LFM3 audio-language model for speech recognition, dialogue and speech output.
Released
Oct 27, 2026
Context window
Not disclosed
Max output
Not disclosed
Parameters
2B
Input price
Not disclosed
Output price
Not disclosed
Prices are first-party list prices in USD at the standard tier. Last verified Oct 30, 2026.
Pricing
No first-party API. This is an open-weights release you can run yourself.
Specifications
- Developer
- Liquid AI
- Model type
- Multimodal
- Architecture
- Hybrid
- Parameters
- 2B
- Input
- Text Audio
- Output
- Text Audio
- Knowledge cutoff
- Not disclosed
- License
- LFM Open License v1.0
- API access
- No first-party API
- Capabilities
- Small LM