Liquid AI · Released Feb 24, 2026LFM2 24B A2B
Efficient open Liquid MoE instruct model for on-device chat and tool calling.
- Capability
- —No ECI score yet
- Input
- $0.03per 1M tokens
- Output
- $0.12per 1M tokens
- Context
- 33K33K max output
What it costs
- Input
- $0.03per million tokens
- Output
- $0.12per million tokens
- Blended (3:1)
- $0.052cheaper than 96% of priced models
Typical monthly bills
| Monthly usage | Estimated cost |
|---|---|
| Side project2M input + 0.5M output tokens | $0.12 |
| Team assistant25M input + 5M output tokens | $1.35 |
| Production app250M input + 50M output tokens | $13.50 |
Median of 1 paid API provider on models.dev.
Independent benchmarks
Epoch AI has not published a Capabilities Index score for LFM2 24B A2B yet.
The details
- Lab
- Liquid AI
- Released
- Feb 24, 2026
- Context window
- 32,768 tokens
- Max output
- 32,768 tokens
- Inputs
- Text
- Output
- Text
- Reasoning
- No
- Tool calling
- Yes
- Structured output
- No
- Availability
- 1 API providerlisted on models.dev
About LFM2 24B A2B
How much does LFM2 24B A2B cost?
LFM2 24B A2B costs $0.03 input / $0.12 output per million tokens (median across 1 API provider). At a 3:1 input-to-output mix that is $0.052 per million tokens, cheaper than 96% of the 445 priced models we track.
What is the context window of LFM2 24B A2B?
LFM2 24B A2B accepts up to 32,768 tokens per request and can write up to 32,768 tokens in one response.
How good is LFM2 24B A2B?
Epoch AI has not published a Capabilities Index score for LFM2 24B A2B yet.
Is LFM2 24B A2B open source?
Yes. Liquid AI publishes the weights under the LFM Open License v1.0 licence, so it can be downloaded and self-hosted.
What inputs does LFM2 24B A2B support?
LFM2 24B A2B accepts text and replies in text. It is not a dedicated reasoning model, supports tool calling.
When was LFM2 24B A2B released?
Liquid AI released LFM2 24B A2B on Feb 24, 2026.
What are the best alternatives to LFM2 24B A2B?
The closest current models from other labs on capability, price and release date are Qwen3.5 4B (Alibaba (Qwen), $0.04 / $0.07), Gemma 4 E2B IT (Google, $0.04 / $0.08), Schematron V2 Turbo (Inference.net, $0.03 / $0.15) and AutoGLM Phone 9B Multilingual (Z.ai (Zhipu), $0.035 / $0.138).