Using LFM2.5-2.6B on OpenRouter

Implementation guide · LFM-2.5 · Liquid AI

Serverless
Open Weights

OpenRouter exposes LFM2.5-2.6B through model ID liquid/lfm-2.5-2.6b:free. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-10-19. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at OpenRouter and generate an API key.
  2. 2
    Use the OpenRouter SDK or REST API to call liquid/lfm-2.5-2.6b:free — see the documentation for request format.
  3. 3
    You'll be billed Free/1M input, Free/1M output tokens. See full pricing.
API PortalDocumentationPricingModel Card

Code Examples

See OpenRouter documentation for integration details.

Pricing on OpenRouter

TypePrice (per 1M)
Input tokensFree
Output tokensFree

Capabilities

ReasoningJSON / Tool use

About LFM2.5-2.6B

Liquid AI LFM2.5-2.6B is a 2.69B-parameter hybrid (LFM2 architecture) on-device model with 131,072-token context and agentic post-training. It is a pure reasoning model that always emits a <think> block, and it writes Pythonic function calls between tool-call tokens. It covers 16 languages. Liquid recommends it for agents, tool use, data extraction, RAG and long-context work, but not for agentic coding or knowledge-heavy tasks. Released 4 August 2026 under the LFM Open License v1.0, with GGUF and DSpark variants.

Full model details →

Model Specs

Released2026-08-04
Parameters2.69B
Context128K
ArchitectureDecoder Only

More Models on OpenRouter

LFM2.5-24B-A2B
All models on OpenRouter →

Provider

OpenRouter

OpenRouter, Inc.

New York, NY, USA