.42, - "cache_read": 0.144 + "input": 0.95, + "output": 4, + "cache_read": 0.16 }, "group": "via OpenRouter", "note": null, @@ -6174,9 +6740,9 @@ ] }, "cost": { - "input": 3, - "output": 15, - "cache_read": 0.3 + "input": 1.7, + "output": 8.5, + "cache_read": 0.17 }, "group": "via OpenRouter", "note": null, @@ -6303,9 +6869,9 @@ ] }, "cost": { - "input": 5, - "output": 30, - "cache_read": 0.5 + "input": 2, + "output": 10, + "cache_read": 0.2 }, "group": "via OpenRouter", "note": null, @@ -6319,6 +6885,50 @@ "last_updated": "2026-07-09", "knowledge": "2026-02-16" }, + { + "id": "openai/gpt-6-astra", + "label": "GPT-6 Astra", + "family": "gpt", + "context": 1050000, + "output_limit": 128000, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": true, + "structured_output": true, + "temperature": false, + "open_weights": false, + "modalities": { + "input": [ + "pdf", + "image", + "text" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 10, + "output": 50, + "cache_read": 1, + "cache_write": 12.5 + }, + "group": "via OpenRouter", + "note": null, + "endpoint": null, + "hidden": false, + "active": true, + "priority": 88, + "default": false, + "aliases": [], + "release_date": "2026-09-03", + "last_updated": "2026-09-03", + "knowledge": "2026-04-30" + }, { "id": "x-ai/grok-4.3", "label": "Grok 4.3", @@ -6403,6 +7013,49 @@ "last_updated": "2026-07-09", "knowledge": null }, + { + "id": "x-ai/grok-4.6", + "label": "Grok 4.6", + "family": "grok", + "context": 500000, + "output_limit": 450000, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": true, + "structured_output": true, + "temperature": true, + "open_weights": false, + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 2, + "output": 6, + "cache_read": 0.5 + }, + "group": "via OpenRouter", + "note": null, + "endpoint": null, + "hidden": false, + "active": true, + "priority": 48, + "default": false, + "aliases": [], + "release_date": "2026-08-12", + "last_updated": "2026-08-12", + "knowledge": "2026-02-01" + }, { "id": "z-ai/glm-4.7", "label": "GLM-4.7", @@ -6443,6 +7096,47 @@ "release_date": "2025-12-22", "last_updated": "2025-12-22", "knowledge": "2025-04" + }, + { + "id": "z-ai/glm-5.3", + "label": "GLM 5.3", + "family": "glm", + "context": 1310720, + "output_limit": 131072, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": false, + "structured_output": true, + "temperature": true, + "open_weights": true, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 0.91, + "output": 2.86, + "cache_read": 0.169 + }, + "group": "via OpenRouter", + "note": null, + "endpoint": null, + "hidden": false, + "active": true, + "priority": 15, + "default": false, + "aliases": [], + "release_date": "2026-08-18", + "last_updated": "2026-08-18", + "knowledge": null } ] }, @@ -6458,6 +7152,49 @@ "models_endpoint": null, "supports_live": false, "models": [ + { + "id": "anthropic/claude-fable-5", + "label": "Claude Fable 5", + "family": "claude-fable", + "context": 1000000, + "output_limit": 128000, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": true, + "structured_output": true, + "temperature": false, + "open_weights": false, + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 10, + "output": 50, + "cache_read": 1 + }, + "group": "Agent API", + "note": null, + "endpoint": "/v1/agent", + "hidden": false, + "active": true, + "priority": 186, + "default": false, + "aliases": [], + "release_date": "2026-06-09", + "last_updated": "2026-06-09", + "knowledge": "2026-01" + }, { "id": "anthropic/claude-haiku-4-5", "label": "Claude Haiku 4.5", @@ -6759,98 +7496,12 @@ "last_updated": "2025-09-29", "knowledge": "2025-07-31" }, - { - "id": "anthropic/claude-sonnet-4-6", - "label": "Claude Sonnet 4.6", - "family": "claude-sonnet", - "context": 200000, - "output_limit": 64000, - "reasoning": true, - "supports_effort": true, - "effort": { - "kind": "none" - }, - "tool_call": true, - "attachment": true, - "structured_output": true, - "temperature": true, - "open_weights": false, - "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text" - ] - }, - "cost": { - "input": 3, - "output": 15, - "cache_read": 0.3 - }, - "group": "Agent API", - "note": null, - "endpoint": "/v1/agent", - "hidden": false, - "active": true, - "priority": 150, - "default": false, - "aliases": [], - "release_date": "2026-02-17", - "last_updated": "2026-02-17", - "knowledge": "2025-08-31" - }, - { - "id": "anthropic/claude-sonnet-5", - "label": "Claude Sonnet 5", - "family": "claude-sonnet", - "context": 1000000, - "output_limit": 128000, - "reasoning": true, - "supports_effort": true, - "effort": { - "kind": "none" - }, - "tool_call": true, - "attachment": true, - "structured_output": true, - "temperature": false, - "open_weights": false, - "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text" - ] - }, - "cost": { - "input": 3, - "output": 15, - "cache_read": 0.3 - }, - "group": "Agent API", - "note": "Introductory pricing of $2 / $10 per MTok applies through 2026-08-31.", - "endpoint": "/v1/agent", - "hidden": false, - "active": true, - "priority": 155, - "default": false, - "aliases": [], - "release_date": "2026-06-30", - "last_updated": "2026-06-30", - "knowledge": "2026-01" - }, - { - "id": "google/gemini-2.5-flash", - "label": "Gemini 2.5 Flash", - "family": "gemini-flash", - "context": 1048576, - "output_limit": 65536, + { + "id": "anthropic/claude-sonnet-4-6", + "label": "Claude Sonnet 4.6", + "family": "claude-sonnet", + "context": 200000, + "output_limit": 64000, "reasoning": true, "supports_effort": true, "effort": { @@ -6865,8 +7516,6 @@ "input": [ "text", "image", - "audio", - "video", "pdf" ], "output": [ @@ -6874,28 +7523,28 @@ ] }, "cost": { - "input": 0.3, - "output": 2.5, - "cache_read": 0.03 + "input": 3, + "output": 15, + "cache_read": 0.3 }, "group": "Agent API", "note": null, "endpoint": "/v1/agent", "hidden": false, "active": true, - "priority": 40, + "priority": 150, "default": false, "aliases": [], - "release_date": "2025-03-20", - "last_updated": "2025-06-05", - "knowledge": "2025-01" + "release_date": "2026-02-17", + "last_updated": "2026-02-17", + "knowledge": "2025-08-31" }, { - "id": "google/gemini-2.5-pro", - "label": "Gemini 2.5 Pro", - "family": "gemini-pro", - "context": 1048576, - "output_limit": 65536, + "id": "anthropic/claude-sonnet-5", + "label": "Claude Sonnet 5", + "family": "claude-sonnet", + "context": 1000000, + "output_limit": 128000, "reasoning": true, "supports_effort": true, "effort": { @@ -6904,14 +7553,12 @@ "tool_call": true, "attachment": true, "structured_output": true, - "temperature": true, + "temperature": false, "open_weights": false, "modalities": { "input": [ "text", "image", - "audio", - "video", "pdf" ], "output": [ @@ -6919,21 +7566,21 @@ ] }, "cost": { - "input": 1.25, + "input": 2, "output": 10, - "cache_read": 0.125 + "cache_read": 0.2 }, "group": "Agent API", "note": null, "endpoint": "/v1/agent", "hidden": false, "active": true, - "priority": 50, + "priority": 155, "default": false, "aliases": [], - "release_date": "2025-03-20", - "last_updated": "2025-06-05", - "knowledge": "2025-01" + "release_date": "2026-06-30", + "last_updated": "2026-06-30", + "knowledge": "2026-01" }, { "id": "google/gemini-3-flash-preview", @@ -7071,44 +7718,94 @@ "knowledge": "2025-01" }, { - "id": "nvidia/nemotron-3-super-120b-a12b", - "label": "Nemotron 3 Super 120B", - "family": "nemotron", - "context": 1000000, - "output_limit": 32000, + "id": "google/gemini-3.6-flash", + "label": "Gemini 3.6 Flash", + "family": "gemini-flash", + "context": 1048576, + "output_limit": 65536, "reasoning": true, "supports_effort": true, "effort": { "kind": "none" }, "tool_call": true, - "attachment": false, + "attachment": true, "structured_output": true, "temperature": true, - "open_weights": true, + "open_weights": false, "modalities": { "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ "text" + ] + }, + "cost": { + "input": 1.5, + "output": 7.5, + "cache_read": 0.15 + }, + "group": "Agent API", + "note": null, + "endpoint": "/v1/agent", + "hidden": false, + "active": true, + "priority": 74, + "default": false, + "aliases": [], + "release_date": "2026-07-21", + "last_updated": "2026-07-21", + "knowledge": "2026-03" + }, + { + "id": "google/gemini-3.8-flash", + "label": "Gemini 3.8 Flash", + "family": "gemini-flash", + "context": 1048576, + "output_limit": 65536, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": true, + "structured_output": true, + "temperature": true, + "open_weights": false, + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" ], "output": [ "text" ] }, "cost": { - "input": 0.25, - "output": 2.5 + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 }, "group": "Agent API", "note": null, "endpoint": "/v1/agent", "hidden": false, "active": true, - "priority": 30, + "priority": 78, "default": false, "aliases": [], - "release_date": "2026-03-11", - "last_updated": "2026-03-11", - "knowledge": "2026-02" + "release_date": "2026-09-02", + "last_updated": "2026-09-02", + "knowledge": "2026-03" }, { "id": "openai/gpt-5-mini", @@ -7450,6 +8147,131 @@ "last_updated": "2026-07-09", "knowledge": "2026-02-16" }, + { + "id": "perplexity/glm-5.3", + "label": "GLM 5.3", + "family": "glm", + "context": 1048576, + "output_limit": 131072, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": false, + "structured_output": true, + "temperature": true, + "open_weights": true, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 1.4, + "output": 4.4, + "cache_read": 0.26 + }, + "group": "Agent API", + "note": null, + "endpoint": "/v1/agent", + "hidden": false, + "active": true, + "priority": 33, + "default": false, + "aliases": [], + "release_date": "2026-08-18", + "last_updated": "2026-08-18", + "knowledge": null + }, + { + "id": "perplexity/kimi-k3", + "label": "Kimi K3", + "family": "kimi-k3", + "context": 1048576, + "output_limit": null, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": true, + "structured_output": true, + "temperature": false, + "open_weights": true, + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 3, + "output": 15, + "cache_read": 0.3 + }, + "group": "Agent API", + "note": null, + "endpoint": "/v1/agent", + "hidden": false, + "active": true, + "priority": 35, + "default": false, + "aliases": [], + "release_date": "2026-07-16", + "last_updated": "2026-07-16", + "knowledge": null + }, + { + "id": "perplexity/nemotron-3-ultra-550b-a55b", + "label": "Nemotron 3 Ultra", + "family": "nemotron", + "context": null, + "output_limit": null, + "reasoning": false, + "supports_effort": false, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": false, + "structured_output": false, + "temperature": true, + "open_weights": true, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 0.25, + "output": 2.5, + "cache_read": 0.25 + }, + "group": "Agent API", + "note": null, + "endpoint": "/v1/agent", + "hidden": false, + "active": true, + "priority": 31, + "default": false, + "aliases": [], + "release_date": null, + "last_updated": null, + "knowledge": null + }, { "id": "perplexity/sonar", "label": "Sonar", @@ -7660,13 +8482,13 @@ "knowledge": "2025-09-01" }, { - "id": "xai/grok-4-1-fast-non-reasoning", - "label": "Grok 4.1 Fast (Non-Reasoning)", + "id": "xai/grok-4.5", + "label": "Grok 4.5", "family": "grok", - "context": 2000000, + "context": 500000, "output_limit": 