LFM2.5-2.6B
Liquid AI developed LFM2.5-2.6B as a compact model designed for efficient reasoning and long-context tasks. It supports text-based inputs and outputs, making it suitable for data extraction and retrieval-augmented generation workflows.
LFM2.5-2.6B specs and pricing
- Provider: LiquidAI
- Released: August 11, 2026
- Context window: 128K tokens
- Max output: 8K tokens
- Input: text
- Output: text
- Price: $0.35 input / $0.50 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What LFM2.5-2.6B is good at
- Processing long-context documents
- Automated data extraction tasks
- Retrieval-augmented generation workflows
To-dos to try with LFM2.5-2.6B
- Summarize the key findings from a 100-page research report.
- Extract specific contact information and dates from a series of unstructured emails.
- Retrieve relevant information from a large knowledge base to answer a complex query.
FAQ
- What is the primary focus of the LFM2.5-2.6B model? This model is designed for reasoning tasks, agent workflows, and processing large amounts of text data.
- Can this model process image files? No, the model is limited to text-based inputs and outputs.
- How much does LFM2.5-2.6B cost? LFM2.5-2.6B costs $0.35 per million input tokens and $0.50 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 1.05 credits ($1 = 100 credits).
- What is the context window of LFM2.5-2.6B? LFM2.5-2.6B can read up to 128K tokens at once and write up to 8K tokens in one reply.
- Can I use LFM2.5-2.6B without coding? Yes. In todo.is you pick LFM2.5-2.6B 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.