AI Agent StoreLiquid AI · Provider verified
LFM2.5-24B-A2B
A text model for assistants that reason and use tools. You can use a hosted service or download the files to run it on your own hardware.
Released 2026-10-13 · Catalog added 2026-10-13 UTC · Checked 2026-10-15. Catalog addition and provider launch are separate dates.
We still need comparable independent tests. You can compare the confirmed features and limits below, but we cannot yet give this version an Agent Fit or Practical Value rating. Test it on your own tasks before switching; results for another version or thinking setting may not apply.
What you can use today
Token prices measure the small pieces of text the model reads or produces. Capacity is the amount the service accepts in a request; check the limits below for any fallback to another model. A dash means the rate is unverified.
Exact catalog ID: liquid/lfm-2.5-24b-a2b. This 24B model activates about 2.45B parameters per token and always thinks before answering. Liquid recommends tools or retrieval for knowledge-heavy work. Your application runs tool calls and checks the results.
Local use needs suitable hardware and setup. The Liquid license restricts commercial use above its $10 million annual-revenue threshold; check the license for your organization. GGUF, FP8, ONNX and MLX files are formats of this model, not separate quality results.
The downloadable model documents 131,072 context tokens. This OpenRouter offer has a 128,000-token context and 8,192-token output cap. Hosted limits are not interchangeable with the download.
Displayed prices apply to the OpenRouter service, not to running the download. Liquid’s published speed and task scores are vendor evidence; comparable independent results remain pending. Your bill can also include tools, retries and charged thinking tokens. Check the offer used by your application.
Provider release and specifications ↗
Inspect the exact catalog model ↗
More setup and licensing details ↗
Test it before switching
Give each model the same examples, tools and definition of success. Record correct outcomes, response time, retries and total cost. A cheaper token price does not guarantee a cheaper completed task.
Compare caching and long-context costs ↗