30000, - "reasoning": false, - "supports_effort": false, + "reasoning": true, + "supports_effort": true, "effort": { "kind": "none" }, @@ -7685,28 +8507,28 @@ ] }, "cost": { - "input": 0.2, - "output": 0.5, - "cache_read": 0.05 + "input": 2, + "output": 6, + "cache_read": 0.3 }, "group": "Agent API", "note": null, "endpoint": "/v1/agent", "hidden": false, "active": true, - "priority": 20, + "priority": 25, "default": false, "aliases": [], - "release_date": "2025-11-19", - "last_updated": "2025-11-19", - "knowledge": "2025-07" + "release_date": "2026-07-09", + "last_updated": "2026-07-09", + "knowledge": null }, { - "id": "xai/grok-4.5", - "label": "Grok 4.5", + "id": "xai/grok-4.6", + "label": "Grok 4.6", "family": "grok", "context": 500000, - "output_limit": 30000, + "output_limit": null, "reasoning": true, "supports_effort": true, "effort": { @@ -7729,19 +8551,19 @@ "cost": { "input": 2, "output": 6, - "cache_read": 0.3 + "cache_read": 0.5 }, "group": "Agent API", - "note": null, + "note": "Input/output pricing doubles for prompts above 200k tokens.", "endpoint": "/v1/agent", "hidden": false, "active": true, - "priority": 25, + "priority": 28, "default": false, "aliases": [], - "release_date": "2026-07-09", - "last_updated": "2026-07-09", - "knowledge": null + "release_date": "2026-08-12", + "last_updated": "2026-08-12", + "knowledge": "2026-02-01" } ] } diff --git a/dist/providers/anthropic.json b/dist/providers/anthropic.json index c1bd2c8..fbcd1f3 100644 --- a/dist/providers/anthropic.json +++ b/dist/providers/anthropic.json @@ -1,7 +1,7 @@ { "schemaVersion": 1, - "generatedAt": "2026-08-01T15:53:14.483Z", - "commit": "4f94308", + "generatedAt": "2026-09-21T11:46:14.774Z", + "commit": "28896da", "provider": { "id": "anthropic", "name": "Anthropic", @@ -56,7 +56,51 @@ "aliases": [], "release_date": "2026-06-09", "last_updated": "2026-06-09", - "knowledge": null + "knowledge": "2026-01" + }, + { + "id": "claude-fable-5-1", + "label": "Claude Fable 5.1", + "family": "claude-fable", + "context": 1000000, + "output_limit": 128000, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": true, + "structured_output": true, + "temperature": false, + "open_weights": false, + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 10, + "output": 50, + "cache_read": 0.25, + "cache_write": 12.5 + }, + "group": null, + "note": null, + "endpoint": null, + "hidden": false, + "active": true, + "priority": 45, + "default": false, + "aliases": [], + "release_date": "2026-09-01", + "last_updated": "2026-09-01", + "knowledge": "2026-06" }, { "id": "claude-haiku-4-5", @@ -173,13 +217,13 @@ ] }, "cost": { - "input": 3, - "output": 15, - "cache_read": 0.3, - "cache_write": 3.75 + "input": 2, + "output": 10, + "cache_read": 0.2, + "cache_write": 2.5 }, "group": null, - "note": "Introductory pricing of $2 / $10 per MTok applies through 2026-08-31.", + "note": null, "endpoint": null, "hidden": false, "active": true, diff --git a/dist/providers/antigravity-cli.json b/dist/providers/antigravity-cli.json index ac8537c..da6b13f 100644 --- a/dist/providers/antigravity-cli.json +++ b/dist/providers/antigravity-cli.json @@ -1,7 +1,7 @@ { "schemaVersion": 1, - "generatedAt": "2026-08-01T15:53:14.483Z", - "commit": "4f94308", + "generatedAt": "2026-09-21T11:46:14.774Z", + "commit": "28896da", "provider": { "id": "antigravity-cli", "name": "Antigravity CLI", diff --git a/dist/providers/antigravity-sdk.json b/dist/providers/antigravity-sdk.json index 905d22f..35e592b 100644 --- a/dist/providers/antigravity-sdk.json +++ b/dist/providers/antigravity-sdk.json @@ -1,7 +1,7 @@ { "schemaVersion": 1, - "generatedAt": "2026-08-01T15:53:14.483Z", - "commit": "4f94308", + "generatedAt": "2026-09-21T11:46:14.774Z", + "commit": "28896da", "provider": { "id": "antigravity-sdk", "name": "Antigravity SDK", @@ -193,8 +193,8 @@ "knowledge": "2025-01" }, { - "id": "gemini-3.5-flash-high", - "label": "Gemini 3.5 Flash (High)", + "id": "gemini-3.6-flash-high", + "label": "Gemini 3.6 Flash (High)", "family": "gemini-flash", "context": 1048576, "output_limit": 65536, @@ -221,25 +221,25 @@ ] }, "cost": { - "input": 1.5, - "output": 9, - "cache_read": 0.15 + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 }, "group": null, - "note": null, + "note": "Introductory pricing through 2026-12-31; $1.50 / $7.50 per MTok from 2027-01-01.", "endpoint": null, "hidden": false, "active": true, - "priority": 50, + "priority": 100, "default": false, "aliases": [], - "release_date": "2026-05-19", - "last_updated": "2026-05-19", - "knowledge": "2025-01" + "release_date": "2026-07-21", + "last_updated": "2026-07-21", + "knowledge": "2026-03" }, { - "id": "gemini-3.5-flash-low", - "label": "Gemini 3.5 Flash (Low)", + "id": "gemini-3.6-flash-low", + "label": "Gemini 3.6 Flash (Low)", "family": "gemini-flash", "context": 1048576, "output_limit": 65536, @@ -266,25 +266,25 @@ ] }, "cost": { - "input": 1.5, - "output": 9, - "cache_read": 0.15 + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 }, "group": null, - "note": null, + "note": "Introductory pricing through 2026-12-31; $1.50 / $7.50 per MTok from 2027-01-01.", "endpoint": null, "hidden": false, "active": true, - "priority": 35, + "priority": 80, "default": false, "aliases": [], - "release_date": "2026-05-19", - "last_updated": "2026-05-19", - "knowledge": "2025-01" + "release_date": "2026-07-21", + "last_updated": "2026-07-21", + "knowledge": "2026-03" }, { - "id": "gemini-3.5-flash-medium", - "label": "Gemini 3.5 Flash (Medium)", + "id": "gemini-3.6-flash-medium", + "label": "Gemini 3.6 Flash (Medium)", "family": "gemini-flash", "context": 1048576, "output_limit": 65536, @@ -311,25 +311,25 @@ ] }, "cost": { - "input": 1.5, - "output": 9, - "cache_read": 0.15 + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 }, "group": null, - "note": null, + "note": "Introductory pricing through 2026-12-31; $1.50 / $7.50 per MTok from 2027-01-01.", "endpoint": null, "hidden": false, "active": true, - "priority": 40, + "priority": 90, "default": false, "aliases": [], - "release_date": "2026-05-19", - "last_updated": "2026-05-19", - "knowledge": "2025-01" + "release_date": "2026-07-21", + "last_updated": "2026-07-21", + "knowledge": "2026-03" }, { - "id": "gemini-3.6-flash-high", - "label": "Gemini 3.6 Flash (High)", + "id": "gemini-3.7-flash-high", + "label": "Gemini 3.7 Flash (High)", "family": "gemini-flash", "context": 1048576, "output_limit": 65536, @@ -356,25 +356,25 @@ ] }, "cost": { - "input": 1.5, - "output": 7.5, - "cache_read": 0.15 + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 }, "group": null, - "note": null, + "note": "Introductory pricing through 2026-12-31; $1.50 / $7.50 per MTok from 2027-01-01.", "endpoint": null, "hidden": false, "active": true, - "priority": 100, + "priority": 130, "default": false, "aliases": [], - "release_date": "2026-07-21", - "last_updated": "2026-07-21", + "release_date": "2026-08-13", + "last_updated": "2026-08-13", "knowledge": "2026-03" }, { - "id": "gemini-3.6-flash-low", - "label": "Gemini 3.6 Flash (Low)", + "id": "gemini-3.7-flash-low", + "label": "Gemini 3.7 Flash (Low)", "family": "gemini-flash", "context": 1048576, "output_limit": 65536, @@ -401,25 +401,25 @@ ] }, "cost": { - "input": 1.5, - "output": 7.5, - "cache_read": 0.15 + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 }, "group": null, - "note": null, + "note": "Introductory pricing through 2026-12-31; $1.50 / $7.50 per MTok from 2027-01-01.", "endpoint": null, "hidden": false, "active": true, - "priority": 80, + "priority": 110, "default": false, "aliases": [], - "release_date": "2026-07-21", - "last_updated": "2026-07-21", + "release_date": "2026-08-13", + "last_updated": "2026-08-13", "knowledge": "2026-03" }, { - "id": "gemini-3.6-flash-medium", - "label": "Gemini 3.6 Flash (Medium)", + "id": "gemini-3.7-flash-medium", + "label": "Gemini 3.7 Flash (Medium)", "family": "gemini-flash", "context": 1048576, "output_limit": 65536, @@ -446,20 +446,155 @@ ] }, "cost": { - "input": 1.5, - "output": 7.5, - "cache_read": 0.15 + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 }, "group": null, - "note": null, + "note": "Introductory pricing through 2026-12-31; $1.50 / $7.50 per MTok from 2027-01-01.", "endpoint": null, "hidden": false, "active": true, - "priority": 90, + "priority": 120, "default": false, "aliases": [], - "release_date": "2026-07-21", - "last_updated": "2026-07-21", + "release_date": "2026-08-13", + "last_updated": "2026-08-13", + "knowledge": "2026-03" + }, + { + "id": "gemini-3.8-flash-high", + "label": "Gemini 3.8 Flash (High)", + "family": "gemini-flash", + "context": 1048576, + "output_limit": 65536, + "reasoning": true, + "supports_effort": false, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": true, + "structured_output": true, + "temperature": true, + "open_weights": false, + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 + }, + "group": null, + "note": "Introductory pricing through 2026-12-31; $1.50 / $7.50 per MTok from 2027-01-01.", + "endpoint": null, + "hidden": false, + "active": true, + "priority": 160, + "default": false, + "aliases": [], + "release_date": "2026-09-02", + "last_updated": "2026-09-02", + "knowledge": "2026-03" + }, + { + "id": "gemini-3.8-flash-low", + "label": "Gemini 3.8 Flash (Low)", + "family": "gemini-flash", + "context": 1048576, + "output_limit": 65536, + "reasoning": true, + "supports_effort": false, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": true, + "structured_output": true, + "temperature": true, + "open_weights": false, + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 + }, + "group": null, + "note": "Introductory pricing through 2026-12-31; $1.50 / $7.50 per MTok from 2027-01-01.", + "endpoint": null, + "hidden": false, + "active": true, + "priority": 140, + "default": false, + "aliases": [], + "release_date": "2026-09-02", + "last_updated": "2026-09-02", + "knowledge": "2026-03" + }, + { + "id": "gemini-3.8-flash-medium", + "label": "Gemini 3.8 Flash (Medium)", + "family": "gemini-flash", + "context": 1048576, + "output_limit": 65536, + "reasoning": true, + "supports_effort": false, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": true, + "structured_output": true, + "temperature": true, + "open_weights": false, + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 + }, + "group": null, + "note": "Introductory pricing through 2026-12-31; $1.50 / $7.50 per MTok from 2027-01-01.", + "endpoint": null, + "hidden": false, + "active": true, + "priority": 150, + "default": false, + "aliases": [], + "release_date": "2026-09-02", + "last_updated": "2026-09-02", "knowledge": "2026-03" }, { diff --git a/dist/providers/claude-code.json b/dist/providers/claude-code.json index 96102b5..fbcbd98 100644 --- a/dist/providers/claude-code.json +++ b/dist/providers/claude-code.json @@ -1,7 +1,7 @@ { "schemaVersion": 1, - "generatedAt": "2026-08-01T15:53:14.483Z", - "commit": "4f94308", + "generatedAt": "2026-09-21T11:46:14.774Z", + "commit": "28896da", "provider": { "id": "claude-code", "name": "Claude Code", @@ -62,7 +62,59 @@ "aliases": [], "release_date": "2026-06-09", "last_updated": "2026-06-09", - "knowledge": null + "knowledge": "2026-01" + }, + { + "id": "claude-fable-5-1", + "label": "Fable 5.1", + "family": "claude-fable", + "context": 1000000, + "output_limit": 128000, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "levels", + "levels": [ + "low", + "medium", + "high", + "xhigh", + "max" + ], + "default": "high" + }, + "tool_call": true, + "attachment": true, + "structured_output": true, + "temperature": false, + "open_weights": false, + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 10, + "output": 50, + "cache_read": 0.25, + "cache_write": 12.5 + }, + "group": null, + "note": null, + "endpoint": null, + "hidden": false, + "active": true, + "priority": 65, + "default": false, + "aliases": [], + "release_date": "2026-09-01", + "last_updated": "2026-09-01", + "knowledge": "2026-06" }, { "id": "claude-haiku-4-5-20251001", @@ -249,13 +301,13 @@ ] }, "cost": { - "input": 3, - "output": 15, - "cache_read": 0.3, - "cache_write": 3.75 + "input": 2, + "output": 10, + "cache_read": 0.2, + "cache_write": 2.5 }, "group": null, - "note": "Introductory pricing of $2 / $10 per MTok applies through 2026-08-31.", + "note": null, "endpoint": null, "hidden": false, "active": true, diff --git a/dist/providers/cloudflare-workers-ai.json b/dist/providers/cloudflare-workers-ai.json index a4c4f99..6075202 100644 --- a/dist/providers/cloudflare-workers-ai.json +++ b/dist/providers/cloudflare-workers-ai.json @@ -1,7 +1,7 @@ { "schemaVersion": 1, - "generatedAt": "2026-08-01T15:53:14.483Z", - "commit": "4f94308", + "generatedAt": "2026-09-21T11:46:14.774Z", + "commit": "28896da", "provider": { "id": "cloudflare-workers-ai", "name": "Cloudflare Workers AI", @@ -94,6 +94,88 @@ "last_updated": "2025-01-22", "knowledge": null }, + { + "id": "@cf/deepseek-ai/deepseek-v4-flash-0731", + "label": "DeepSeek V4 Flash", + "family": "deepseek-flash", + "context": 1048576, + "output_limit": null, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": false, + "structured_output": false, + "temperature": true, + "open_weights": true, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 0.44, + "output": 1.32, + "cache_read": 0.014 + }, + "group": null, + "note": "Requires the Workers Paid plan.", + "endpoint": null, + "hidden": false, + "active": true, + "priority": 154, + "default": false, + "aliases": [], + "release_date": "2026-04-24", + "last_updated": "2026-07-31", + "knowledge": null + }, + { + "id": "@cf/deepseek-ai/deepseek-v4-pro-0813", + "label": "DeepSeek V4 Pro", + "family": "deepseek-thinking", + "context": 1048576, + "output_limit": null, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": false, + "structured_output": false, + "temperature": true, + "open_weights": true, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 1.32, + "output": 3.96, + "cache_read": 0.044 + }, + "group": null, + "note": "Requires the Workers Paid plan.", + "endpoint": null, + "hidden": false, + "active": true, + "priority": 174, + "default": false, + "aliases": [], + "release_date": "2026-04-24", + "last_updated": "2026-08-13", + "knowledge": null + }, { "id": "@cf/google/gemma-4-26b-a4b-it", "label": "Gemma 4 26B A4B IT", @@ -447,7 +529,7 @@ "cache_read": 0.16 }, "group": null, - "note": null, + "note": "Requires the Workers Paid plan.", "endpoint": null, "hidden": false, "active": true, @@ -489,15 +571,15 @@ "cache_read": 0.19 }, "group": null, - "note": null, + "note": "Requires the Workers Paid plan.", "endpoint": null, "hidden": false, "active": true, "priority": 145, "default": false, "aliases": [], - "release_date": null, - "last_updated": null, + "release_date": "2026-06-12", + "last_updated": "2026-06-12", "knowledge": null }, { @@ -700,6 +782,48 @@ "last_updated": "2025-04-30", "knowledge": null }, + { + "id": "@cf/qwen/qwen3.8-27b", + "label": "Qwen 3.8 27B", + "family": "qwen", + "context": 262144, + "output_limit": null, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": true, + "structured_output": false, + "temperature": true, + "open_weights": false, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 0.45, + "output": 3.2, + "cache_read": 0.05 + }, + "group": null, + "note": null, + "endpoint": null, + "hidden": false, + "active": true, + "priority": 152, + "default": false, + "aliases": [], + "release_date": "2026-08-14", + "last_updated": "2026-08-17", + "knowledge": null + }, { "id": "@cf/qwen/qwq-32b", "label": "Qwq 32B", @@ -765,7 +889,7 @@ ] }, "cost": { - "input": 0.0605, + "input": 0.06, "output": 0.4 }, "group": null, @@ -779,6 +903,89 @@ "release_date": "2026-01-19", "last_updated": "2026-01-19", "knowledge": "2025-04" + }, + { + "id": "@cf/zai-org/glm-5.3", + "label": "GLM 5.3", + "family": "glm", + "context": 1310720, + "output_limit": null, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": false, + "structured_output": false, + "temperature": true, + "open_weights": true, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 1.4, + "output": 4.4, + "cache_read": 0.26 + }, + "group": null, + "note": "Requires the Workers Paid plan.", + "endpoint": null, + "hidden": false, + "active": true, + "priority": 176, + "default": false, + "aliases": [], + "release_date": "2026-08-18", + "last_updated": "2026-08-28", + "knowledge": null + }, + { + "id": "@cf/zai-org/glm-5.3-flash", + "label": "GLM 5.3 Flash", + "family": "glm-flash", + "context": 1310720, + "output_limit": null, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": true, + "structured_output": false, + "temperature": true, + "open_weights": true, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 0.15, + "output": 0.5, + "cache_read": 0.03 + }, + "group": null, + "note": "Requires the Workers Paid plan.", + "endpoint": null, + "hidden": false, + "active": true, + "priority": 156, + "default": false, + "aliases": [], + "release_date": "2026-08-25", + "last_updated": "2026-08-26", + "knowledge": null } ] } diff --git a/dist/providers/codex-cli.json b/dist/providers/codex-cli.json index ba207f7..7e76926 100644 --- a/dist/providers/codex-cli.json +++ b/dist/providers/codex-cli.json @@ -1,7 +1,7 @@ { "schemaVersion": 1, - "generatedAt": "2026-08-01T15:53:14.483Z", - "commit": "4f94308", + "generatedAt": "2026-09-21T11:46:14.774Z", + "commit": "28896da", "provider": { "id": "codex-cli", "name": "Codex CLI", @@ -12,60 +12,11 @@ "models_endpoint": null, "supports_live": false, "models": [ - { - "id": "gpt-5.4-mini", - "label": "GPT-5.4 mini", - "family": "gpt-mini", - "context": 400000, - "output_limit": 128000, - "reasoning": true, - "supports_effort": true, - "effort": { - "kind": "levels", - "levels": [ - "low", - "medium", - "high", - "xhigh" - ], - "default": "medium" - }, - "tool_call": true, - "attachment": true, - "structured_output": true, - "temperature": false, - "open_weights": false, - "modalities": { - "input": [ - "text", - "image" - ], - "output": [ - "text" - ] - }, - "cost": { - "input": 0.75, - "output": 4.5, - "cache_read": 0.075 - }, - "group": null, - "note": null, - "endpoint": null, - "hidden": false, - "active": true, - "priority": 20, - "default": false, - "aliases": [], - "release_date": "2026-03-17", - "last_updated": "2026-03-17", - "knowledge": "2025-08-31" - }, { "id": "gpt-5.5", "label": "GPT-5.5", "family": "gpt", - "context": 400000, + "context": 1050000, "output_limit": 128000, "reasoning": true, "supports_effort": true, @@ -199,12 +150,12 @@ ] }, "cost": { - "input": 5, - "output": 30, - "cache_read": 0.5 + "input": 4, + "output": 20, + "cache_read": 0.4 }, "group": null, - "note": null, + "note": "Promotional pricing, guaranteed through 2026-11-21 (was $5 / $30).", "endpoint": null, "hidden": false, "active": true, @@ -214,7 +165,7 @@ "gpt-5.6" ], "release_date": "2026-07-09", - "last_updated": "2026-07-09", + "last_updated": "2026-08-21", "knowledge": "2026-02-16" }, { @@ -268,6 +219,58 @@ "release_date": "2026-07-09", "last_updated": "2026-07-09", "knowledge": "2026-02-16" + }, + { + "id": "gpt-6-astra", + "label": "GPT-6 Astra", + "family": "gpt", + "context": 1050000, + "output_limit": 128000, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "levels", + "levels": [ + "low", + "medium", + "high", + "xhigh", + "max", + "ultra" + ], + "default": "medium" + }, + "tool_call": true, + "attachment": true, + "structured_output": true, + "temperature": false, + "open_weights": false, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 10, + "output": 50, + "cache_read": 1, + "cache_write": 12.5 + }, + "group": null, + "note": "Most capable", + "endpoint": null, + "hidden": false, + "active": true, + "priority": 85, + "default": false, + "aliases": [], + "release_date": "2026-09-03", + "last_updated": "2026-09-03", + "knowledge": "2026-04-30" } ] } diff --git a/dist/providers/deepseek.json b/dist/providers/deepseek.json index e7d9ef9..3176c3c 100644 --- a/dist/providers/deepseek.json +++ b/dist/providers/deepseek.json @@ -1,7 +1,7 @@ { "schemaVersion": 1, - "generatedAt": "2026-08-01T15:53:14.483Z", - "commit": "4f94308", + "generatedAt": "2026-09-21T11:46:14.774Z", + "commit": "28896da", "provider": { "id": "deepseek", "name": "DeepSeek", @@ -15,45 +15,55 @@ "supports_live": true, "models": [ { - "id": "deepseek-v4-flash", - "label": "DeepSeek V4 Flash", + "id": "deepseek-flash", + "label": "DeepSeek V4.1 Flash", "family": "deepseek-flash", "context": 1000000, "output_limit": 384000, "reasoning": true, "supports_effort": true, "effort": { - "kind": "none" + "kind": "levels", + "levels": [ + "low", + "high", + "max" + ], + "default": "high" }, "tool_call": true, - "attachment": false, + "attachment": true, "structured_output": true, "temperature": true, "open_weights": true, "modalities": { "input": [ - "text" + "text", + "image" ], "output": [ "text" ] }, "cost": { - "input": 0.14, - "output": 0.28, - "cache_read": 0.0028 + "input": 0.3, + "output": 1.2, + "cache_read": 0.006 }, "group": null, - "note": null, + "note": "Peak-hour pricing. Rates halve off-peak (outside 01:00-04:00 and 06:00-10:00 UTC, Mon-Fri).", "endpoint": null, "hidden": false, "active": true, - "priority": 10, - "default": false, - "aliases": [], - "release_date": "2026-04-24", - "last_updated": "2026-04-24", - "knowledge": "2025-05" + "priority": 30, + "default": true, + "aliases": [ + "deepseek-v4-flash", + "deepseek-v4-flash-vision-exp" + ], + "release_date": "2026-09-10", + "last_updated": "2026-09-10", + "knowledge": null }, { "id": "deepseek-v4-pro", @@ -64,7 +74,13 @@ "reasoning": true, "supports_effort": true, "effort": { - "kind": "none" + "kind": "levels", + "levels": [ + "low", + "high", + "max" + ], + "default": "high" }, "tool_call": true, "attachment": false, @@ -80,20 +96,20 @@ ] }, "cost": { - "input": 0.435, - "output": 0.87, - "cache_read": 0.003625 + "input": 1.32, + "output": 3.96, + "cache_read": 0.044 }, "group": null, - "note": null, + "note": "Peak-hour pricing. Rates halve off-peak (outside 01:00-04:00 and 06:00-10:00 UTC, Mon-Fri).", "endpoint": null, "hidden": false, "active": true, "priority": 20, - "default": true, + "default": false, "aliases": [], "release_date": "2026-04-24", - "last_updated": "2026-04-24", + "last_updated": "2026-08-13", "knowledge": "2025-05" } ] diff --git a/dist/providers/gemini-api.json b/dist/providers/gemini-api.json index e2bf808..2498788 100644 --- a/dist/providers/gemini-api.json +++ b/dist/providers/gemini-api.json @@ -1,7 +1,7 @@ { "schemaVersion": 1, - "generatedAt": "2026-08-01T15:53:14.483Z", - "commit": "4f94308", + "generatedAt": "2026-09-21T11:46:14.774Z", + "commit": "28896da", "provider": { "id": "gemini-api", "name": "Google", @@ -410,7 +410,7 @@ "aliases": [], "release_date": "2026-07-21", "last_updated": "2026-07-21", - "knowledge": null + "knowledge": "2026-03" }, { "id": "gemini-3.6-flash", @@ -446,12 +446,12 @@ ] }, "cost": { - "input": 1.5, - "output": 7.5, - "cache_read": 0.15 + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 }, "group": null, - "note": null, + "note": "Introductory pricing through 2026-12-31; $1.50 / $7.50 per MTok from 2027-01-01.", "endpoint": null, "hidden": false, "active": true, @@ -461,6 +461,108 @@ "release_date": "2026-07-21", "last_updated": "2026-07-21", "knowledge": "2026-03" + }, + { + "id": "gemini-3.7-flash", + "label": "Gemini 3.7 Flash", + "family": "gemini-flash", + "context": 1048576, + "output_limit": 65536, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "thinking_level", + "levels": [ + "low", + "medium", + "high" + ], + "default": "medium" + }, + "tool_call": true, + "attachment": true, + "structured_output": true, + "temperature": true, + "open_weights": false, + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 + }, + "group": null, + "note": "Introductory pricing through 2026-12-31; $1.50 / $7.50 per MTok from 2027-01-01.", + "endpoint": null, + "hidden": false, + "active": true, + "priority": 90, + "default": false, + "aliases": [], + "release_date": "2026-08-13", + "last_updated": "2026-08-13", + "knowledge": "2026-03" + }, + { + "id": "gemini-3.8-flash", + "label": "Gemini 3.8 Flash", + "family": "gemini-flash", + "context": 1048576, + "output_limit": 65536, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "thinking_level", + "levels": [ + "low", + "medium", + "high" + ], + "default": "medium" + }, + "tool_call": true, + "attachment": true, + "structured_output": true, + "temperature": true, + "open_weights": false, + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 + }, + "group": null, + "note": "Introductory pricing through 2026-12-31; $1.50 / $7.50 per MTok from 2027-01-01.", + "endpoint": null, + "hidden": false, + "active": true, + "priority": 100, + "default": false, + "aliases": [], + "release_date": "2026-09-02", + "last_updated": "2026-09-02", + "knowledge": "2026-03" } ] } diff --git a/dist/providers/github-copilot.json b/dist/providers/github-copilot.json index 12725d0..5511205 100644 --- a/dist/providers/github-copilot.json +++ b/dist/providers/github-copilot.json @@ -1,7 +1,7 @@ { "schemaVersion": 1, - "generatedAt": "2026-08-01T15:53:14.483Z", - "commit": "4f94308", + "generatedAt": "2026-09-21T11:46:14.774Z", + "commit": "28896da", "provider": { "id": "github-copilot", "name": "GitHub Copilot CLI", @@ -57,9 +57,9 @@ "knowledge": null }, { - "id": "claude-haiku-4.5", - "label": "Claude Haiku 4.5", - "family": "claude-haiku", + "id": "claude-fable-5", + "label": "Claude Fable 5", + "family": "claude-fable", "context": 200000, "output_limit": 64000, "reasoning": true, @@ -77,7 +77,7 @@ "tool_call": true, "attachment": true, "structured_output": true, - "temperature": true, + "temperature": false, "open_weights": false, "modalities": { "input": [ @@ -90,29 +90,29 @@ ] }, "cost": { - "input": 1, - "output": 5, - "cache_read": 0.1, - "cache_write": 1.25 + "input": 10, + "output": 50, + "cache_read": 1, + "cache_write": 12.5 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 20, + "priority": 227, "default": false, "aliases": [], - "release_date": "2025-10-15", - "last_updated": "2025-10-15", - "knowledge": "2025-02-28" + "release_date": "2026-06-09", + "last_updated": "2026-06-09", + "knowledge": "2026-01" }, { - "id": "claude-opus-4.5", - "label": "Claude Opus 4.5", - "family": "claude-opus", + "id": "claude-fable-5.1", + "label": "Claude Fable 5.1", + "family": "claude-fable", "context": 200000, - "output_limit": 32000, + "output_limit": 64000, "reasoning": true, "supports_effort": true, "effort": { @@ -128,7 +128,7 @@ "tool_call": true, "attachment": true, "structured_output": true, - "temperature": true, + "temperature": false, "open_weights": false, "modalities": { "input": [ @@ -141,29 +141,29 @@ ] }, "cost": { - "input": 5, - "output": 25, - "cache_read": 0.5, - "cache_write": 6.25 + "input": 10, + "output": 50, + "cache_read": 0.25, + "cache_write": 12.5 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 190, + "priority": 228, "default": false, "aliases": [], - "release_date": "2025-11-24", - "last_updated": "2025-11-24", - "knowledge": "2025-03-31" + "release_date": "2026-09-01", + "last_updated": "2026-09-01", + "knowledge": "2026-06" }, { - "id": "claude-opus-4.6", - "label": "Claude Opus 4.6", - "family": "claude-opus", + "id": "claude-haiku-4.5", + "label": "Claude Haiku 4.5", + "family": "claude-haiku", "context": 200000, - "output_limit": 32000, + "output_limit": 64000, "reasoning": true, "supports_effort": true, "effort": { @@ -192,22 +192,22 @@ ] }, "cost": { - "input": 5, - "output": 25, - "cache_read": 0.5, - "cache_write": 6.25 + "input": 1, + "output": 5, + "cache_read": 0.1, + "cache_write": 1.25 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 200, + "priority": 20, "default": false, "aliases": [], - "release_date": "2026-02-05", - "last_updated": "2026-03-13", - "knowledge": "2025-05-31" + "release_date": "2025-10-15", + "last_updated": "2025-10-15", + "knowledge": "2025-02-28" }, { "id": "claude-opus-4.7", @@ -362,57 +362,6 @@ "last_updated": "2026-07-24", "knowledge": "2026-05" }, - { - "id": "claude-sonnet-4.5", - "label": "Claude Sonnet 4.5", - "family": "claude-sonnet", - "context": 200000, - "output_limit": 32000, - "reasoning": true, - "supports_effort": true, - "effort": { - "kind": "levels", - "levels": [ - "low", - "medium", - "high", - "xhigh" - ], - "default": "medium" - }, - "tool_call": true, - "attachment": true, - "structured_output": true, - "temperature": true, - "open_weights": false, - "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text" - ] - }, - "cost": { - "input": 3, - "output": 15, - "cache_read": 0.3, - "cache_write": 3.75 - }, - "group": null, - "note": null, - "endpoint": null, - "hidden": false, - "active": true, - "priority": 170, - "default": false, - "aliases": [], - "release_date": "2025-09-29", - "last_updated": "2025-09-29", - "knowledge": "2025-07-31" - }, { "id": "claude-sonnet-4.6", "label": "Claude Sonnet 4.6", @@ -498,10 +447,10 @@ ] }, "cost": { - "input": 3, - "output": 15, - "cache_read": 0.3, - "cache_write": 3.75 + "input": 2, + "output": 10, + "cache_read": 0.2, + "cache_write": 2.5 }, "group": null, "note": null, @@ -515,162 +464,6 @@ "last_updated": "2026-06-30", "knowledge": "2026-01" }, - { - "id": "gemini-2.5-pro", - "label": "Gemini 2.5 Pro", - "family": "gemini-pro", - "context": 128000, - "output_limit": 64000, - "reasoning": true, - "supports_effort": true, - "effort": { - "kind": "levels", - "levels": [ - "low", - "medium", - "high", - "xhigh" - ], - "default": "medium" - }, - "tool_call": true, - "attachment": true, - "structured_output": true, - "temperature": true, - "open_weights": false, - "modalities": { - "input": [ - "text", - "image", - "audio", - "video", - "pdf" - ], - "output": [ - "text" - ] - }, - "cost": { - "input": 1.25, - "output": 10, - "cache_read": 0.125 - }, - "group": null, - "note": null, - "endpoint": null, - "hidden": false, - "active": true, - "priority": 70, - "default": false, - "aliases": [], - "release_date": "2025-03-20", - "last_updated": "2025-06-05", - "knowledge": "2025-01" - }, - { - "id": "gemini-3-flash-preview", - "label": "Gemini 3 Flash Preview", - "family": "gemini-flash", - "context": 128000, - "output_limit": 64000, - "reasoning": true, - "supports_effort": true, - "effort": { - "kind": "levels", - "levels": [ - "low", - "medium", - "high", - "xhigh" - ], - "default": "medium" - }, - "tool_call": true, - "attachment": true, - "structured_output": true, - "temperature": true, - "open_weights": false, - "modalities": { - "input": [ - "text", - "image", - "video", - "audio", - "pdf" - ], - "output": [ - "text" - ] - }, - "cost": { - "input": 0.5, - "output": 3, - "cache_read": 0.05 - }, - "group": null, - "note": null, - "endpoint": null, - "hidden": false, - "active": true, - "priority": 80, - "default": false, - "aliases": [], - "release_date": "2025-12-17", - "last_updated": "2025-12-17", - "knowledge": "2025-01" - }, - { - "id": "gemini-3.1-pro-preview", - "label": "Gemini 3.1 Pro Preview", - "family": "gemini-pro", - "context": 200000, - "output_limit": 64000, - "reasoning": true, - "supports_effort": true, - "effort": { - "kind": "levels", - "levels": [ - "low", - "medium", - "high", - "xhigh" - ], - "default": "medium" - }, - "tool_call": true, - "attachment": true, - "structured_output": true, - "temperature": true, - "open_weights": false, - "modalities": { - "input": [ - "text", - "image", - "video", - "audio", - "pdf" - ], - "output": [ - "text" - ] - }, - "cost": { - "input": 2, - "output": 12, - "cache_read": 0.2 - }, - "group": null, - "note": null, - "endpoint": null, - "hidden": false, - "active": true, - "priority": 90, - "default": false, - "aliases": [], - "release_date": "2026-02-19", - "last_updated": "2026-02-19", - "knowledge": "2025-01" - }, { "id": "gemini-3.5-flash", "label": "Gemini 3.5 Flash", @@ -759,9 +552,9 @@ ] }, "cost": { - "input": 1.5, - "output": 7.5, - "cache_read": 0.15 + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 }, "group": null, "note": null, @@ -776,12 +569,12 @@ "knowledge": "2026-03" }, { - "id": "gpt-4.1", - "label": "GPT-4.1", - "family": "gpt", - "context": 128000, - "output_limit": 16384, - "reasoning": false, + "id": "gemini-3.8-flash", + "label": "Gemini 3.8 Flash", + "family": "gemini-flash", + "context": 200000, + "output_limit": 64000, + "reasoning": true, "supports_effort": true, "effort": { "kind": "levels", @@ -802,6 +595,8 @@ "input": [ "text", "image", + "video", + "audio", "pdf" ], "output": [ @@ -809,21 +604,21 @@ ] }, "cost": { - "input": 2, - "output": 8, - "cache_read": 0.5 + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 60, + "priority": 108, "default": false, "aliases": [], - "release_date": "2025-04-14", - "last_updated": "2025-04-14", - "knowledge": "2024-04" + "release_date": "2026-09-02", + "last_updated": "2026-09-02", + "knowledge": "2026-03" }, { "id": "gpt-5-mini", @@ -875,9 +670,9 @@ "knowledge": "2024-05-30" }, { - "id": "gpt-5.2", - "label": "GPT-5.2", - "family": "gpt", + "id": "gpt-5.3-codex", + "label": "GPT-5.3 Codex", + "family": "gpt-codex", "context": 400000, "output_limit": 128000, "reasoning": true, @@ -900,7 +695,8 @@ "modalities": { "input": [ "text", - "image" + "image", + "pdf" ], "output": [ "text" @@ -916,17 +712,17 @@ "endpoint": null, "hidden": false, "active": true, - "priority": 110, + "priority": 130, "default": false, "aliases": [], - "release_date": "2025-12-11", - "last_updated": "2025-12-11", + "release_date": "2026-02-05", + "last_updated": "2026-02-05", "knowledge": "2025-08-31" }, { - "id": "gpt-5.2-codex", - "label": "GPT-5.2 Codex", - "family": "gpt-codex", + "id": "gpt-5.4", + "label": "GPT-5.4", + "family": "gpt", "context": 400000, "output_limit": 128000, "reasoning": true, @@ -957,26 +753,26 @@ ] }, "cost": { - "input": 1.75, - "output": 14, - "cache_read": 0.175 + "input": 2.5, + "output": 15, + "cache_read": 0.25 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 120, + "priority": 140, "default": false, "aliases": [], - "release_date": "2025-12-11", - "last_updated": "2025-12-11", + "release_date": "2026-03-05", + "last_updated": "2026-03-05", "knowledge": "2025-08-31" }, { - "id": "gpt-5.3-codex", - "label": "GPT-5.3 