LFM3-1.7B
LFM3-1.7B is a large language model made by LiquidAI, added to the catalog on 6 Nov 2026. It has a context window of 262,144 tokens and costs $0.08 per 1M input tokens and $0.20 per 1M output tokens. It accepts text and produces text. Typical uses: question answering over long documents, summarising lengthy text and generating structured text responses.
Price checked ยท source: OpenRouter
What LFM3-1.7B is
LiquidAI LFM3-1.7B is a compact text model that accepts text prompts and produces text. The provider describes it as a 1.7B-parameter model post-trained for agent-oriented use, tool calling, and structured outputs. It supports reasoning and is described as reasoning before it answers. Tool support allows it to take part in tool-based interactions, while structured outputs and response-format support are relevant to workflows that require responses in a specified format.
The model supports a context of up to 262,144 tokens and can produce up to 8,192 output tokens. Its large context can accommodate substantial text within a single request, such as long documents or collections of related material. The output limit sets the maximum length of a response; it does not mean every response will use that many tokens.
These features suit tasks involving long-text question answering, document summarisation, and generating text in a requested structure. Reasoning support may also suit multi-step text tasks, while tool calling is relevant to agent workflows that use tools. The model's listed input and output modalities are both text, so its described capabilities center on text prompts and text responses. It is a fit to consider when an application needs a text model with extended context, configurable response formats, or tool support. The catalog does not specify particular tools or response schemas, so those details depend on the surrounding application.
Key features
- Accepts text and produces text
- Supports a context of up to 262,144 tokens
- Supports tool calling and structured outputs
- Supports reasoning and response formats
- Can produce up to 8,192 output tokens
Typical uses
- Question answering over long documents
- Summarising lengthy text
- Generating structured text responses
- Tool-based agent workflows
LFM3-1.7B pricing
US dollars, list price through OpenRouter.
| Item | Standard | Free |
|---|---|---|
| Input, per 1M tokens | $0.08 | $0 |
| Output, per 1M tokens | $0.20 | $0 |
| Cached input read, per 1M tokens | $0.02 | n/a |
| Variant | Model id |
|---|---|
| Free | liquid/lfm-3-1.7b:free |
A variant is the same model under another id, with prices or limits of its own. Its prices are the columns of the list above.
No price change since it was added on 6 Nov 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0001 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0022 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0028 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.012 |
LFM3-1.7B specifications
| Model id | liquid/lfm-3-1.7b |
|---|---|
| Version | lfm-3-1.7b-20261106 |
| Context window | 262,144 tokensAbout 196,608 English words |
| Max output | 8,192 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 6 Nov 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 LFM3-1.7B yet.
Compare LFM3-1.7B
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.