LFM2.5-24B-A2B
LFM2.5-24B-A2B is a reasoning model from Liquid AI designed for agents that call tools. It takes text as input, produces text as output, and has a 128,000-token context window.
LFM2.5-24B-A2B specs and pricing
- Provider: LiquidAI
- Released: October 13, 2026
- Context window: 128K tokens
- Max output: 8K tokens
- Input: text
- Output: text
- Price: $0.05 input / $0.70 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What LFM2.5-24B-A2B is good at
- Analyzing long text documents
- Reasoning through text-based problems
- Agent tasks that involve calling tools
To-dos to try with LFM2.5-24B-A2B
- Read this contract and list every deadline mentioned.
- Compare these three written proposals and summarize their differences.
- Use an available calculator tool to check the arithmetic in this budget.
FAQ
- Can LFM2.5-24B-A2B read images? No. The model accepts text input only.
- What is LFM2.5-24B-A2B designed for? Liquid AI describes it as a reasoning model built for agents that call tools.
- How much does LFM2.5-24B-A2B cost? LFM2.5-24B-A2B costs $0.05 per million input tokens and $0.70 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.24 credits ($1 = 100 credits).
- What is the context window of LFM2.5-24B-A2B? LFM2.5-24B-A2B can read up to 128K tokens at once and write up to 8K tokens in one reply.
- Can I use LFM2.5-24B-A2B without coding? Yes. In todo.is you pick LFM2.5-24B-A2B as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.