liquid
LiquidAI: LFM3-1.7B (free)
liquid/lfm-3-1.7b:free
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
liquid/lfm-3-1.7b:free is OpenRouter's free endpoint for LiquidAI's post-trained, text-only 1.73B checkpoint. LiquidAI describes a compact tri-hybrid model with a 256K-token context, aimed at local agents, tool calling, structured outputs and domain specialization. OpenRouter marks reasoning as mandatory for this endpoint, while the model card says thinking is enabled by default and can be inconsistent to disable. The supplied evidence contains no complete measured benchmark results, so these are source-reported capabilities rather than verified performance.[1][2]
Strengths
- A compact 1.73B-parameter, text-only checkpoint with a documented 256K-token context for long inputs and outputs.[1][2]
- Source materials describe post-training for agent workflows, XML tool calls and structured outputs; the OpenRouter endpoint also exposes tools, tool_choice, response_format and structured_outputs.[1][2]
- The vendor says a 4-bit version uses about 1 GB of memory, lists multiple deployment formats and languages, and documents single-GPU fine-tuning.[2]
Limitations
- LiquidAI advises retrieval or search for knowledge-heavy tasks and does not recommend this model for agentic coding or complex multi-step reasoning because of its small size.[2]
- Reasoning control is unclear in practice: OpenRouter marks it as mandatory, while the vendor documentation says it is enabled by default and disabling can be inconsistent.[1][2]
- No complete independent benchmark or workload measurements are supplied; validate quality, latency, tool-use reliability and privacy. OpenRouter also says prompts and outputs may be retained and used, but the provided wording is truncated.[1][2]
Where to use it
- Evaluate for prototypes of tool-using assistants or local-agent workflows where a compact model and structured tool interface matter.[1][2]
- Consider for structured data extraction or machine-readable responses over long inputs, subject to task validation.[1][2]
- A candidate for domain-specialized multilingual assistants or small edge deployments when fine-tuning or quantized formats are available; confirm language and hardware fit.[2]
Sources
- [1] OpenRouter catalog · LiquidAI: LFM3-1.7B (free)Sources checked: Nov 13, 2026
- [2] Model documentation · LiquidAI: LFM3-1.7B (free)Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
A compact 1.7B-parameter text model with a 256K-token context, post-trained for agents, tool calling, and structured outputs. It reasons before it answers. Prompts and outputs may be retained and used...
Specifications
- Model ID
- liquid/lfm-3-1.7b:free
- Canonical ID
- liquid/lfm-3-1.7b-20261106
- Creator
- liquid
- Added to OpenRouter
- 06.11.2026
- Context length
- 262,144
- Modality
- text->text
- Input modalities
- text
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0 / out $0
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | reasoning: mandatory · parameters: include_reasoning, reasoning |
| Coding | No measurement | — |
| Agents | No measurement | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: mandatory · parameters: include_reasoning, reasoning |
| Document analysis | No measurement | — |
| Vision | No measurement | — |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Liquidfp8 | 262,144 | $0 | $0 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.