OpenAI-compatible router that puts free LLM models from 13 providers behind one endpoint with automatic failover
Local LLM routing layer for Claude Code, Codex, and OpenCode
Stage
Not given
Startup
Founded
Not given
Not given
Based in
FR
US
Pricing model
Freemium
Freemium
Pricing
Free: open core under BSL 1.1, no account or card required. Pro: 12 € monthly (or 9.08 € per month billed annually at 109 €/yr), or 199 € for Lifetime license (one payment, no renewals, limited to first 200). 14-day free trial for Pro requires a card.
Free: $0 per month with 50M tokens a month and 2 connected devices. Pro: $30 per month with unlimited tokens and 5 connected devices.
Key features
Automatic failover across 13 free LLM providers
OpenAI-compatible API endpoint
Model capability testing for tools, JSON and vision
Hardcoded zero paid model fallback
Local router with keys staying on your machine
Model fusion and answer synthesis in Pro
Custom virtual model profiles in Pro
Native prompt compression to reduce tokens
Automatic model cooling and recovery probing
Support for Cursor, Continue, Open WebUI, LangChain and Claude Code
Routes to 293 models from 24 providers
Automatic fallback across providers
Included inference on all plans
End-to-end encrypted key vault
Shared memory across agents
OpenAI and Anthropic compatible APIs
Context.dev integration for web data
Works with Claude Code, Codex, OpenCode and other tools
Browser chat with voice transcription
Cost and usage analytics
What makes it different
Structured inability to spend money on paid models, enforced in code not configuration
No middleman: keys stay local, prompts go directly to providers
Benchmarked quality parity with gpt-5 for classification, extraction and reasoning
Millisecond failover when a model rate-limits or fails
First request works with no setup or keys required
All your keys and models accessible through one layer
Ficelle
OpenLLM