LFM-2 Models by Liquid AI
2 models2025Up to 32k ctxFrom $0.03/1M input
About
LFM-2 (Liquid Foundation Model 2) is Liquid AI's second-generation hybrid architecture model series, combining attention-based and structured state-space layers for efficient long-context inference.
Current Variants
Use-when guidance is derived from seed capabilities, context, release, and replacement fields.
2 in view
Together LFM2-24BCurrent
Use when the workload needs 8k context and 23.8B parameters.
2025-128k context23.8B parameters
LFM2-24B-A2BCurrent
Use when the workload needs 32k context, 24B parameters, and tool use.
2025-1132k context24B parameterstool use
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Together LFM2-24B | Use when the workload needs 8k context and 23.8B parameters. | 2025-12 | 8k context23.8B parameters | Current |
| LFM2-24B-A2B | Use when the workload needs 32k context, 24B parameters, and tool use. | 2025-11 | 32k context24B parameterstool use | Current |
Release Timeline
2 release groups2025-12
1 current
Together LFM2-24B
Current8k context23.8B parameters
2025-11
1 current
LFM2-24B-A2B
Current32k context24B parameterstool use
Specifications(2 models)
| Model | Released | Context | Parameters | Fn Calling | Tool Use | Structured Outputs |
|---|---|---|---|---|---|---|
| Together LFM2-24B | 2025-12 | 8k | 23.8B | No | No | No |
| LFM2-24B-A2B | 2025-11 | 32k | 24B | Yes | Yes | Yes |
Available From(1 provider)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| LFM2-24B-A2B | OpenRouter | $0.03 | $0.12 | Serverless |
Frequently Asked Questions
- What is LFM-2 used for?
- LFM-2 is used for agent workflows and tool use and structured outputs. The family description and listed model capabilities point to those workloads as the best fit.
- How does LFM-2 compare to LFM-2.5?
- LFM-2 by Liquid AI is strongest where you need agent workflows and tool use, while LFM-2.5 by Liquid AI is the closest related family to check for reasoning. LFM-2 has 2 listed variants and reaches up to 32k context, while LFM-2.5 reaches up to 128k context, so compare the specs and pricing tables before choosing a production model.
- Which LFM-2 model should I use?
- For the lowest listed input price, start with LFM2-24B-A2B through OpenRouter at $0.03/1M input tokens. For the most capable/latest local choice, evaluate LFM2-24B-A2B with 32k context and tool use, function calling, and structured outputs.
