LiquidReasoningFreeReleased 11 August 2026
LFM2.5-2.6B (free) pricing, context and benchmark
LFM2.5-2.6B is a compact reasoning model from Liquid AI.
66K
Input context
8K
Output context
Free
Official input
Free
Official output
n/a
AA index
01 · Model Overview
Everything that matters, in one table
Context, pricing, cache, modalities and tooling, from the model registry and Artificial Analysis.
| Model | LFM2.5-2.6B (free) |
| Model ID | liquid/lfm-2.5-2.6b:free |
| Provider | Liquid |
| Release date | 11 August 2026 |
| Status | Generally available |
| Input context | 65,536 tokens |
| Output context | 8,192 tokens |
| Official input pricing | Free per 1M tokens |
| Official output pricing | Free per 1M tokens |
| Cache read pricing | Not published |
| Market input pricing | Free per 1M (cheapest route) |
| Market output pricing | Free per 1M (cheapest route) |
| Input modalities | text |
| Output modalities | text |
| Reasoning control | Not exposed |
| Tool support | Text generation only |
| Tokenizer | Other |
| Provider routes | 1 endpoint |
| Artificial Analysis index | Not published |
| Speed | Not published |
| Knowledge cutoff | Not publicly stated |
Input and output support
| Modality | Input | Output | Billed at |
|---|---|---|---|
| Text | ✓ yes | ✓ yes | Free in |
| Image | no | no | not supported |
| Audio | no | no | not supported |
| Video | no | no | not supported |
| File (PDF) | no | no | not supported |
02 · Overview
What is LFM2.5-2.6B (free)?
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...
LFM2.5-2.6B (free) carries a 66K token window, uses the Other tokenizer and is served by Liquid. On Hoodgen it sits in the Reasoning tier of the model menu next to its siblings, so you can switch mid conversation without losing the thread.
03 · Release
Release and what changed from the previous version
Released11 August 2026
This is the only release of LFM2.5-2.6B (free) on OpenRouter, released 11 August 2026. The provider has not published a knowledge cutoff, so treat training data as recent but unconfirmed for very new events.
07 · Use cases
What can you do with LFM2.5-2.6B (free)?
Debugging and root cause
Multi file failures where the model has to hold a causal chain before answering.
Architecture and planning
Design docs, migration plans and trade off analysis over long context.
Data analysis
Spreadsheets and logs read in one pass, then summarised with the numbers quoted back.
Agentic coding
Repo wide changes that need plan, edit and verify loops.
09 · Pricing
LFM2.5-2.6B (free) pricing
Official pricing
List price
Free / 1M in
Free / 1M out
- 66K context
- text input
Cheapest route
Free / 1M in
Free / 1M out
- 1 route on OpenRouter
- What Hoodgen routes to first
- Same model, lower bill
Market pricing, every route
| Provider | Tier | Input | Output | Cache read | Uptime 24h |
|---|---|---|---|---|---|
| Liquid | standard | Free | Free | n/a | 97.0% |
API pricing and cost calculator
| Rate | Per call | Total | Credits |
|---|---|---|---|
| Cheapest route | $0.0000 | $0.00 | 1 |
| List price | $0.0000 | $0.00 | 1 |
10 · Developers
API and developer information
| Model ID | liquid/lfm-2.5-2.6b:free |
| Endpoint | https://openrouter.ai/api/v1/chat/completions |
| Parameters | prompt and max_tokens |
| Streaming | Yes, server sent events |
| Modality string | text->text |
| Max prompt tokens | 65,536 |
| Max completion tokens | 8,192 |
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "liquid/lfm-2.5-2.6b:free",
"messages": [{ "role": "user", "content": "Summarise this document." }],
"max_tokens": 1024
}'11 · Limitations
Model limitations
| Text only output | It cannot generate images, audio or video. Pair it with an image model on Hoodgen when you need visuals. |
| Output cap | 8,192 tokens per request. Long deliverables have to be chunked. |
| Benchmarks not published | Artificial Analysis does not publish an Intelligence Index for this release, so no benchmark score is claimed here. |
| Knowledge cutoff | The provider does not state a fixed cutoff for every release. Verify very recent events against search. |
| Rate limits | Free routes are rate limited by the provider, so heavy batch jobs should use a paid route. |
12 · Comparison
LFM2.5-2.6B (free) vs other Liquid models
| Model | Context | Input /1M | Output /1M | AA index | Released |
|---|---|---|---|---|---|
| LFM2.5-2.6B (free) | 66K | Free | Free | n/a | 2026 |
13 · Privacy
Privacy and data policy
- On Hoodgen, prompts and attachments answer that request and stay in your conversation history so you can reopen it. They are not used to train models.
- Requests route through OpenRouter to Liquid and are covered by that provider's API terms.
- Do not paste secrets or personal data you would not send to any hosted model.
14 · FAQ
LFM2.5-2.6B (free) questions, answered
LFM2.5-2.6B (free) is a reasoning model from Liquid, released 11 August 2026. LFM2.5-2.6B is a compact reasoning model from Liquid AI.
✦
Start chatting with LFM2.5-2.6B (free)
Free to try on Hoodgen AI, with a live credit estimate before every send. No API key, no setup.