liquid › LFM2.5 2.6B › Pricing
$0.35 / $0.50per 1M tokens in / out
$0.04cache read · −89%
#190on OpenRouter by tokens · 12.1B / week
Price sheetper 1M tokens
| Input | $0.35 | list |
| Output | $0.50 | |
| Cache read | $0.04 | −89% vs input |
| Context · max output | 131K · 8K | tokens |
| Free tier | yes | free OpenRouter route |
Where to buy1 provider · per 1M tokens
| Provider | Input | Output | Context |
|---|---|---|---|
| Liquidlab | $0.35 | $0.50 | 128K |
In liquid's line-upper 1M in / out
| LFM2.5 24B A2B | $0.05 / $0.70 | −45% |
| LFM2.5 2.6B | $0.35 / $0.50 | this model |
Cheaper for the same workvs LFM2.5 2.6B
| Claude Haiku 5.5 max | -48% | score ×5.2 | $0.21 |
| MiniMax M3.1 Flash thinking | -32% | score ×5.1 | $0.22 |
| GLM 5.3 Flash maxOpen | -39% | score ×5 | $0.28 |
| Qwen3.8 Flash thinkingOpen | -41% | score ×4.7 | $0.37 |
| GPT-6 Luna max | -48% | score ×4.5 | $0.068 |
Pricing questions
How much does LFM2.5 2.6B cost?›
$0.35 per 1M input tokens and $0.50 per 1M output tokens. Cached input is $0.04.
Is LFM2.5 2.6B free to use?›
Yes, with limits: free OpenRouter route. Free route; provider availability and account rate limits apply.
How much does prompt caching save?›
Cache reads cost $0.04 per 1M, 89% below the input price.
What is a cheaper alternative to LFM2.5 2.6B?›
Claude Haiku 5.5 at max effort costs -48% per task with a score ×5.2 on Humanity's Last Exam.