LFM2.5-24B-A2B
LFM2.5-24B-A2B is a large language model made by LiquidAI, added to the catalog on 13 Oct 2026. It has a context window of 128,000 tokens and costs $0.05 per 1M input tokens and $0.70 per 1M output tokens. It accepts text and produces text. Typical uses: answering text-based questions, summarising long documents and drafting structured responses.
Price checked ยท source: OpenRouter
What LFM2.5-24B-A2B is
LiquidAI LFM2.5-24B-A2B is a text-in, text-out reasoning model from Liquid AI. It accepts text and produces text, and its listed capabilities include reasoning, tool use, structured outputs, and response formatting. The model is described as reasoning before answering and as being built for agents that call tools. These capabilities make it suited to workflows that combine written instructions with tool-based steps or require responses in a defined format.
The model has a context length of 128,000 tokens and a maximum output of 8,192 tokens. Its context can accommodate substantial amounts of text in a single request, such as long documents or collections of related material, while the output limit sets the maximum size of a response. It accepts text only; the provided specifications do not list image, audio, or other input modalities. Its outputs are text.
Potential tasks include working through text-based questions, summarising longer material, drafting structured responses, and supporting agent workflows that use tools. The facts describe its reasoning and tool support but do not specify particular tools, response schemas, or domain specialisations. This model is a fit to consider when a text-only workflow needs a large context window and may benefit from tool calls or formatted output.
Key features
- Accepts text and produces text
- 128,000-token context length
- Maximum output of 8,192 tokens
- Supports reasoning and tool use
- Supports structured outputs and response formatting
Typical uses
- Answering text-based questions
- Summarising long documents
- Drafting structured responses
- Supporting tool-using agent workflows
LFM2.5-24B-A2B pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.05 |
| Output, per 1M tokens | $0.70 |
| Cached input read, per 1M tokens | $0.025 |
No price change since it was added on 13 Oct 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0002 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0018 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0029 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.0086 |
LFM2.5-24B-A2B specifications
| Model id | liquid/lfm-2.5-24b-a2b |
|---|---|
| Version | lfm-2.5-24b-a2b-20261012 |
| Context window | 128,000 tokensAbout 96,000 English words |
| Max output | 8,192 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 13 Oct 2026 |
| Input types | text |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | No |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for LFM2.5-24B-A2B yet.
Compare LFM2.5-24B-A2B
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.