LFM3-1.7B
LiquidAI's LFM3-1.7B is a compact text-only model designed for agentic workflows and structured data tasks. It features a 256K-token context window and is specifically post-trained to perform reasoning before generating its output.
LFM3-1.7B specs and pricing
- Provider: LiquidAI
- Released: November 6, 2026
- Context window: 262K tokens
- Max output: 8K tokens
- Input: text
- Output: text
- Price: $0.08 input / $0.20 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What LFM3-1.7B is good at
- Complex reasoning tasks
- Automated tool calling
- Generating structured data outputs
To-dos to try with LFM3-1.7B
- Analyze a long document and extract key information into a structured JSON format
- Use tool calling to retrieve data from an external API based on user input
- Reason through a multi-step logical problem to provide a step-by-step solution
FAQ
- What is the primary purpose of the LFM3-1.7B model? It is designed for agent-based applications that require tool calling and structured output generation.
- Does this model support image processing? No, the model is limited to text input and text output.
- How much does LFM3-1.7B cost? LFM3-1.7B costs $0.08 per million input tokens and $0.20 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.25 credits ($1 = 100 credits).
- What is the context window of LFM3-1.7B? LFM3-1.7B can read up to 262K tokens at once and write up to 8K tokens in one reply.
- Can I use LFM3-1.7B without coding? Yes. In todo.is you pick LFM3-1.7B 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.