Lfm 2.5 2.6b (free)

lfm-2.5-2.6b-free · Liquid

LFM-2.5-2.6B is a compact reasoning model developed by Liquid, featuring a generous 128,000 token context length. It is highly suited for agent workflows, data extraction, retrieval-augmented generation (RAG), and long-context processing. However, the developer advises against using this model for agentic coding tasks.

Specifications

Context128K tokens
Modalitiestext
Featuresreasoning, long context
Endpointschat_completions

Frequently asked questions

What is lfm-2.5-2.6b-free?

LFM-2.5-2.6B is a compact reasoning model developed by Liquid, featuring a generous 128,000 token context length. It is highly suited for agent workflows, data extraction, retrieval-augmented generation (RAG), and long-context processing. However, the developer advises against using this model for agentic coding tasks.

What is the context length of lfm-2.5-2.6b-free?

lfm-2.5-2.6b-free has a 128,000 token context window.

What modalities does lfm-2.5-2.6b-free support?

lfm-2.5-2.6b-free accepts text input.

What capabilities does lfm-2.5-2.6b-free support?

lfm-2.5-2.6b-free supports reasoning and long context. Per-protocol parameter support is listed in the capability table on this page.

How do I call lfm-2.5-2.6b-free via API?

lfm-2.5-2.6b-free is available through the AIHubMix unified API. The API is OpenAI-compatible: point your OpenAI SDK at https://aihubmix.com/v1, use your AIHubMix API key, and set the model name to lfm-2.5-2.6b-free — no other code changes needed.

Who created lfm-2.5-2.6b-free?

lfm-2.5-2.6b-free is developed by Liquid. AIHubMix aggregates it alongside models from other providers behind one API and one bill.

Use lfm-2.5-2.6b-free via the AIHubMix unified API — one interface for every major LLM.