A unified API gateway aggregating 34 free LLM providers and 635 free model endpoints, offering approximately 7.4 billion free tokens per month with smart routing, automatic failover, and encrypted key storage.
- v0.16.28
- Published at
- 7h ago
- 51,654
- Stars
- 89,805
- Download
- Synced at
- 10m ago
Latest release
v0.16.28Nov 13, 2026, 10:16 AMDownloads slow? Switch the source anytime above
README
Project Overview
FreeLLMAPI is a unified API gateway that aggregates 34 free LLM providers and 635 free model endpoints, offering approximately 7.4 billion free tokens per month. It provides a single OpenAI-compatible /v1 endpoint and supports custom OpenAI-compatible chat, embedding, image, and audio endpoints.
Key Features
- Unified OpenAI-compatible API: Single
/v1endpoint for all models - Smart Routing & Automatic Failover: Picks the best available model for each request, fails over to the next provider when one is rate-limited
- Encrypted Key Storage: API keys are stored encrypted for security
- Usage Tracking: Tracks per-key usage to stay under every free-tier cap
- Live Catalog Updates: Router updates its model catalog from a signed feed; new free models and quota changes land without a
git pull
Target Audience
- Developers who need free access to multiple LLMs
- Researchers looking to aggregate multiple free providers to reduce costs
- AI enthusiasts conducting personal experimentation and prototyping
Quick Start
- Visit freellmapi.co to obtain an API key
- Connect using any OpenAI-compatible client
- The system automatically routes to the best available model
Core Advantages
- Approximately 7.4 billion free tokens per month
- Aggregates 34 providers to avoid rate-limiting issues
- Smart routing and automatic failover ensure high availability
- Supports 635 free model endpoints for broad coverage
System Requirements
- OS: Cross-platform (Web API-based)
Notes
- For personal experimentation only
- Free version uses monthly snapshots; premium version provides live catalog updates
Release history
Sort
Related projects
ollama
ollama/ollama
Running open models locally no longer needs the cloud — ollama compresses downloading, running, and serving into a few commands, offering a CLI, a REST API, and official Python / JS libraries across macOS, Windows, Linux, and Docker.
v0.40.17-rc0 Go
Author updated 2d ago
llama.cpp
ggml-org/llama.cpp
A C/C++ implementation for LLM and VLM inference with minimal setup and state-of-the-art performance, supporting multiple model formats with CLI, server, and built-in Web UI.
b12362 C++
Author updated 13m ago
vllm
vllm-project/vllm
vLLM is a high-throughput, memory-efficient LLM inference and serving engine (Python). Built on PagedAttention and continuous batching, it serves 200+ model architectures behind an OpenAI-compatible API across many hardware backends.
v0.33.0rc3 Python
Author updated 11d ago
OmniRoute
cheaper-inference/OmniRoute
A free MIT AI gateway providing a unified endpoint to 290+ providers and 500+ models with quota-aware auto-fallback and token compression.
v3.8.53 TypeScript
Author updated 7d ago
llmfit
AlexsJones/llmfit
A command-line tool that recommends the best local LLMs for your hardware configuration, supporting multi-GPU, MoE architectures, and multiple quantization formats.
v1.1.20 Rust
Author updated 10d ago
magpie
yetone/magpie
Magpie is a locally running AI gateway that lets coding agents such as Claude Code, Codex, Gemini CLI and OpenCode use models like Kimi, DeepSeek, GLM and ChatGPT, with one-click menu bar switching and automatic failover to the next account when quota runs out.
v0.1.4082 Go
Author updated 54m ago