modelbenchmark.io

LFM2.5 2.6B

lfm-2-5-2-6b

Compare

Liquid AI's compact 2.6B reasoning model for agent workflows, data extraction, RAG, and long-context processing. It supports tool calling and structured output, but Liquid advises against using it for agentic coding. Warning: prompts and responses may be logged and used for model training or service improvement; do not send sensitive data.

Specification

most-agreed values

Context
128K
Max output
33K
Released
2026-08-12
Knowledge cutoff
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.10
Output
$0.20
Cache read
$0.05

Available from 3 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
kilo · freefreefree66K8K
openrouter · freefreefree66K8K
nano-gpt · liquid$0.10$0.20$0.05128K33K