Available models
We currently offer the following models, which may change or expand over time. Each is described along with model-specific parameters.
| Model Name | Type | Modalities | Context (Tokens) | License |
|---|---|---|---|---|
| gpt-oss-120b | Chat + reasoning | Text, tool-calling | 131,072 | Apache 2.0 |
| Ministral-3-14B-Instruct-2512 | Chat + vision | Text, image, tool-calling | 262144 | Apache 2.0 |
| Devstral-Small-2-24B-Instruct-2512 | Chat | Text, image, tool-calling | 262144 | Apache 2.0 |
| Qwen3-Embedding-8B | Embedding | Text to vector | 32,768 | Apache 2.0 |
| Whisper-Large-V3-Turbo | Speech-to-Text | Audio to text | N/A (audio-based) | MIT |
Please have a look on the following pages to gather more information about a specific model:
📄️ Ministral-3-14B-Instruct-2512
Detailled information on Ministral-3-14B-Instruct-2512
📄️ Devstral-Small-2-24B-Instruct-2512
Detailled information on Devstral-Small-2-24B-Instruct-2512
📄️ Qwen3-Embedding-8B
Detailled information on Qwen3-Embedding-8B
📄️ gpt-oss-120b
Detailled information on gpt-oss-120b
📄️ Whisper-Large-V3-Turbo
Detailed information about Whisper-Large-V3-Turbo