Source: https://ailoot.ai/models/en/liquid-lfm-2-5-2-6b-u003a-free/
Canonical: https://ailoot.ai/models/en/liquid-lfm-2-5-2-6b-u003a-free/
Language: en

# LiquidAI: LFM2.5-2.6B (free)

[Markdown](https://ailoot.ai/models/en/liquid-lfm-2-5-2-6b-u003a-free/index.md) · [JSON](https://ailoot.ai/models/en/liquid-lfm-2-5-2-6b-u003a-free/facts.json)

## [LiquidAI: LFM2.5-2.6B (free)](https://ailoot.ai/models/en/liquid-lfm-2-5-2-6b-u003a-free/)

Liquid AI LFM2.5-2.6B is a compact text reasoning model for agents, tool use, data extraction and RAG. Its hybrid design has 2.69B parameters. It reasons before answering and works best with concrete source material and clearly defined tools; the maker cautions against agentic coding and knowledge-heavy tasks.

- [**Ailoot Ultra · OpenAI Chat** `POST /v1/chat/completions` `liquid/lfm-2.5-2.6b:free`](https://ailoot.ai/models/en/liquid-lfm-2-5-2-6b-u003a-free/#method-0)
- [**Ailoot Ultra · Anthropic Messages** `POST /v1/messages` `liquid/lfm-2.5-2.6b:free`](https://ailoot.ai/models/en/liquid-lfm-2-5-2-6b-u003a-free/#method-1)

About the model

This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.

Liquid AI LFM2.5-2.6B is the post-trained text model in Liquid’s compact LFM2.5 family, designed for on-device agents and practical workflows. Its exact model card lists 2.69B parameters and 30 layers: 22 double-gated short-convolution blocks and eight grouped-query attention blocks. The hybrid design targets efficient text processing. The model accepts text and returns text, including a reasoned answer or a request to use a defined function.

The manufacturer recommends it for agentic workloads, tool use, data extraction, retrieval-augmented generation and long-context workflows. The release’s training pipeline combines supervised fine-tuning, specialized teachers, multi-domain on-policy distillation and reinforcement learning inside agent environments. This helps explain its focus on following task instructions, using tool observations and progressing through several steps. Give it the actual materials and a precise objective, rather than relying on broad learned knowledge to fill gaps.

For extraction, define the fields and source rules before supplying the material. A practical request is: “Read these service updates, extract each record’s identifier, stated status and next required action, and retain the sentence supporting every field. Return null when a field is missing.” Specify whether to copy a value exactly, normalize it or infer it. This makes the output inspectable and prevents a plausible interpretation from silently replacing information actually present in the source.

For RAG, provide relevant passages with stable labels and ask for an answer grounded in those passages. An example is: “Using only these installation instructions, explain which steps apply to the stated environment and list the prerequisites that remain unknown.” Keep document versions and conditions with the text. Ask the model to identify a missing or conflicting fact rather than invent a complete procedure. This fits the maker’s recommendation for source-grounded tasks better than asking the compact model to act as an exhaustive store of specialist knowledge.

LFM2.5-2.6B is a pure reasoning model: its chat template begins the assistant answer with a thinking marker, and it reasons before the final answer. The manufacturer’s model card recommends temperature 0.1, top-k 50 and repetition penalty 1.1 for generation. Those are settings for the named model’s recipe. Keep the final deliverable distinct from the reasoning text, and leave space for both in a working request. Controls or direct-answer modes belonging to other LFM instruction editions should not be assumed for this model.

The model uses a ChatML-like conversation format with system, user, assistant and tool roles. Its documented function workflow has four stages: define the tools, let the model request a function, execute that function in the surrounding application, and return the actual result so the model can answer. Native calls are Pythonic lists enclosed by tool-call markers; the maker also describes requesting JSON call format through the system instruction. Use the appropriate parser, check the function name and arguments against the supplied definitions, and retain the result with the call that produced it.

For a compact agent workflow, expose only the functions relevant to the current task, with concise descriptions and explicit argument types. Tool definitions themselves occupy context. A useful sequence might look up the status of a supplied record, compare the returned status with a rule and explain whether follow-up is needed. Supply the record identifier as evidence and ask for a final answer tied to the returned observation. The model proposes and interprets the operation; the application supplies its actual execution and result.

