LFM2.5-24B-A2B
lfm2-5-24b-a2b
Reasoning model for deliberate analysis, multi-step problem solving, and tool use
Specification
most-agreed values
Context
128K
Max output
8K
Released
2026-10-13
Knowledge cutoff
—
Retires
—
Open weights
no
Input
text
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.05
Output
$0.70
Cache read
$0.025
Available from 1 host
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| vercel · liquid | $0.05 | $0.70 | $0.025 | — | 128K | 8K | — |
Other listings of this model
this page is one of them
The corpus files LFM2.5-24B-A2B under several keys. This page is the lfm2-5-24b-a2b listing. The full record — every host, every price and every benchmark score — is on the main LFM2.5-24B-A2B page.