LFM2.5 2.6B

nano-gpt/liquid/lfm-2.5-2.6b · family liquid · in: text → out: text · price provider-declared (via models.dev). Capabilities: toolsreasoningtext.

$0.13Blended $/1M (3:1)

$0.1Input $/1M

$0.2Output $/1M

$0.301M in + 1M out

$0.05 −50%Cache read $/1M

#845 of 5,819Cheapest rank

Provider: NanoGPT (nano-gpt)
Kind: text (outputs text)
Context: 128,000 tokens
Max output: 32,768 tokens
Capabilities: toolsreasoningtext

Call it

jishie indexes & prices models; it does not proxy inference.

Most providers are OpenAI-compatible — point base_url at NanoGPT and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"liquid/lfm-2.5-2.6b","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):