Codex", - "family": "gpt-codex", + "id": "gpt-5.4-mini", + "label": "GPT-5.4 mini", + "family": "gpt-mini", "context": 400000, "output_limit": 128000, "reasoning": true, @@ -999,33 +795,32 @@ "modalities": { "input": [ "text", - "image", - "pdf" + "image" ], "output": [ "text" ] }, "cost": { - "input": 1.75, - "output": 14, - "cache_read": 0.175 + "input": 0.75, + "output": 4.5, + "cache_read": 0.075 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 130, + "priority": 50, "default": false, "aliases": [], - "release_date": "2026-02-05", - "last_updated": "2026-02-05", + "release_date": "2026-03-17", + "last_updated": "2026-03-17", "knowledge": "2025-08-31" }, { - "id": "gpt-5.4", - "label": "GPT-5.4", + "id": "gpt-5.5", + "label": "GPT-5.5", "family": "gpt", "context": 400000, "output_limit": 128000, @@ -1057,26 +852,26 @@ ] }, "cost": { - "input": 2.5, - "output": 15, - "cache_read": 0.25 + "input": 5, + "output": 30, + "cache_read": 0.5 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 140, + "priority": 150, "default": false, "aliases": [], - "release_date": "2026-03-05", - "last_updated": "2026-03-05", - "knowledge": "2025-08-31" + "release_date": "2026-04-23", + "last_updated": "2026-04-23", + "knowledge": "2025-12-01" }, { - "id": "gpt-5.4-mini", - "label": "GPT-5.4 mini", - "family": "gpt-mini", + "id": "gpt-5.6-luna", + "label": "GPT-5.6 Luna", + "family": "gpt", "context": 400000, "output_limit": 128000, "reasoning": true, @@ -1099,33 +894,34 @@ "modalities": { "input": [ "text", - "image" + "image", + "pdf" ], "output": [ "text" ] }, "cost": { - "input": 0.75, - "output": 4.5, - "cache_read": 0.075 + "input": 0.2, + "output": 1.2, + "cache_read": 0.02 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 50, + "priority": 152, "default": false, "aliases": [], - "release_date": "2026-03-17", - "last_updated": "2026-03-17", - "knowledge": "2025-08-31" + "release_date": "2026-07-09", + "last_updated": "2026-07-09", + "knowledge": "2026-02-16" }, { - "id": "gpt-5.4-nano", - "label": "GPT-5.4 nano", - "family": "gpt-nano", + "id": "gpt-5.6-sol", + "label": "GPT-5.6 Sol", + "family": "gpt", "context": 400000, "output_limit": 128000, "reasoning": true, @@ -1148,32 +944,33 @@ "modalities": { "input": [ "text", - "image" + "image", + "pdf" ], "output": [ "text" ] }, "cost": { - "input": 0.2, - "output": 1.25, - "cache_read": 0.02 + "input": 4, + "output": 20, + "cache_read": 0.4 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 40, + "priority": 156, "default": false, "aliases": [], - "release_date": "2026-03-17", - "last_updated": "2026-03-17", - "knowledge": "2025-08-31" + "release_date": "2026-07-09", + "last_updated": "2026-07-09", + "knowledge": "2026-02-16" }, { - "id": "gpt-5.5", - "label": "GPT-5.5", + "id": "gpt-5.6-terra", + "label": "GPT-5.6 Terra", "family": "gpt", "context": 400000, "output_limit": 128000, @@ -1205,25 +1002,25 @@ ] }, "cost": { - "input": 5, - "output": 30, - "cache_read": 0.5 + "input": 2, + "output": 12, + "cache_read": 0.2 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 150, + "priority": 154, "default": false, "aliases": [], - "release_date": "2026-04-23", - "last_updated": "2026-04-23", - "knowledge": "2025-12-01" + "release_date": "2026-07-09", + "last_updated": "2026-07-09", + "knowledge": "2026-02-16" }, { - "id": "gpt-5.6-luna", - "label": "GPT-5.6 Luna", + "id": "gpt-6-astra", + "label": "GPT-6 Astra", "family": "gpt", "context": 400000, "output_limit": 128000, @@ -1247,36 +1044,36 @@ "modalities": { "input": [ "text", - "image", - "pdf" + "image" ], "output": [ "text" ] }, "cost": { - "input": 0.2, - "output": 1.2, - "cache_read": 0.02 + "input": 10, + "output": 50, + "cache_read": 1, + "cache_write": 12.5 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 152, + "priority": 158, "default": false, "aliases": [], - "release_date": "2026-07-09", - "last_updated": "2026-07-09", - "knowledge": "2026-02-16" + "release_date": "2026-09-03", + "last_updated": "2026-09-03", + "knowledge": "2026-04-30" }, { - "id": "gpt-5.6-sol", - "label": "GPT-5.6 Sol", - "family": "gpt", - "context": 400000, - "output_limit": 128000, + "id": "grok-4.6", + "label": "Grok 4.6", + "family": "grok", + "context": 500000, + "output_limit": null, "reasoning": true, "supports_effort": true, "effort": { @@ -1292,21 +1089,20 @@ "tool_call": true, "attachment": true, "structured_output": true, - "temperature": false, + "temperature": true, "open_weights": false, "modalities": { "input": [ "text", - "image", - "pdf" + "image" ], "output": [ "text" ] }, "cost": { - "input": 5, - "output": 30, + "input": 2, + "output": 6, "cache_read": 0.5 }, "group": null, @@ -1314,19 +1110,19 @@ "endpoint": null, "hidden": false, "active": true, - "priority": 156, + "priority": 109, "default": false, "aliases": [], - "release_date": "2026-07-09", - "last_updated": "2026-07-09", - "knowledge": "2026-02-16" + "release_date": "2026-08-12", + "last_updated": "2026-08-12", + "knowledge": "2026-02-01" }, { - "id": "gpt-5.6-terra", - "label": "GPT-5.6 Terra", - "family": "gpt", - "context": 400000, - "output_limit": 128000, + "id": "kimi-k3", + "label": "Kimi K3", + "family": "kimi-k3", + "context": 1048576, + "output_limit": null, "reasoning": true, "supports_effort": true, "effort": { @@ -1343,82 +1139,74 @@ "attachment": true, "structured_output": true, "temperature": false, - "open_weights": false, + "open_weights": true, "modalities": { "input": [ "text", "image", - "pdf" + "video" ], "output": [ "text" ] }, "cost": { - "input": 2, - "output": 12, - "cache_read": 0.2 + "input": 3, + "output": 15, + "cache_read": 0.3 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 154, + "priority": 65, "default": false, "aliases": [], - "release_date": "2026-07-09", - "last_updated": "2026-07-09", - "knowledge": "2026-02-16" + "release_date": "2026-07-16", + "last_updated": "2026-07-16", + "knowledge": null }, { - "id": "raptor-mini", - "label": "Raptor mini", - "family": "gpt-mini", - "context": 264000, - "output_limit": 128000, - "reasoning": true, - "supports_effort": true, + "id": "mai-code-1.1-flash", + "label": "MAI-Code-1.1-Flash", + "family": "mai-code", + "context": null, + "output_limit": null, + "reasoning": false, + "supports_effort": false, "effort": { - "kind": "levels", - "levels": [ - "low", - "medium", - "high", - "xhigh" - ], - "default": "medium" + "kind": "none" }, "tool_call": true, - "attachment": true, - "structured_output": true, - "temperature": false, + "attachment": false, + "structured_output": false, + "temperature": true, "open_weights": false, "modalities": { "input": [ - "text", - "image" + "text" ], "output": [ "text" ] }, "cost": { - "input": 0.25, - "output": 2, - "cache_read": 0.025 + "input": 0.2, + "output": 1.2, + "cache_read": 0.02 }, "group": null, - "note": null, + "note": "Code", "endpoint": null, "hidden": false, "active": true, - "priority": 10, + "priority": 12, "default": false, "aliases": [], - "release_date": "2025-08-07", - "last_updated": "2026-06-22", - "knowledge": "2024-05-30" + "release_date": "2026-08-11", + "last_updated": "2026-08-11", + "knowledge": null } ] } diff --git a/dist/providers/grok.json b/dist/providers/grok.json index b4f1e8c..8b23bab 100644 --- a/dist/providers/grok.json +++ b/dist/providers/grok.json @@ -1,7 +1,7 @@ { "schemaVersion": 1, - "generatedAt": "2026-08-01T15:53:14.483Z", - "commit": "4f94308", + "generatedAt": "2026-09-21T11:46:14.774Z", + "commit": "28896da", "provider": { "id": "grok", "name": "xAI", @@ -18,7 +18,7 @@ "id": "grok-4.20-0309-non-reasoning", "label": "Grok 4.20 (Non-Reasoning)", "family": "grok", - "context": 2000000, + "context": 1000000, "output_limit": 30000, "reasoning": false, "supports_effort": false, @@ -33,8 +33,7 @@ "modalities": { "input": [ "text", - "image", - "pdf" + "image" ], "output": [ "text" @@ -61,7 +60,7 @@ "id": "grok-4.20-0309-reasoning", "label": "Grok 4.20 (Reasoning)", "family": "grok", - "context": 2000000, + "context": 1000000, "output_limit": 30000, "reasoning": true, "supports_effort": true, @@ -76,8 +75,7 @@ "modalities": { "input": [ "text", - "image", - "pdf" + "image" ], "output": [ "text" @@ -114,7 +112,8 @@ "none", "low", "medium", - "high" + "high", + "xhigh" ], "default": "low" }, @@ -126,8 +125,7 @@ "modalities": { "input": [ "text", - "image", - "pdf" + "image" ], "output": [ "text" @@ -145,7 +143,9 @@ "active": true, "priority": 30, "default": true, - "aliases": [], + "aliases": [ + "grok-4.3-latest" + ], "release_date": "2026-04-17", "last_updated": "2026-04-17", "knowledge": null @@ -161,12 +161,12 @@ "effort": { "kind": "levels", "levels": [ - "none", "low", "medium", - "high" + "high", + "xhigh" ], - "default": "low" + "default": "high" }, "tool_call": true, "attachment": true, @@ -194,9 +194,106 @@ "active": true, "priority": 40, "default": false, + "aliases": [ + "grok-4.5-latest" + ], + "release_date": "2026-07-08", + "last_updated": "2026-07-08", + "knowledge": null + }, + { + "id": "grok-4.6", + "label": "Grok 4.6", + "family": "grok", + "context": 500000, + "output_limit": null, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "levels", + "levels": [ + "low", + "medium", + "high", + "xhigh" + ], + "default": "high" + }, + "tool_call": true, + "attachment": true, + "structured_output": true, + "temperature": true, + "open_weights": false, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 2, + "output": 6, + "cache_read": 0.5 + }, + "group": null, + "note": "Input/output pricing doubles for prompts at or above 200k tokens.", + "endpoint": null, + "hidden": false, + "active": true, + "priority": 50, + "default": false, "aliases": [], - "release_date": "2026-07-09", - "last_updated": "2026-07-09", + "release_date": "2026-08-12", + "last_updated": "2026-08-12", + "knowledge": "2026-02-01" + }, + { + "id": "grok-build-0.1", + "label": "Grok Build 0.1", + "family": "grok-build", + "context": 256000, + "output_limit": null, + "reasoning": true, + "supports_effort": false, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": true, + "structured_output": true, + "temperature": true, + "open_weights": false, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 1, + "output": 2, + "cache_read": 0.2 + }, + "group": null, + "note": "Code", + "endpoint": null, + "hidden": false, + "active": true, + "priority": 35, + "default": false, + "aliases": [ + "grok-code-fast-1", + "grok-code-fast", + "grok-code-fast-1-0825" + ], + "release_date": "2026-05-19", + "last_updated": "2026-05-19", "knowledge": null } ] diff --git a/dist/providers/kimi-api.json b/dist/providers/kimi-api.json index 01d1d8b..8c60194 100644 --- a/dist/providers/kimi-api.json +++ b/dist/providers/kimi-api.json @@ -1,7 +1,7 @@ { "schemaVersion": 1, - "generatedAt": "2026-08-01T15:53:14.483Z", - "commit": "4f94308", + "generatedAt": "2026-09-21T11:46:14.774Z", + "commit": "28896da", "provider": { "id": "kimi-api", "name": "Kimi (Moonshot)", @@ -15,9 +15,9 @@ "supports_live": true, "models": [ { - "id": "kimi-k2.5", - "label": "Kimi K2.5", - "family": "kimi-k2.5", + "id": "kimi-k2.6", + "label": "Kimi K2.6", + "family": "kimi-k2.6", "context": 262144, "output_limit": 262144, "reasoning": true, @@ -26,7 +26,7 @@ "kind": "none" }, "tool_call": true, - "attachment": false, + "attachment": true, "structured_output": true, "temperature": false, "open_weights": true, @@ -41,28 +41,28 @@ ] }, "cost": { - "input": 0.6, - "output": 3, - "cache_read": 0.1 + "input": 0.95, + "output": 4, + "cache_read": 0.16 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 10, - "default": false, + "priority": 20, + "default": true, "aliases": [], - "release_date": null, - "last_updated": null, + "release_date": "2026-04-21", + "last_updated": "2026-04-21", "knowledge": "2025-01" }, { - "id": "kimi-k2.6", - "label": "Kimi K2.6", - "family": "kimi-k2.6", + "id": "kimi-k2.7-code", + "label": "Kimi K2.7 Code", + "family": "kimi-k2.7", "context": 262144, - "output_limit": 262144, + "output_limit": null, "reasoning": true, "supports_effort": true, "effort": { @@ -71,7 +71,7 @@ "tool_call": true, "attachment": true, "structured_output": true, - "temperature": true, + "temperature": false, "open_weights": true, "modalities": { "input": [ @@ -86,23 +86,23 @@ "cost": { "input": 0.95, "output": 4, - "cache_read": 0.16 + "cache_read": 0.19 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 20, - "default": true, + "priority": 25, + "default": false, "aliases": [], - "release_date": "2026-04-21", - "last_updated": "2026-04-21", - "knowledge": "2025-01" + "release_date": "2026-06-12", + "last_updated": "2026-06-12", + "knowledge": null }, { - "id": "kimi-k2.7-code", - "label": "Kimi K2.7 Code", + "id": "kimi-k2.7-code-highspeed", + "label": "Kimi K2.7 Code HighSpeed", "family": "kimi-k2.7", "context": 262144, "output_limit": null, @@ -114,7 +114,7 @@ "tool_call": true, "attachment": true, "structured_output": true, - "temperature": true, + "temperature": false, "open_weights": true, "modalities": { "input": [ @@ -127,20 +127,18 @@ ] }, "cost": { - "input": 0.95, - "output": 4, - "cache_read": 0.19 + "input": 1.9, + "output": 8, + "cache_read": 0.38 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 25, + "priority": 22, "default": false, - "aliases": [ - "kimi-k2.7-code-highspeed" - ], + "aliases": [], "release_date": null, "last_updated": null, "knowledge": null @@ -150,7 +148,7 @@ "label": "Kimi K3", "family": "kimi-k3", "context": 1048576, - "output_limit": null, + "output_limit": 1048576, "reasoning": true, "supports_effort": true, "effort": { @@ -165,7 +163,7 @@ "tool_call": true, "attachment": true, "structured_output": true, - "temperature": true, + "temperature": false, "open_weights": true, "modalities": { "input": [ diff --git a/dist/providers/kimi-code.json b/dist/providers/kimi-code.json index b8165e6..eb7b65b 100644 --- a/dist/providers/kimi-code.json +++ b/dist/providers/kimi-code.json @@ -1,7 +1,7 @@ { "schemaVersion": 1, - "generatedAt": "2026-08-01T15:53:14.483Z", - "commit": "4f94308", + "generatedAt": "2026-09-21T11:46:14.774Z", + "commit": "28896da", "provider": { "id": "kimi-code", "name": "Kimi Code CLI", @@ -12,49 +12,6 @@ "models_endpoint": null, "supports_live": false, "models": [ - { - "id": "kimi-k2.5", - "label": "Kimi K2.5", - "family": "kimi-k2.5", - "context": 262144, - "output_limit": 262144, - "reasoning": true, - "supports_effort": true, - "effort": { - "kind": "none" - }, - "tool_call": true, - "attachment": false, - "structured_output": true, - "temperature": false, - "open_weights": true, - "modalities": { - "input": [ - "text", - "image", - "video" - ], - "output": [ - "text" - ] - }, - "cost": { - "input": 0.6, - "output": 3, - "cache_read": 0.1 - }, - "group": null, - "note": null, - "endpoint": null, - "hidden": false, - "active": true, - "priority": 10, - "default": false, - "aliases": [], - "release_date": null, - "last_updated": null, - "knowledge": "2025-01" - }, { "id": "kimi-k2.6", "label": "Kimi K2.6", @@ -69,7 +26,7 @@ "tool_call": true, "attachment": true, "structured_output": true, - "temperature": true, + "temperature": false, "open_weights": true, "modalities": { "input": [ @@ -112,7 +69,7 @@ "tool_call": true, "attachment": true, "structured_output": true, - "temperature": true, + "temperature": false, "open_weights": true, "modalities": { "input": [ @@ -136,11 +93,9 @@ "active": true, "priority": 25, "default": false, - "aliases": [ - "kimi-k2.7-code-highspeed" - ], - "release_date": null, - "last_updated": null, + "aliases": [], + "release_date": "2026-06-12", + "last_updated": "2026-06-12", "knowledge": null }, { @@ -148,7 +103,7 @@ "label": "Kimi K3", "family": "kimi-k3", "context": 1048576, - "output_limit": null, + "output_limit": 1048576, "reasoning": true, "supports_effort": true, "effort": { @@ -163,7 +118,7 @@ "tool_call": true, "attachment": true, "structured_output": true, - "temperature": true, + "temperature": false, "open_weights": true, "modalities": { "input": [ diff --git a/dist/providers/mistral.json b/dist/providers/mistral.json index d59d155..51f47f9 100644 --- a/dist/providers/mistral.json +++ b/dist/providers/mistral.json @@ -1,7 +1,7 @@ { "schemaVersion": 1, - "generatedAt": "2026-08-01T15:53:14.483Z", - "commit": "4f94308", + "generatedAt": "2026-09-21T11:46:14.774Z", + "commit": "28896da", "provider": { "id": "mistral", "name": "Mistral", @@ -18,7 +18,7 @@ "id": "codestral", "label": "Codestral", "family": "codestral", - "context": 256000, + "context": 131072, "output_limit": 4096, "reasoning": false, "supports_effort": false, @@ -29,7 +29,7 @@ "attachment": false, "structured_output": true, "temperature": true, - "open_weights": true, + "open_weights": false, "modalities": { "input": [ "text" @@ -40,7 +40,8 @@ }, "cost": { "input": 0.3, - "output": 0.9 + "output": 0.9, + "cache_read": 0.03 }, "group": null, "note": "Code", @@ -50,15 +51,16 @@ "priority": 10, "default": false, "aliases": [ - "codestral-latest" + "codestral-latest", + "codestral-2508" ], - "release_date": "2024-05-29", - "last_updated": "2025-01-04", - "knowledge": "2024-10" + "release_date": "2025-07-30", + "last_updated": "2025-07-30", + "knowledge": null }, { "id": "mistral-large", - "label": "Mistral Large", + "label": "Mistral Large 3", "family": "mistral-large", "context": 262144, "output_limit": 262144, @@ -83,7 +85,8 @@ }, "cost": { "input": 0.5, - "output": 1.5 + "output": 1.5, + "cache_read": 0.05 }, "group": null, "note": null, @@ -94,11 +97,11 @@ "default": true, "aliases": [ "mistral-large-latest", - "mistral-large-2411" + "mistral-large-2512" ], - "release_date": "2024-11-01", + "release_date": "2025-12-02", "last_updated": "2025-12-02", - "knowledge": "2024-11" + "knowledge": null }, { "id": "mistral-medium", @@ -109,7 +112,16 @@ "reasoning": true, "supports_effort": true, "effort": { - "kind": "none" + "kind": "levels", + "levels": [ + "none", + "minimal", + "low", + "medium", + "high", + "xhigh" + ], + "default": "high" }, "tool_call": true, "attachment": true, @@ -127,7 +139,8 @@ }, "cost": { "input": 1.5, - "output": 7.5 + "output": 7.5, + "cache_read": 0.15 }, "group": null, "note": null, @@ -138,7 +151,8 @@ "default": false, "aliases": [ "mistral-medium-latest", - "mistral-medium-3-5-26-04" + "mistral-medium-3-5", + "mistral-medium-3" ], "release_date": "2026-04-28", "last_updated": "2026-04-28", @@ -153,16 +167,26 @@ "reasoning": true, "supports_effort": true, "effort": { - "kind": "none" + "kind": "levels", + "levels": [ + "none", + "minimal", + "low", + "medium", + "high", + "xhigh" + ], + "default": "high" }, "tool_call": true, - "attachment": false, + "attachment": true, "structured_output": true, "temperature": true, "open_weights": true, "modalities": { "input": [ - "text" + "text", + "image" ], "output": [ "text" @@ -170,7 +194,8 @@ }, "cost": { "input": 0.15, - "output": 0.6 + "output": 0.6, + "cache_read": 0.015 }, "group": null, "note": null, @@ -186,6 +211,50 @@ "release_date": "2026-03-16", "last_updated": "2026-03-16", "knowledge": null + }, + { + "id": "zai-glm-5-3", + "label": "GLM 5.3", + "family": "glm", + "context": 1048576, + "output_limit": 131072, + "reasoning": true, + "supports_effort": false, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": false, + "structured_output": true, + "temperature": true, + "open_weights": true, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 1.4, + "output": 4.4, + "cache_read": 0.14 + }, + "group": null, + "note": "Code", + "endpoint": null, + "hidden": false, + "active": true, + "priority": 25, + "default": false, + "aliases": [ + "zai-glm-5", + "zai-glm-latest" + ], + "release_date": "2026-09-15", + "last_updated": "2026-09-15", + "knowledge": null } ] } diff --git a/dist/providers/nvidia-nim.json b/dist/providers/nvidia-nim.json index 800ce2b..a8a4b29 100644 --- a/dist/providers/nvidia-nim.json +++ b/dist/providers/nvidia-nim.json @@ -1,7 +1,7 @@ { "schemaVersion": 1, - "generatedAt": "2026-08-01T15:53:14.483Z", - "commit": "4f94308", + "generatedAt": "2026-09-21T11:46:14.774Z", + "commit": "28896da", "provider": { "id": "nvidia-nim", "name": "NVIDIA NIM", @@ -15,13 +15,13 @@ "supports_live": true, "models": [ { - "id": "deepseek-ai/deepseek-v4-flash", - "label": "DeepSeek V4 Flash", - "family": "deepseek-flash", - "context": 1048576, - "output_limit": 393216, - "reasoning": true, - "supports_effort": true, + "id": "mistralai/mistral-nemotron", + "label": "mistral-nemotron", + "family": null, + "context": 128000, + "output_limit": 8192, + "reasoning": false, + "supports_effort": false, "effort": { "kind": "none" }, @@ -39,73 +39,79 @@ ] }, "cost": { - "input": 0.14, - "output": 0.28, - "cache_read": 0.0028 + "input": 0, + "output": 0 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 60, + "priority": 10, "default": false, "aliases": [], - "release_date": "2026-04-24", - "last_updated": "2026-04-24", - "knowledge": "2025-05" + "release_date": "2025-06-11", + "last_updated": "2025-06-12", + "knowledge": null }, { - "id": "deepseek-ai/deepseek-v4-pro", - "label": "DeepSeek V4 Pro", - "family": "deepseek-thinking", - "context": 1048576, - "output_limit": 393216, + "id": "moonshotai/kimi-k2.6", + "label": "Kimi K2.6", + "family": "kimi-k2.6", + "context": 262144, + "output_limit": 262144, "reasoning": true, "supports_effort": true, "effort": { "kind": "none" }, "tool_call": true, - "attachment": false, + "attachment": true, "structured_output": true, "temperature": true, "open_weights": true, "modalities": { "input": [ - "text" + "text", + "image", + "video" ], "output": [ "text" ] }, "cost": { - "input": 0.435, - "output": 0.87, - "cache_read": 0.003625 + "input": 0, + "output": 0 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 70, + "priority": 50, "default": false, "aliases": [], - "release_date": "2026-04-24", - "last_updated": "2026-04-24", - "knowledge": "2025-05" + "release_date": "2026-04-21", + "last_updated": "2026-04-21", + "knowledge": "2025-01" }, { - "id": "meta/llama-4-maverick-17b-128e-instruct", - "label": "Llama 4 Maverick 17b 128e Instruct", - "family": null, - "context": 128000, - "output_limit": 4096, - "reasoning": false, - "supports_effort": false, + "id": "moonshotai/kimi-k3", + "label": "Kimi K3", + "family": "kimi-k3", + "context": 1048576, + "output_limit": 65536, + "reasoning": true, + "supports_effort": true, "effort": { - "kind": "none" + "kind": "levels", + "levels": [ + "low", + "high", + "max" + ], + "default": "high" }, "tool_call": true, "attachment": true, @@ -130,19 +136,19 @@ "endpoint": null, "hidden": false, "active": true, - "priority": 40, + "priority": 98, "default": false, "aliases": [], - "release_date": "2025-04-01", - "last_updated": "2025-04-01", - "knowledge": "2024-02" + "release_date": "2026-07-16", + "last_updated": "2026-07-16", + "knowledge": null }, { - "id": "minimaxai/minimax-m2.7", - "label": "MiniMax-M2.7", - "family": "minimax", - "context": 204800, - "output_limit": 131072, + "id": "nvidia/nemotron-3-super-120b-a12b", + "label": "Nemotron 3 Super", + "family": "nemotron", + "context": 1048576, + "output_limit": 262144, "reasoning": true, "supports_effort": true, "effort": { @@ -162,29 +168,29 @@ ] }, "cost": { - "input": 0, - "output": 0 + "input": 0.2, + "output": 0.8 }, "group": null, "note": null, "endpoint": null, "hidden": false, "active": true, - "priority": 80, - "default": false, + "priority": 100, + "default": true, "aliases": [], - "release_date": "2026-03-18", - "last_updated": "2026-04-11", - "knowledge": null + "release_date": "2026-03-11", + "last_updated": "2026-03-11", + "knowledge": "2024-04" }, { - "id": "mistralai/mistral-nemotron", - "label": "mistral-nemotron", - "family": null, - "context": 128000, - "output_limit": 8192, - "reasoning": false, - "supports_effort": false, + "id": "nvidia/nemotron-3-ultra-550b-a55b", + "label": "Nemotron 3 Ultra", + "family": "nemotron", + "context": 1048576, + "output_limit": null, + "reasoning": true, + "supports_effort": true, "effort": { "kind": "none" }, @@ -210,34 +216,32 @@ "endpoint": null, "hidden": false, "active": true, - "priority": 10, + "priority": 94, "default": false, "aliases": [], - "release_date": "2025-06-11", - "last_updated": "2025-06-12", + "release_date": "2026-06-04", + "last_updated": "2026-06-04", "knowledge": null }, { - "id": "moonshotai/kimi-k2.6", - "label": "Kimi K2.6", - "family": "kimi-k2.6", - "context": 262144, - "output_limit": 262144, + "id": "nvidia/nemotron-3.5-lightning-30b-a3b", + "label": "Nemotron 3.5 Lightning", + "family": "nemotron", + "context": 1048576, + "output_limit": null, "reasoning": true, "supports_effort": true, "effort": { "kind": "none" }, "tool_call": true, - "attachment": true, + "attachment": false, "structured_output": true, "temperature": true, "open_weights": true, "modalities": { "input": [ - "text", - "image", - "video" + "text" ], "output": [ "text" @@ -252,21 +256,21 @@ "endpoint": null, "hidden": false, "active": true, - "priority": 50, + "priority": 86, "default": false, "aliases": [], - "release_date": "2026-04-21", - "last_updated": "2026-04-21", - "knowledge": "2025-01" + "release_date": "2026-08-11", + "last_updated": "2026-08-11", + "knowledge": null }, { - "id": "nvidia/nemotron-3-super-120b-a12b", - "label": "Nemotron 3 Super", - "family": "nemotron", - "context": 262144, - "output_limit": 262144, + "id": "openai/gpt-oss-20b", + "label": "GPT OSS 20B", + "family": "gpt-oss", + "context": 131072, + "output_limit": 32768, "reasoning": true, - "supports_effort": true, + "supports_effort": false, "effort": { "kind": "none" }, @@ -283,46 +287,6 @@ "text" ] }, - "cost": { - "input": 0.2, - "output": 0.8 - }, - "group": null, - "note": null, - "endpoint": null, - "hidden": false, - "active": true, - "priority": 100, - "default": true, - "aliases": [], - "release_date": "2026-03-11", - "last_updated": "2026-03-11", - "knowledge": "2024-04" - }, - { - "id": "openai/gpt-oss-120b", - "label": "GPT-OSS-120B", - "family": "gpt-oss", - "context": 128000, - "output_limit": 8192, - "reasoning": true, - "supports_effort": true, - "effort": { - "kind": "none" - }, - "tool_call": false, - "attachment": true, - "structured_output": false, - "temperature": true, - "open_weights": false, - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, "cost": { "input": 0, "output": 0 @@ -332,21 +296,21 @@ "endpoint": null, "hidden": false, "active": true, - "priority": 30, + "priority": 20, "default": false, "aliases": [], - "release_date": "2025-08-04", - "last_updated": "2025-08-14", - "knowledge": "2025-08" + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "knowledge": null }, { - "id": "openai/gpt-oss-20b", - "label": "GPT OSS 20B", - "family": "gpt-oss", - "context": 131072, - "output_limit": 32768, + "id": "z-ai/glm-5.3", + "label": "GLM 5.3", + "family": "glm", + "context": 1048576, + "output_limit": null, "reasoning": true, - "supports_effort": false, + "supports_effort": true, "effort": { "kind": "none" }, @@ -372,32 +336,33 @@ "endpoint": null, "hidden": false, "active": true, - "priority": 20, + "priority": 96, "default": false, "aliases": [], - "release_date": "2025-08-05", - "last_updated": "2025-08-05", + "release_date": "2026-08-18", + "last_updated": "2026-08-18", "knowledge": null }, { - "id": "z-ai/glm-5.1", - "label": "GLM-5.1", - "family": "glm", - "context": 131072, - "output_limit": 131072, + "id": "z-ai/glm-5.3-flash", + "label": "GLM 5.3 Flash", + "family": "glm-flash", + "context": 1048576, + "output_limit": null, "reasoning": true, "supports_effort": true, "effort": { "kind": "none" }, "tool_call": true, - "attachment": false, + "attachment": true, "structured_output": true, "temperature": true, "open_weights": true, "modalities": { "input": [ - "text" + "text", + "image" ], "output": [ "text" @@ -412,11 +377,11 @@ "endpoint": null, "hidden": false, "active": true, - "priority": 90, + "priority": 88, "default": false, "aliases": [], - "release_date": "2026-03-27", - "last_updated": "2026-03-27", + "release_date": "2026-08-25", + "last_updated": "2026-08-25", "knowledge": null } ] diff --git a/dist/providers/openai.json b/dist/providers/openai.json index 56d1709..a084b1d 100644 --- a/dist/providers/openai.json +++ b/dist/providers/openai.json @@ -1,7 +1,7 @@ { "schemaVersion": 1, - "generatedAt": "2026-08-01T15:53:14.483Z", - "commit": "4f94308", + "generatedAt": "2026-09-21T11:46:14.774Z", + "commit": "28896da", "provider": { "id": "openai", "name": "OpenAI", @@ -166,10 +166,11 @@ "effort": { "kind": "levels", "levels": [ - "minimal", + "none", "low", "medium", - "high" + "high", + "xhigh" ], "default": "medium" }, @@ -216,10 +217,11 @@ "effort": { "kind": "levels", "levels": [ - "minimal", + "none", "low", "medium", - "high" + "high", + "xhigh" ], "default": "medium" }, @@ -265,10 +267,11 @@ "effort": { "kind": "levels", "levels": [ - "minimal", + "none", "low", "medium", - "high" + "high", + "xhigh" ], "default": "medium" }, @@ -314,10 +317,11 @@ "effort": { "kind": "levels", "levels": [ - "minimal", + "none", "low", "medium", - "high" + "high", + "xhigh" ], "default": "medium" }, @@ -441,12 +445,12 @@ ] }, "cost": { - "input": 5, - "output": 30, - "cache_read": 0.5 + "input": 4, + "output": 20, + "cache_read": 0.4 }, "group": null, - "note": null, + "note": "Promotional pricing, guaranteed through 2026-11-21 (was $5 / $30).", "endpoint": null, "hidden": false, "active": true, @@ -456,7 +460,7 @@ "gpt-5.6" ], "release_date": "2026-07-09", - "last_updated": "2026-07-09", + "last_updated": "2026-08-21", "knowledge": "2026-02-16" }, { diff --git a/dist/providers/openrouter.json b/dist/providers/openrouter.json index 022eace..ae71326 100644 --- a/dist/providers/openrouter.json +++ b/dist/providers/openrouter.json @@ -1,7 +1,7 @@ { "schemaVersion": 1, - "generatedAt": "2026-08-01T15:53:14.483Z", - "commit": "4f94308", + "generatedAt": "2026-09-21T11:46:14.774Z", + "commit": "28896da", "provider": { "id": "openrouter", "name": "OpenRouter", @@ -14,6 +14,50 @@ "models_endpoint": "/models", "supports_live": true, "models": [ + { + "id": "anthropic/claude-fable-5.1", + "label": "Claude Fable 5.1", + "family": "claude-fable", + "context": 1000000, + "output_limit": 128000, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": true, + "structured_output": true, + "temperature": false, + "open_weights": false, + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 10, + "output": 50, + "cache_read": 0.25, + "cache_write": 12.5 + }, + "group": "via OpenRouter", + "note": null, + "endpoint": null, + "hidden": false, + "active": true, + "priority": 108, + "default": false, + "aliases": [], + "release_date": "2026-09-01", + "last_updated": "2026-09-01", + "knowledge": "2026-06" + }, { "id": "anthropic/claude-opus-4.8", "label": "Claude Opus 4.8", @@ -173,10 +217,10 @@ ] }, "cost": { - "input": 3, - "output": 15, - "cache_read": 0.3, - "cache_write": 3.75 + "input": 2, + "output": 10, + "cache_read": 0.2, + "cache_write": 2.5 }, "group": "via OpenRouter", "note": null, @@ -215,9 +259,9 @@ ] }, "cost": { - "input": 0.435, - "output": 0.87, - "cache_read": 0.003625 + "input": 0.9553, + "output": 1.9105, + "cache_read": 0.0796 }, "group": "via OpenRouter", "note": null, @@ -231,6 +275,48 @@ "last_updated": "2026-04-24", "knowledge": "2025-05" }, + { + "id": "deepseek/deepseek-v4.1-flash", + "label": "DeepSeek V4.1 Flash", + "family": "deepseek-flash", + "context": 1048576, + "output_limit": 384000, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": true, + "structured_output": true, + "temperature": true, + "open_weights": true, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 0.15, + "output": 0.6, + "cache_read": 0.003 + }, + "group": "via OpenRouter", + "note": null, + "endpoint": null, + "hidden": false, + "active": true, + "priority": 35, + "default": false, + "aliases": [], + "release_date": "2026-09-10", + "last_updated": "2026-09-10", + "knowledge": null + }, { "id": "google/gemini-3.1-pro-preview", "label": "Gemini 3.1 Pro Preview", @@ -352,9 +438,9 @@ ] }, "cost": { - "input": 1.5, - "output": 7.5, - "cache_read": 0.15 + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 }, "group": "via OpenRouter", "note": null, @@ -368,6 +454,51 @@ "last_updated": "2026-07-21", "knowledge": "2026-03" }, + { + "id": "google/gemini-3.8-flash", + "label": "Gemini 3.8 Flash", + "family": "gemini-flash", + "context": 1048576, + "output_limit": 65536, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": true, + "structured_output": true, + "temperature": true, + "open_weights": false, + "modalities": { + "input": [ + "text", + "image", + "video", + "pdf", + "audio" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 + }, + "group": "via OpenRouter", + "note": null, + "endpoint": null, + "hidden": false, + "active": true, + "priority": 58, + "default": false, + "aliases": [], + "release_date": "2026-09-02", + "last_updated": "2026-09-02", + "knowledge": "2026-03" + }, { "id": "moonshotai/kimi-k2.6", "label": "Kimi K2.6", @@ -394,9 +525,9 @@ ] }, "cost": { - "input": 0.684, - "output": 3.42, - "cache_read": 0.144 + "input": 0.95, + "output": 4, + "cache_read": 0.16 }, "group": "via OpenRouter", "note": null, @@ -437,9 +568,9 @@ ] }, "cost": { - "input": 3, - "output": 15, - "cache_read": 0.3 + "input": 1.7, + "output": 8.5, + "cache_read": 0.17 }, "group": "via OpenRouter", "note": null, @@ -566,9 +697,9 @@ ] }, "cost": { - "input": 5, - "output": 30, - "cache_read": 0.5 + "input": 2, + "output": 10, + "cache_read": 0.2 }, "group": "via OpenRouter", "note": null, @@ -582,6 +713,50 @@ "last_updated": "2026-07-09", "knowledge": "2026-02-16" }, + { + "id": "openai/gpt-6-astra", + "label": "GPT-6 Astra", + "family": "gpt", + "context": 1050000, + "output_limit": 128000, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": true, + "structured_output": true, + "temperature": false, + "open_weights": false, + "modalities": { + "input": [ + "pdf", + "image", + "text" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 10, + "output": 50, + "cache_read": 1, + "cache_write": 12.5 + }, + "group": "via