liquid
LiquidAI: LFM2.5-2.6B
liquid/lfm-2.5-2.6b
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
liquid/lfm-2.5-2.6b is a compact, text-only Liquid AI model presented for on-device and agent-oriented workloads. Its model card describes a long context window, multilingual coverage, tool calling, and always-on reasoning, while the OpenRouter listing confirms text input and output with tool and structured-output parameters. Vendor-reported results emphasize efficient local and high-throughput serving, but the supplied evidence is limited to the provider documentation and catalog data, so suitability should be validated on the intended workload.[1][2]
Strengths
- Designed for local and edge deployment, with vendor-reported efficient CPU, GPU, and Apple-silicon inference.[2]
- Post-trained for agent workflows and exposes tool calling, structured outputs, reasoning controls, and other production-oriented parameters.[1][2]
- Combines a long context window with multilingual support, including English, Spanish, and Portuguese.[2]
Limitations
- Liquid AI advises against using this variant for agentic coding and knowledge-heavy tasks.[2]
- Reasoning is mandatory rather than optional, which may be unsuitable when direct answers without a thinking phase are required.[1][2]
- The evidence pack contains vendor documentation and a catalog listing, but no independent model-card review; validate quality, latency, memory use, and reliability on target workloads.[1][2]
Where to use it
- Local or privacy-sensitive assistants and agents that need tool calling and structured outputs.[1][2]
- Data extraction, retrieval-augmented generation, and long-context processing where the vendor's guidance fits the task.[1][2]
- Prototype multilingual workflows after testing the required languages and domain accuracy.[2]
Sources
- [1] OpenRouter catalog · LiquidAI: LFM2.5-2.6BSources checked: Nov 13, 2026
- [2] Model documentation · LiquidAI: LFM2.5-2.6BSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...
Specifications
- Model ID
- liquid/lfm-2.5-2.6b
- Canonical ID
- liquid/lfm-2.5-2.6b-20260811
- Creator
- liquid
- Added to OpenRouter
- 11.08.2026
- Context length
- 128,000
- Modality
- text->text
- Input modalities
- text
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.350 / out $0.500
- Knowledge cutoff
- —
- Expiration date
- 13.11.2026
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 | CC — below the B band | — |
| 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
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Artificial Analysis | Coding index | 7.7 | CC — below the B band | 13.11.2026 |
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 details are unavailable right now; the catalog data above is unaffected.
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.