134+ free LLM APIs & AI API keys from 40+ providers. Google Gemini, NVIDIA NIM, Groq, OpenRouter & more. One-click setup for Claude Code, Cursor and Codex.
-
Updated
Nov 16, 2026
134+ free LLM APIs & AI API keys from 40+ providers. Google Gemini, NVIDIA NIM, Groq, OpenRouter & more. One-click setup for Claude Code, Cursor and Codex.
Chasing a free LLM API? Here is how routers like OpenRouter price models, how to sort for the cheapest options, and what to do when your models are not text.
Run Claude Code through FreeLLMAPI + LiteLLM with Anthropic compatibility, Windows setup guides, troubleshooting, validation tests, and community-driven fixes.
A source-linked directory of free and trial LLM APIs, multimodal models, embeddings, speech, translation, safety, and other inference endpoints. Companion catalog for freellmapi.io.
FreeAIGateway One gateway, two protocols, sixteen providers — zero cost. FreeAIGateway — An OpenAI & Anthropic compatible proxy that aggregates free tiers from 16+ LLM providers (~1.7B tokens/month) behind a single /v1 endpoint and a Claude-compatible endpoint. Smart routing, automatic failover, encrypted key storage. For personal experimentation
Free-first, model-adaptive coding agent runtime that makes local small LLMs work reliably with harness, checkpointing, verification, cache-aware context, and free-model fallback.
Free agentic AI coding assistant for VS Code. Multiplexes many free-tier LLM providers into one self-healing surface — auto-routes, auto-fails-over, learns your codebase. Zero setup with keyless providers; bring your own keys anytime.
project for web to api with emulated tool calling.
An interactive CLI tool to dynamically patch and add custom OpenAI-compatible providers to FreeLLMAPI.
FreeLLMAPI as a self-contained DeepSeek Harness plugin: the local free-model router ships inside the plugin, so one install gives you a first-class model provider route plus start/stop control — no Docker, no separate checkout.
FreeDSH — free-first multi-model routing, safe core updates and pt-BR/Windows support for DeepSeek Harness. Installable as a DSH bundle (dsh plugin add). Unofficial project.
FreeLLMAPI (Auto) provider route for DeepSeek Harness: pick the auto model and a local FreeLLMAPI gateway chooses the best free model, fails over automatically, and streams back as native DSH chunks.
7.4 billion tokens per month. 34 free LLM providers. 635 free model endpoints. All behind one /v1 endpoint, plus any custom OpenAI-compatible endpoint. Smart routing, automatic failover, encrypted keys. Personal experimentation only.
免费大模型/AI算力实战手册 · 18 篇连载正文,可长期更新的活文档(额度时效、聚合代理、限速应对、合规红线)
Claude Code MCP server + skill that offloads cheap, bulk subtasks to free local LLMs via a self-hosted freellmapi router. Save your Opus/Sonnet tokens.
It acts as a routing layer, ensuring that incoming requests are distributed across all available and working LLMs. This project intelligently routes each subsequent request to the next available model, maximizing resource utilization and providing a robust, fault-tolerant system for LLM-powered applications.
Evidence-bound outbound request policy for FreeLLMAPI: reproducible offline demo, scoped upstream contribution, and validation evidence.
Read-only Omarchy bar widget for a local FreeLLMAPI gateway: health, providers, chat/Fusion, media lanes, quota
To associate your repository with the freellmapi topic, visit your repo's landing page and select "manage topics."