freellmapi
SHA-256OpenAI-compatible proxy that aggregates free tiers of 16+ LLM providers behind a single /v1 endpoint, with smart routing, automatic failover, and encrypted key storage. Personal experimentation only.
Smart Download
Download Download Version
v0.4.1 · 101 MB
One endpoint for all free LLMs: aggregate tiers, smart routing, failover, encrypted keys.
Core Features
- Aggregates free tiers of 16+ LLM providers (~1.7B tokens/month)
- Fully OpenAI-compatible (chat, responses, embeddings, images, audio)
- Smart routing and automatic failover across models (up to 20 retries)
- Sticky sessions: same conversation stays on same model for 30 minutes
- Encrypted key storage (AES-256-GCM), unified API key, no upstream key exposure
What It Can't Do
- •This tool is intended for personal experimentation only. Do not use in production or commercial applications. Each free tier has strict rate limits; exceeding them may cause request failures or provider bans. Model switching may cause slight context inconsistency; enable Context Handoff to mitigate. Respect each provider's Terms of Service. Avoid storing sensitive data as request logs may contain content.
Use Cases
- Developers who want to explore multiple LLMs for free without subscribing to each provider
- Running a personal AI agent locally or on an edge device, avoiding per-API billing management
FreeLLMAPI is an open-source proxy that unifies the free tiers of 16+ LLM providers—Google, Groq, Cerebras, NVIDIA, Mistral, OpenRouter, GitHub Models, Cohere, Cloudflare, HuggingFace, Zhipu, Ollama, and more—into a single OpenAI-compatible endpoint. It handles rate limits, failover, and per-key tracking transparently, so you can route any OpenAI SDK or client (LangChain, Continue, Claude Code) through your own local server. Unlike manually juggling multiple SDKs or using individual provider wrappers, FreeLLMAPI provides a unified dashboard for key management, fallback chain configuration, and usage analytics—all while keeping your API keys encrypted at rest. Perfect for developers who want to explore a wide range of models without subscription costs. Note: intended for personal experimentation only; not for production use.
Tags
Getting Started
Download installer
Click the button above to download the installer for your system
Install the software
Open the downloaded dmg file, then drag the app to Applications
Visit freellmapi.co to get the install script, or download the desktop installer (Windows .exe) from Releases
Run the install script (requires Docker) or double-click the installer and follow the wizard
Open http://localhost:3001 in your browser, create your admin account, and add your API keys
- Visit freellmapi.co to get the install script, or download the desktop installer (Windows .exe) from Releases
- Run the install script (requires Docker) or double-click the installer and follow the wizard
- Open http://localhost:3001 in your browser, create your admin account, and add your API keys
SHA-256 checksum verified
Checksum extracted from GitHub official Release page
SHA256 Checksum
1af7a3b5515a875c68ebe5d50fba86c0b57b6b71b270a4e1282fc36790d59be6This checksum is extracted from the GitHub Release page. Verify file integrity after download.
All SHA-256 checksums on this platform are extracted from the project's official GitHub Release page, without any modification. You can independently verify them on the GitHub Releases page.
Open Source Transparency
View GitHub SourceUninstall Info
Delete the ~/freellmapi directory (contains SQLite database and config). If using Docker, stop and remove the container and its associated data volume.
No Extra Dependencies
Ready to use after download. No additional runtime required.
Having issues? Check the FAQ below
5 FAQs
Similar Projects
ragflow
RAGFlow is a leading open-source RAG engine that fuses deep document understanding with agentic workflows, offering precise, citation-grounded answers. Unlike LangChain's DIY approach, RAGFlow provides a turnkey, enterprise-ready platform with a visual interface and template-based chunking, reducing hallucinations and setup complexity.
unsloth
Unsloth is the first desktop app to run and train AI models locally. It supports a wide range of models including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, and FLUX. Unlike most local model tools that focus only on inference, Unsloth adds a full training stack: fine-tune LLMs, diffusion, TTS, and embedding models 2× faster with 70% less VRAM. It also supports LoRA, QLoRA, RL, GRPO, DPO, and FP8. The app includes built-in Agents & Tools integration (Claude Code, Codex, MCP), private search and RAG, image/video diffusion, and audio support. With hardware support for CPU, NVIDIA, AMD, Intel, macOS, and multi-GPU setups, plus remote access via Cloudflare, Unsloth is a comprehensive local AI studio. It can export to GGUF, NVFP4, FP8 and offers an OpenAI-compatible API for easy deployment.
ollama
Ollama lets you download, run, and manage large language models locally. One command, multiple platforms, endless possibilities.