The current manufacturer model card specifies a 131,072-token model context, and the release describes a dedicated context-extension stage. Work within the window of the configuration in use, retaining source boundaries, relevant history and room for the continuation. For several documents, ask for a particular comparison or dependency to trace. The native checkpoint, GGUF, ONNX and MLX artifacts serve different deployment needs, and a speculative-decoding draft is a separate companion artifact. Resource or speed figures from one configuration do not automatically describe every model format and working window.

Liquid explicitly does not recommend LFM2.5-2.6B for agentic coding or knowledge-heavy tasks. Keep it focused on concrete workflows with supplied evidence, extraction rules and tool observations. The pre-trained Base checkpoint is also a separate artifact intended for customization, while this post-trained edition is the agent model. For the final result, inspect extracted values against their source, check that a cited passage supports the answer, and distinguish a requested tool call from an operation with a recorded outcome. Preserve unresolved information where it affects the conclusion instead of letting fluent text obscure it.

**Ailoot Ultra · OpenAI Chat** `POST /v1/chat/completions` `liquid/lfm-2.5-2.6b:free`

[`liquid/lfm-2.5-2.6b:free`](https://ailoot.ai/models/en/#m=liquid%2Flfm-2.5-2.6b%3Afree&route=Ultra&caller=liquid%2Flfm-2.5-2.6b%3Afree&fmt=chat)

LiquidAI /`liquid/lfm-2.5-2.6b:free`

### Overview

Liquid AI LFM2.5-2.6B is a compact text reasoning model for agents, tool use, data extraction and RAG. Its hybrid design has 2.69B parameters. It reasons before answering and works best with concrete source material and clearly defined tools; the maker cautions against agentic coding and knowledge-heavy tasks.

Accepted inputs

Text

Results

Text

### Available in Ailoot · inputs & methods

**Ailoot Ultra · OpenAI Chat** `POST /v1/chat/completions`

Input types

`text`

Output types

`text`

Context

65,536 tokens

Maximum output

8,192 tokens

Output format

JSON

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits liquid/lfm-2.5-2.6b:free | Default— |
| Field`messages` | Type`array` | RequirementRequired | Values & limits | Default— |
| Field`stream` | Type`boolean` | RequirementOptional | Values & limits false | Defaultfalse |
| Field`max_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Maximum: 8,192 | Default— |
| Field`max_completion_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Maximum: 8,192 | Default— |
| Field`n` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Maximum: 128 | Default— |
| Field`temperature` | Type`number` | RequirementOptional | Values & limits | Default— |
| Field`top_p` | Type`number` | RequirementOptional | Values & limits | Default— |
| Field`seed` | Type`integer` | RequirementOptional | Values & limits | Default— |
| Field`stop` | Type`` | RequirementOptional | Values & limits | Default— |
| Field`frequency_penalty` | Type`number` | RequirementOptional | Values & limits | Default— |
| Field`presence_penalty` | Type`number` | RequirementOptional | Values & limits | Default— |
| Field`user` | Type`string` | RequirementOptional | Values & limits | Default— |

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`content_type` | Contractapplication/json |
| Parameter`required` | Contractmodel, messages |
| Parameter`optional` | Contractstream, max\_tokens, max\_completion\_tokens, n, temperature, top\_p, seed, stop, frequency\_penalty, presence\_penalty, user |
| Parameter`material_types` | Contracttext |
| Parameter`conditions` | ContractUse literal text messages only. Cache controls, tools, image/audio/video content and streamed responses are unavailable for this method., The complete encoded JSON request must not exceed 65536 bytes. |

Lifecycle: `synchronous_json`

### Pricing

Tariff references do not add request options. Supported parameters are listed for the selected method.

Fast mode

Standard rate When fast mode is selected

Flex mode

Standard rate When flex mode is selected

Maximum reasoning effort

Standard rate When maximum reasoning effort uses the default adjustment

Explicit cache pricing

Not enabled When explicit cache is requested

Text-only zero rates

Text input and output only. Cache, tools, media and streaming are unavailable. For text-only input and output

#### Ailoot rates

#### Prices by configuration

| Configuration | Rate schedule | Charge |
| --- | --- | --- |
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens **$0** / 1K tokens Output · Output tokens **$0** / 1K tokens Input · Cache read **—** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/)

