LFM2.5-24B-A2B
- Family
- LFM-2.5
- Released
- 2026-10-13
- Context
- 128K
- Parameters
- 24B
- Architecture
- Mixture of Experts
- Specialization
- general
- Openness
- Open weights
- License
- LFM Open License v1.0Commercial use: conditional
- Weights
- Available
- Code
- Unknown
- Training
- Multi-stage
Cheapest of 3 routes · OpenRouter · cache read $0.025
About
LFM2.5-24B-A2B is Liquid AI's largest LFM2.5 model: a 24B-parameter mixture-of-experts reasoning model with about 2B active parameters per token, built for fast on-device agents. It keeps the LFM2 hybrid of gated short convolutions and GQA (40 layers, 64 experts, top-4 routing), extends context from 32,768 to 131,072 tokens, doubles the vocabulary to 128K, and scales pre-training from 17T to 33T tokens. Unlike LFM2-24B-A2B, it is reasoning-only (explicit chain of thought before the final answer) and is post-trained for tool calling and multi-step agent harnesses.
Providers(3)
Compare all 3Compare API pricing across 3 tracked provider routes for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Cache | Route |
|---|---|---|---|---|
| OpenRouter | $0.050 | $0.700 | read $0.025 | Serverless |
| Vercel AI Gateway | $0.050 | $0.700 | read $0.025 | Serverless |
| Liquid AI | $0.100 | $1.00 | read $0.050 | Serverless |
Capabilities
Benchmark peer barsfor RAG
No task-mapped benchmark peers are available for this model yet.
Benchmark scores(3)
| Benchmark | Score | Version | Evaluation | Source |
|---|---|---|---|---|
| Google-Proof Q&A | 74.4 | GPQA DiamondObserved 2026-10-14 | — | Source |
| Instruction-Following Evaluation | 96.8 | IFEvalObserved 2026-10-14 | — | Source |
| MATH-500 | 96.0 | MATH-500Observed 2026-10-14 | — | Source |
Migration checks
No linked migration route is available for this model yet.
API versions
LFM2.5-24B-A2BLiquidAI/LFM2.5-24B-A2Bliquid/lfm-2.5-24b-a2bliquid/lfm2.5-24b-a2blfm-2.5-24b-a2bCheapest of 3 routes · OpenRouter · cache read $0.025