OpenRouter", + "note": null, + "endpoint": null, + "hidden": false, + "active": true, + "priority": 88, + "default": false, + "aliases": [], + "release_date": "2026-09-03", + "last_updated": "2026-09-03", + "knowledge": "2026-04-30" + }, { "id": "x-ai/grok-4.3", "label": "Grok 4.3", @@ -666,6 +841,49 @@ "last_updated": "2026-07-09", "knowledge": null }, + { + "id": "x-ai/grok-4.6", + "label": "Grok 4.6", + "family": "grok", + "context": 500000, + "output_limit": 450000, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": true, + "structured_output": true, + "temperature": true, + "open_weights": false, + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 2, + "output": 6, + "cache_read": 0.5 + }, + "group": "via OpenRouter", + "note": null, + "endpoint": null, + "hidden": false, + "active": true, + "priority": 48, + "default": false, + "aliases": [], + "release_date": "2026-08-12", + "last_updated": "2026-08-12", + "knowledge": "2026-02-01" + }, { "id": "z-ai/glm-4.7", "label": "GLM-4.7", @@ -706,6 +924,47 @@ "release_date": "2025-12-22", "last_updated": "2025-12-22", "knowledge": "2025-04" + }, + { + "id": "z-ai/glm-5.3", + "label": "GLM 5.3", + "family": "glm", + "context": 1310720, + "output_limit": 131072, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": false, + "structured_output": true, + "temperature": true, + "open_weights": true, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 0.91, + "output": 2.86, + "cache_read": 0.169 + }, + "group": "via OpenRouter", + "note": null, + "endpoint": null, + "hidden": false, + "active": true, + "priority": 15, + "default": false, + "aliases": [], + "release_date": "2026-08-18", + "last_updated": "2026-08-18", + "knowledge": null } ] } diff --git a/dist/providers/perplexity.json b/dist/providers/perplexity.json index 57593c1..d810cd1 100644 --- a/dist/providers/perplexity.json +++ b/dist/providers/perplexity.json @@ -1,7 +1,7 @@ { "schemaVersion": 1, - "generatedAt": "2026-08-01T15:53:14.483Z", - "commit": "4f94308", + "generatedAt": "2026-09-21T11:46:14.774Z", + "commit": "28896da", "provider": { "id": "perplexity", "name": "Perplexity", @@ -14,6 +14,49 @@ "models_endpoint": null, "supports_live": false, "models": [ + { + "id": "anthropic/claude-fable-5", + "label": "Claude Fable 5", + "family": "claude-fable", + "context": 1000000, + "output_limit": 128000, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": true, + "structured_output": true, + "temperature": false, + "open_weights": false, + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 10, + "output": 50, + "cache_read": 1 + }, + "group": "Agent API", + "note": null, + "endpoint": "/v1/agent", + "hidden": false, + "active": true, + "priority": 186, + "default": false, + "aliases": [], + "release_date": "2026-06-09", + "last_updated": "2026-06-09", + "knowledge": "2026-01" + }, { "id": "anthropic/claude-haiku-4-5", "label": "Claude Haiku 4.5", @@ -385,12 +428,12 @@ ] }, "cost": { - "input": 3, - "output": 15, - "cache_read": 0.3 + "input": 2, + "output": 10, + "cache_read": 0.2 }, "group": "Agent API", - "note": "Introductory pricing of $2 / $10 per MTok applies through 2026-08-31.", + "note": null, "endpoint": "/v1/agent", "hidden": false, "active": true, @@ -402,8 +445,8 @@ "knowledge": "2026-01" }, { - "id": "google/gemini-2.5-flash", - "label": "Gemini 2.5 Flash", + "id": "google/gemini-3-flash-preview", + "label": "Gemini 3 Flash Preview", "family": "gemini-flash", "context": 1048576, "output_limit": 65536, @@ -421,8 +464,8 @@ "input": [ "text", "image", - "audio", "video", + "audio", "pdf" ], "output": [ @@ -430,25 +473,25 @@ ] }, "cost": { - "input": 0.3, - "output": 2.5, - "cache_read": 0.03 + "input": 0.5, + "output": 3, + "cache_read": 0.05 }, "group": "Agent API", "note": null, "endpoint": "/v1/agent", "hidden": false, "active": true, - "priority": 40, + "priority": 60, "default": false, "aliases": [], - "release_date": "2025-03-20", - "last_updated": "2025-06-05", + "release_date": "2025-12-17", + "last_updated": "2025-12-17", "knowledge": "2025-01" }, { - "id": "google/gemini-2.5-pro", - "label": "Gemini 2.5 Pro", + "id": "google/gemini-3.1-pro-preview", + "label": "Gemini 3.1 Pro Preview", "family": "gemini-pro", "context": 1048576, "output_limit": 65536, @@ -466,8 +509,8 @@ "input": [ "text", "image", - "audio", "video", + "audio", "pdf" ], "output": [ @@ -475,25 +518,25 @@ ] }, "cost": { - "input": 1.25, - "output": 10, - "cache_read": 0.125 + "input": 2, + "output": 12, + "cache_read": 0.2 }, "group": "Agent API", "note": null, "endpoint": "/v1/agent", "hidden": false, "active": true, - "priority": 50, + "priority": 70, "default": false, "aliases": [], - "release_date": "2025-03-20", - "last_updated": "2025-06-05", + "release_date": "2026-02-19", + "last_updated": "2026-02-19", "knowledge": "2025-01" }, { - "id": "google/gemini-3-flash-preview", - "label": "Gemini 3 Flash Preview", + "id": "google/gemini-3.5-flash", + "label": "Gemini 3.5 Flash", "family": "gemini-flash", "context": 1048576, "output_limit": 65536, @@ -520,26 +563,26 @@ ] }, "cost": { - "input": 0.5, - "output": 3, - "cache_read": 0.05 + "input": 1.5, + "output": 9, + "cache_read": 0.15 }, "group": "Agent API", "note": null, "endpoint": "/v1/agent", "hidden": false, "active": true, - "priority": 60, + "priority": 65, "default": false, "aliases": [], - "release_date": "2025-12-17", - "last_updated": "2025-12-17", + "release_date": "2026-05-19", + "last_updated": "2026-05-19", "knowledge": "2025-01" }, { - "id": "google/gemini-3.1-pro-preview", - "label": "Gemini 3.1 Pro Preview", - "family": "gemini-pro", + "id": "google/gemini-3.6-flash", + "label": "Gemini 3.6 Flash", + "family": "gemini-flash", "context": 1048576, "output_limit": 65536, "reasoning": true, @@ -565,25 +608,25 @@ ] }, "cost": { - "input": 2, - "output": 12, - "cache_read": 0.2 + "input": 1.5, + "output": 7.5, + "cache_read": 0.15 }, "group": "Agent API", "note": null, "endpoint": "/v1/agent", "hidden": false, "active": true, - "priority": 70, + "priority": 74, "default": false, "aliases": [], - "release_date": "2026-02-19", - "last_updated": "2026-02-19", - "knowledge": "2025-01" + "release_date": "2026-07-21", + "last_updated": "2026-07-21", + "knowledge": "2026-03" }, { - "id": "google/gemini-3.5-flash", - "label": "Gemini 3.5 Flash", + "id": "google/gemini-3.8-flash", + "label": "Gemini 3.8 Flash", "family": "gemini-flash", "context": 1048576, "output_limit": 65536, @@ -610,61 +653,21 @@ ] }, "cost": { - "input": 1.5, - "output": 9, - "cache_read": 0.15 + "input": 0.75, + "output": 3.75, + "cache_read": 0.075 }, "group": "Agent API", "note": null, "endpoint": "/v1/agent", "hidden": false, "active": true, - "priority": 65, + "priority": 78, "default": false, "aliases": [], - "release_date": "2026-05-19", - "last_updated": "2026-05-19", - "knowledge": "2025-01" - }, - { - "id": "nvidia/nemotron-3-super-120b-a12b", - "label": "Nemotron 3 Super 120B", - "family": "nemotron", - "context": 1000000, - "output_limit": 32000, - "reasoning": true, - "supports_effort": true, - "effort": { - "kind": "none" - }, - "tool_call": true, - "attachment": false, - "structured_output": true, - "temperature": true, - "open_weights": true, - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "cost": { - "input": 0.25, - "output": 2.5 - }, - "group": "Agent API", - "note": null, - "endpoint": "/v1/agent", - "hidden": false, - "active": true, - "priority": 30, - "default": false, - "aliases": [], - "release_date": "2026-03-11", - "last_updated": "2026-03-11", - "knowledge": "2026-02" + "release_date": "2026-09-02", + "last_updated": "2026-09-02", + "knowledge": "2026-03" }, { "id": "openai/gpt-5-mini", @@ -1006,6 +1009,131 @@ "last_updated": "2026-07-09", "knowledge": "2026-02-16" }, + { + "id": "perplexity/glm-5.3", + "label": "GLM 5.3", + "family": "glm", + "context": 1048576, + "output_limit": 131072, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": false, + "structured_output": true, + "temperature": true, + "open_weights": true, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 1.4, + "output": 4.4, + "cache_read": 0.26 + }, + "group": "Agent API", + "note": null, + "endpoint": "/v1/agent", + "hidden": false, + "active": true, + "priority": 33, + "default": false, + "aliases": [], + "release_date": "2026-08-18", + "last_updated": "2026-08-18", + "knowledge": null + }, + { + "id": "perplexity/kimi-k3", + "label": "Kimi K3", + "family": "kimi-k3", + "context": 1048576, + "output_limit": null, + "reasoning": true, + "supports_effort": true, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": true, + "structured_output": true, + "temperature": false, + "open_weights": true, + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 3, + "output": 15, + "cache_read": 0.3 + }, + "group": "Agent API", + "note": null, + "endpoint": "/v1/agent", + "hidden": false, + "active": true, + "priority": 35, + "default": false, + "aliases": [], + "release_date": "2026-07-16", + "last_updated": "2026-07-16", + "knowledge": null + }, + { + "id": "perplexity/nemotron-3-ultra-550b-a55b", + "label": "Nemotron 3 Ultra", + "family": "nemotron", + "context": null, + "output_limit": null, + "reasoning": false, + "supports_effort": false, + "effort": { + "kind": "none" + }, + "tool_call": true, + "attachment": false, + "structured_output": false, + "temperature": true, + "open_weights": true, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "cost": { + "input": 0.25, + "output": 2.5, + "cache_read": 0.25 + }, + "group": "Agent API", + "note": null, + "endpoint": "/v1/agent", + "hidden": false, + "active": true, + "priority": 31, + "default": false, + "aliases": [], + "release_date": null, + "last_updated": null, + "knowledge": null + }, { "id": "perplexity/sonar", "label": "Sonar", @@ -1216,13 +1344,13 @@ "knowledge": "2025-09-01" }, { - "id": "xai/grok-4-1-fast-non-reasoning", - "label": "Grok 4.1 Fast (Non-Reasoning)", + "id": "xai/grok-4.5", + "label": "Grok 4.5", "family": "grok", - "context": 2000000, + "context": 500000, "output_limit": 30000, - "reasoning": false, - "supports_effort": false, + "reasoning": true, + "supports_effort": true, "effort": { "kind": "none" }, @@ -1241,28 +1369,28 @@ ] }, "cost": { - "input": 0.2, - "output": 0.5, - "cache_read": 0.05 + "input": 2, + "output": 6, + "cache_read": 0.3 }, "group": "Agent API", "note": null, "endpoint": "/v1/agent", "hidden": false, "active": true, - "priority": 20, + "priority": 25, "default": false, "aliases": [], - "release_date": "2025-11-19", - "last_updated": "2025-11-19", - "knowledge": "2025-07" + "release_date": "2026-07-09", + "last_updated": "2026-07-09", + "knowledge": null }, { - "id": "xai/grok-4.5", - "label": "Grok 4.5", + "id": "xai/grok-4.6", + "label": "Grok 4.6", "family": "grok", "context": 500000, - "output_limit": 30000, + "output_limit": null, "reasoning": true, "supports_effort": true, "effort": { @@ -1285,19 +1413,19 @@ "cost": { "input": 2, "output": 6, - "cache_read": 0.3 + "cache_read": 0.5 }, "group": "Agent API", - "note": null, + "note": "Input/output pricing doubles for prompts above 200k tokens.", "endpoint": "/v1/agent", "hidden": false, "active": true, - "priority": 25, + "priority": 28, "default": false, "aliases": [], - "release_date": "2026-07-09", - "last_updated": "2026-07-09", - "knowledge": null + "release_date": "2026-08-12", + "last_updated": "2026-08-12", + "knowledge": "2026-02-01" } ] }