### Example requests

#### Ailoot Ultra · OpenAI Chat

curl · create once and retain the complete result

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
export AILOOT_API_KEY
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "liquid/lfm-2.5-2.6b:free", "messages": [{"role": "user", "content": "Summarize the supplied text in three concise points."}], "stream": false}')

Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
# Submit once. Retain the complete result, original identifiers and every response header.
```

### Receive and save results

#### Ailoot Ultra · OpenAI Chat

JSON

##### Keep all completed results

Keep every complete returned response, file and content part.

Retain the complete response, all actual results, original identifiers, usage and response headers.

##### If the original response needs checking

Preserve the original response, headers and X-Client-Request-ID. An uncertain outcome does not authorize another creation.

### Aliases

#### Model aliases

**Ailoot Ultra** [`liquid/lfm-2.5-2.6b:free`](https://ailoot.ai/models/en/#m=liquid%2Flfm-2.5-2.6b%3Afree&route=Ultra&caller=liquid%2Flfm-2.5-2.6b%3Afree&fmt=chat)

#### Method path aliases

Use the method paths shown above.

#### Related caller IDs

[`liquid/lfm-2.5-2.6b:free`](https://ailoot.ai/models/en/#m=liquid%2Flfm-2.5-2.6b%3Afree&route=Ultra&caller=liquid%2Flfm-2.5-2.6b%3Afree&fmt=chat)

**Ailoot Ultra · Anthropic Messages** `POST /v1/messages` `liquid/lfm-2.5-2.6b:free`

[`liquid/lfm-2.5-2.6b:free`](https://ailoot.ai/models/en/#m=liquid%2Flfm-2.5-2.6b%3Afree&route=Ultra&caller=liquid%2Flfm-2.5-2.6b%3Afree&fmt=messages)

LiquidAI /`liquid/lfm-2.5-2.6b:free`

### Overview

Liquid AI LFM2.5-2.6B is a compact text reasoning model for agents, tool use, data extraction and RAG. Its hybrid design has 2.69B parameters. It reasons before answering and works best with concrete source material and clearly defined tools; the maker cautions against agentic coding and knowledge-heavy tasks.

Accepted inputs

Text

Results

Text

### Available in Ailoot · inputs & methods

**Ailoot Ultra · Anthropic Messages** `POST /v1/messages`

Input types

`text`

Output types

`text`

Context

65,536 tokens

Maximum output

8,192 tokens

Output format

JSON

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits liquid/lfm-2.5-2.6b:free | Default— |
| Field`messages` | Type`array` | RequirementRequired | Values & limits | Default— |
| Field`stream` | Type`boolean` | RequirementOptional | Values & limits false | Defaultfalse |
| Field`system` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`max_tokens` | Type`integer` | RequirementRequired | Values & limits Minimum: 1 Maximum: 8,192 | Default— |
| Field`temperature` | Type`number` | RequirementOptional | Values & limits | Default— |
| Field`top_p` | Type`number` | RequirementOptional | Values & limits | Default— |
| Field`top_k` | Type`integer` | RequirementOptional | Values & limits | Default— |
| Field`stop_sequences` | Type`array` | RequirementOptional | Values & limits | Default— |
| Field`metadata` | Type`object` | RequirementOptional | Values & limits | Default— |

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`content_type` | Contractapplication/json |
| Parameter`required` | Contractmodel, messages, max\_tokens |
| Parameter`optional` | Contractstream, system, temperature, top\_p, top\_k, stop\_sequences, metadata |
| Parameter`material_types` | Contracttext |
| Parameter`conditions` | ContractUse literal text messages only. Cache controls, tools, image/audio/video content and streamed responses are unavailable for this method., The complete encoded JSON request must not exceed 65536 bytes. |

Lifecycle: `synchronous_json`

### Pricing

Tariff references do not add request options. Supported parameters are listed for the selected method.

Fast mode

Standard rate When fast mode is selected

Flex mode

Standard rate When flex mode is selected

Maximum reasoning effort

Standard rate When maximum reasoning effort uses the default adjustment

Text-only zero rates

Text input and output only. Cache, tools, media and streaming are unavailable. For text-only input and output

#### Ailoot rates

#### Prices by configuration

| Configuration | Rate schedule | Charge |
| --- | --- | --- |
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens **$0** / 1K tokens Output · Output tokens **$0** / 1K tokens Input · Cache read **—** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/)

### Example requests

#### Ailoot Ultra · Anthropic Messages

curl · create once and retain the complete result

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
export AILOOT_API_KEY
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "liquid/lfm-2.5-2.6b:free", "messages": [{"role": "user", "content": "Summarize the supplied text in three concise points."}], "stream": false, "max_tokens": 256}')

Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
# Submit once. Retain the complete result, original identifiers and every response header.
```

### Receive and save results

#### Ailoot Ultra · Anthropic Messages

JSON

##### Keep all completed results

Keep every complete returned response, file and content part.

