liquid

LiquidAI: LFM2.5-2.6B (free)

by liquid

OpenRouter
Tools Reasoning

Availability

Available 17 of 17 tracked days. Daily snapshots show whether this model was accessible as a free model on OpenRouter.

JulAug
ModelDays293031123456789101112131415161718192021222324252627
LiquidAI: LFM2.5-2.6B (free)17

About

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

Context Length 66K
Max Output Tokens 8K
Modality text->text
Input text
Output text
Supported Parameters frequency_penalty, include_reasoning, logprobs, max_completion_tokens, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p
Content Moderation No

Error Rate

Based on feedback reported by Free LLM Router users. Error rate reflects the percentage of requests that encountered issues such as rate limiting, unavailability, or errors. Learn more.

Loading chart...
Model 1h 6h 24h 7d 30d
LiquidAI: LFM2.5-2.6B (free) - - - 93.6% 93.6%

Similar Models

More from Liquid

Frequently Asked Questions

Is LiquidAI: LFM2.5-2.6B (free) free to use?

Yes, LiquidAI: LFM2.5-2.6B (free) is completely free to use through OpenRouter. You can access it via the Free LLM Router API at no cost.

What is the context window for LiquidAI: LFM2.5-2.6B (free)?

LiquidAI: LFM2.5-2.6B (free) supports a context window of 66K tokens (65,536 tokens).

What is the maximum output length for LiquidAI: LFM2.5-2.6B (free)?

LiquidAI: LFM2.5-2.6B (free) can generate up to 8K tokens (8,192 tokens) per response.

Does LiquidAI: LFM2.5-2.6B (free) support function calling (tools)?

Yes, LiquidAI: LFM2.5-2.6B (free) supports function calling / tool use, enabling it to interact with external APIs and services.

Does LiquidAI: LFM2.5-2.6B (free) support reasoning?

Yes, LiquidAI: LFM2.5-2.6B (free) supports reasoning capabilities, allowing it to show its step-by-step thought process.