Back to Models
Liquid
lfm-2.5-24b-a2b
Chat only

LFM2.5-24B-A2B

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...

10/13/2026
128,000 tokens
Input: $0.055/M
Output: $0.77/M

Specifications

Modalities

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

Max Output Tokens

8,192

Reasoning Configuration

Default
Thinking on
Turning thinking off
Not possible (always thinks)

How to control thinking, and what it costs

Data policy

Prompt retention
Unknown — we could not confirm
Training
Not used for training

"Unknown" does not mean "safe". It means we could not confirm it.

Whether a provider trains on prompts is a declared value from our terms with them. Retention is determined from the upstream listing for every host this model can reach. Neither is guessed.

Available in the web chat only

LFM2.5-24B-A2B can be used in FastMetal's web chat, billed per token from your prepaid balance like any other model. It is not available through the API or MCP: a request naming it is refused by the gateway (HTTP 403).

Open in chat

How LFM2.5-24B-A2B actually answers

Real responses to our standard prompts, recorded on FastMetal.

Count the number of 'r's in 'strawberry'

Count the number of 'r's in 'strawberry'. Explain your reasoning step by step.

There are **3** "r"s in "strawberry". Here is the step-by-step reasoning: 1. **Write out the word:** s-t-r-a-w-b-e-r-r-y. 2. **Scan each letter individually:** * s (no) * t (no) * **r** (yes, count = 1) * a (no) * w (no) * b (no) * e (no) * **r** (yes, count = 2) * **r** (yes, count = 3) * y (no) 3. **Sum the counts:** You found an "r" after the "t", and two "r"s near the end before the "y". Therefore, the total count is 3.
79.8s response900 output tokens

Debug This Error

I'm getting the following error in my Node.js application: TypeError: Cannot read properties of undefined (reading 'map') at UserList (/app/components/UserList.js:12:25) at renderWithHooks (/app/node_modules/rea…

**Short answer** The error happens because the `users` prop that `UserList` receives is **undefined** – you’re trying to call `.map()` on something that isn’t an array. Fix it by making sure the prop is always an array (or by guarding against its absence). --- ## Why the error occurs ```js function UserList({ users }) { return ( <ul> {users.map(user => <li key={user.id}>{user.name}</li>)} {/* ← crash here */} </ul> ); } ``` When React renders `<UserList />`, it passes whatever props you gave it. If the parent component didn’t pass a `users` prop (or passed `undefined`), the destructuring `{ users }` yields `undefined`. Calling `.map()` on `undefined` throws: ```…
123.1s response1615 output tokens

Code Review

Please review the following Python function and suggest improvements for readability, performance, and best practices: def get_data(url, retries=3): import requests import time for i in range(retries):…

Below is a concise review of the original `get_data` function, followed by a refactored version that addresses the most common readability, performance, and best‑practice concerns. --- ## 1️⃣ What’s wrong / sub‑optimal in the original code? | Issue | Why it matters | |-------|----------------| | **Imports inside the function** | Importing modules every call adds a tiny overhead and makes the module harder to read. | | **No docstring / type hints** | Future maintainers (including yourself) won’t know what the function expects or returns. | | **Bare `except:` clause** | Catches *everything* – including `KeyboardInterrupt` and system exits – which is almost never what you want. | | **Sleep i…
203.2s response2788 output tokens

Compare these answers side by side with other models →

Frequently asked questions

How much does the LFM2.5-24B-A2B API cost?
On FastMetal, LFM2.5-24B-A2B is billed per token: $0.055 per 1M input tokens and $0.77 per 1M output tokens on a US-dollar account, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.
What is the context window of LFM2.5-24B-A2B?
128,000 tokens, shared between the prompt and the response.
What do I need to try LFM2.5-24B-A2B?
Create an account and add credit; the model is then available both in the browser chat and over the API. There is no contract or minimum spend.

Try LFM2.5-24B-A2B right now

LFM2.5-24B-A2B is available on FastMetal through one API key. Start in the browser, or call it from the OpenAI SDK.