How much does LFM2.5-24B-A2B cost?

LFM2.5-24B-A2B costs $0.05/M input tokens and $0.70/M output tokens, with separate rates for Cache Read at $0.025/M tokens.

What is the context length of LFM2.5-24B-A2B?

LFM2.5-24B-A2B has a 128,000 token context window. It supports up to 8,192 completion tokens.

Does LFM2.5-24B-A2B support tool calling and structured outputs?

Yes. LFM2.5-24B-A2B accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

Which providers serve LFM2.5-24B-A2B?

LFM2.5-24B-A2B is served by 1 provider on OpenRouter: Liquid.

What other text models does Liquid have?

LFM3-1.7B, d1.1, d1-ultra and 1 more are other text models from Liquid.

When was LFM2.5-24B-A2B released?

LFM2.5-24B-A2B was released on October 13, 2026.

LiquidAI: LFM2.5-24B-A2B

liquid/lfm-2.5-24b-a2b

Model weights

Compare

LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid recommends pairing it with retrieval or web search for knowledge-heavy tasks.

Modalities

In / out price

$0.05 / $0.70per 1M

Context

128K

Released

Oct 13, 2026

Providers

This model is hosted by one provider. OpenRouter forwards every request without routing.

Latency / throughput


	$0.05	$0.70	$0.025	0.21s	207 tok/s	100.00%

Input $0.05Output $0.70
207 tok/s100.00% uptime

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Weighted average

Input

$0.03183/M tokens

Output

$0.699/M tokens

LFM2.5-24B-A2B — Price history

Price history

No effective price data for this selection

		$0.0318	$0.699	72.5%	100.0%

Effective in $0.0318Effective out $0.699
Token share
100.0%

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)

100.00%

Availability (3d)

93.85%

Availability over the last 3 days

Last 72 hours

Availability 93.85%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

96.01%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Hermes Agent

Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.

260Mtokens

There are many coding agents, but this one is yours.

181Mtokens

Tolokaforge Evaluation

new

180Mtokens

Rayline

new

84.4Mtokens

Hivey AI

new

56.6Mtokens

Top 5 Apps

79.9M

Rest of OpenRouter

59.1M

Not currently available through EU in-region routing. In-region routing docs

More models from Liquid

LFM3-1.7B

A compact 1.7B-parameter text model with a 256K-token context, post-trained for agents, tool calling, and structured outputs. It reasons before it answers. Prompts and outputs may be retained and used to train Liquid models.

Text262K context$0.08 / $0.20

LFM3-1.7B (free)

Text262K contextFree

d1.1

d1.1 is Liquid AI's structured decision model, served as a System One endpoint and the successor to d1. Send a state along with typed questions, and it returns a choice, a score, or a yes/no answer, each with a probability taken directly from the model rather than written out as text. It uses the same /v1/systemone schema as other OpenRouter Decisions models, so it suits routing, classification, and policy checks that need a fast, scored answer instead of prose.

Decisions$0.02 / $0

d1-ultra Latest

This model always redirects to the latest model in the d1-ultra family.

Decisions

d1 Latest

This model always redirects to the latest model in the d1 family.

Decisions

d1-ultra

d1-ultra is Liquid AI's largest decision model, served as a System One endpoint. Send a state of text and images along with typed questions, and it returns a choice, a score, or a yes/no answer, each with a probability taken directly from the model rather than written out as text. It uses the same /v1/systemone schema as other OpenRouter Decisions models, so it suits routing, classification, moderation, and visual checks that need a fast, scored answer instead of prose.

Decisions$0.042 / $0

d1 is Liquid AI's structured decision model, served as a System One endpoint. Send a state along with typed questions, and it returns a choice, a score, or a yes/no answer, each with a probability taken directly from the model rather than written out as text. It uses the same /v1/systemone schema as other OpenRouter Decisions models, so it suits routing, classification, and policy checks that need a fast, scored answer instead of prose.

Decisions$0.02 / $0

LFM2.5-Embedding-350M

LFM2.5-Embedding-350M is a text embedding model from Liquid AI. It produces 1,024-dimensional embeddings for retrieval and semantic search.

Successful OpenRouter requests and embeddings may be retained and used to train Liquid models.

Embeddings

LFM2.5-2.6B

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 knowledge-heavy tasks.

Prompts and outputs may be retained and used to train Liquid models.

Text131K context

LFM2-24B-A2B

LFM2-24B-A2B is the largest model in the LFM2 family of hybrid architectures designed for efficient on-device deployment. Built as a 24B parameter Mixture-of-Experts model with only 2B active parameters per token, it delivers high-quality generation while maintaining low inference costs. The model fits within 32 GB of RAM, making it practical to run on consumer laptops and desktops without sacrificing capability.

Text128K context

LFM2.5-1.2B-Thinking

LFM2.5-1.2B-Thinking is a lightweight reasoning-focused model optimized for agentic tasks, data extraction, and RAG—while still running comfortably on edge devices. It supports long context (up to 32K tokens) and is designed to provide higher-quality “thinking” responses in a small 1.2B model.

Text33K context

LFM2.5-1.2B-Instruct

LFM2.5-1.2B-Instruct is a compact, high-performance instruction-tuned model built for fast on-device AI. It delivers strong chat quality in a 1.2B parameter footprint, with efficient edge inference and broad runtime support.

Text33K context

LFM2-8B-A1B

LFM2-8B-A1B is an efficient on-device Mixture-of-Experts (MoE) model from Liquid AI’s LFM2 family, built for fast, high-quality inference on edge hardware. It uses 8.3B total parameters with only ~1.5B active per token, delivering strong performance while keeping compute and memory usage low—making it ideal for phones, tablets, and laptops.

Text8K context

LFM2-2.6B

LFM2 is a new generation of hybrid models developed by Liquid AI, specifically designed for edge AI and on-device deployment. It sets a new standard in terms of quality, speed, and memory efficiency.

Text33K context

LFM 7B

LFM-7B, a new best-in-class language model. LFM-7B is designed for exceptional chat capabilities, including languages like Arabic and Japanese. Powered by the Liquid Foundation Model (LFM) architecture, it exhibits unique features like low memory footprint and fast inference speed.

LFM-7B is the world’s best-in-class multilingual language model in English, Arabic, and Japanese.

See the launch announcement for benchmarks and more info.

Text33K context

LFM 3B

Liquid's LFM 3B delivers incredible performance for its size. It positions itself as first place among 3B parameter transformers, hybrids, and RNN models It is also on par with Phi-3.5-mini on multiple benchmarks, while being 18.4% smaller.

LFM-3B is the ideal choice for mobile and other edge text-based applications.

See the launch announcement for benchmarks and more info.

Text33K context

LFM 40B MoE

Liquid's 40.3B Mixture of Experts (MoE) model. Liquid Foundation Models (LFMs) are large neural networks built with computational units rooted in dynamic systems.

LFMs are general-purpose AI models that can be used to model any kind of sequential data, including video, audio, text, time series, and signals.

See the launch announcement for benchmarks and more info.

Text33K context

LiquidAI: LFM2.5-24B-A2B

Providers