Open source · August 26, 2026
freelm: Routing Across Free LLM Providers
freelm exposes six free-tier providers through one interface, with explicit controls for failover, quotas, streaming, and paid-model avoidance.
By Shihab Shahriar Antor · Updated 2026-08-26
freelm is an OpenAI-compatible Python and JavaScript client that routes across OpenRouter, Google AI Studio, NVIDIA NIM, Groq, Cerebras, and Mistral. It is designed for development workloads that can use provider free tiers and need a clear failure path when one source is unavailable.
Routing and failover
The client tracks local quota state, rotates keys, opens circuit breakers after failures, and interleaves candidate models across providers. That prevents a provider with a long model list from consuming every attempt before the router reaches a healthy alternative.
Free-only as a guard
OpenRouter mixes free and paid models in one catalogue. freelm rejects non-free OpenRouter model identifiers by default instead of relying on naming convention alone. Users can explicitly opt out of that guard when they intend to use paid capacity.
Limits change
Provider rate limits and catalogues are external facts and change frequently. The library's live model discovery and configurable quotas are more durable than a static comparison table. Documentation should timestamp any specific provider limit rather than presenting it as permanent.