Retain the complete response, all actual results, original identifiers, usage and response headers.

##### If the original response needs checking

Preserve the original response, headers and X-Client-Request-ID. An uncertain outcome does not authorize another creation.

### Aliases

#### Model aliases

**Ailoot Ultra** [`liquid/lfm-2.5-2.6b:free`](https://ailoot.ai/models/en/#m=liquid%2Flfm-2.5-2.6b%3Afree&route=Ultra&caller=liquid%2Flfm-2.5-2.6b%3Afree&fmt=messages)

#### Method path aliases

Use the method paths shown above.

#### Related caller IDs

[`liquid/lfm-2.5-2.6b:free`](https://ailoot.ai/models/en/#m=liquid%2Flfm-2.5-2.6b%3Afree&route=Ultra&caller=liquid%2Flfm-2.5-2.6b%3Afree&fmt=messages)

FAQ · LiquidAI: LFM2.5-2.6B (free)

What inputs and results are available?

`POST /v1/chat/completions` · `liquid/lfm-2.5-2.6b:free`: `text` → `text` `POST /v1/messages` · `liquid/lfm-2.5-2.6b:free`: `text` → `text`

Which fields does the request use?

`POST /v1/chat/completions` · `liquid/lfm-2.5-2.6b:free`: `model`, `messages`, `stream`, `max_tokens`, `max_completion_tokens`, `n`, `temperature`, `top_p`, `seed`, `stop`, `frequency_penalty`, `presence_penalty`, `user` `POST /v1/messages` · `liquid/lfm-2.5-2.6b:free`: `model`, `messages`, `stream`, `system`, `max_tokens`, `temperature`, `top_p`, `top_k`, `stop_sequences`, `metadata`

What limits apply?

`POST /v1/chat/completions` · `liquid/lfm-2.5-2.6b:free`: `ctx`: `65536`; `max_out`: `8192`; `max_tokens.minimum`: `1`; `max_tokens.maximum`: `8192`; `max_completion_tokens.minimum`: `1`; `max_completion_tokens.maximum`: `8192`; `n.minimum`: `1`; `n.maximum`: `128` `POST /v1/messages` · `liquid/lfm-2.5-2.6b:free`: `ctx`: `65536`; `max_out`: `8192`; `max_tokens.minimum`: `1`; `max_tokens.maximum`: `8192`

Connect Ailoot to Claude Code, OpenCode, Hermes or your own app.

## The company and its project portfolio

The company and its project portfolio: millions of customers; monthly sales in the billions.

## Buy tokens at a discount.

Subscription discounts for regular use. Promo codes offer up to 50% off token purchases.

Subscription

Choose a discounted plan for your regular requests.

Promo code: up to 50% off

Enter your code at checkout. The price updates to reflect the current promotion.

Spending in your history

The model, tokens and amount are recorded for each request.

[Choose a subscription](https://ailoot.ai/docs/en/billing/subscriptions/) · [View model prices](https://ailoot.ai/models/en/)

## Connect the API to a product you sell.

Use Ailoot in SaaS, apps and bots under its official service offer and licence agreement. Request a reseller licence for resale.

Commercial application

Add text, image, video and audio generation to paid features in your service.

Reseller licence

Send a description of your project and how you provide access. Request written terms for use and resale.

Documents on the website

The service offer, licence agreement and data processing policy are available before you connect.

[Request a reseller licence](mailto:support@ailoot.ai) · [Service offer and licence agreement](https://ailoot.ai/legal/offer?lang=en)

## Ailoot · The company and its project portfolio





Ailoot combines established operating experience, a large client base, stable service and ongoing KPI control.





The company and its project portfolio: millions of customers; monthly sales in the billions.





Ailoot brings that operating experience to API access for AI features in customer products, agents, applications and automations.