Models
Currently supported providers: OpenAI, Google, Anthropic, Meta, and Mistral AI. See the Model Inclusion Policy for details on selection criteria.
| Model | Provider | Type | Input Modality | Output Modality | Context (tokens) | Deployment Option | Status | Release Date |
|---|---|---|---|---|---|---|---|---|
| Gemma 3 (12B) | Multimodal | Text, Image | Text | 128k | Self-hosted only | Active | 2025-03-10 | |
| Gemma 3 (27B) | Multimodal | Text, Image | Text | 128k | Self-hosted only | Active | 2025-03-10 | |
| OCR | Mistral AI | Vision | Image | Text | — | Hosted API only | Active | 2025-03-06 |
| GPT-4.5 Preview | OpenAI | Multimodal | Text, Image | Text | 128k | Hosted API only | Deprecated | 2025-02-27 |
| Claude 3.7 Sonnet | Anthropic | Multimodal | Text, Image | Text | 200k | Hosted API only | Active | 2025-02-24 |
| Magistral Medium 1.1 | Mistral AI | Multimodal | Text, Image | Text | 128k | Hosted API only | Decommissioned | 2025-02-24 |
| Mistral Saba | Mistral AI | Multimodal | Text, Image | Text | 32k | Self-hosted + Hosted API | Decommissioned | 2025-02-17 |
| Gemma 3 (4B) | Multimodal | Text, Image | Text | 128k | Self-hosted only | Active | 2025-02-10 | |
| Devstral Small 2 | Mistral AI | Multimodal | Text, Image | Text | 256k | Hosted API only | Active | 2025-02-09 |
| Gemini 2.0 Flash | Multimodal | Text, Image, Audio, Video | Text | 8,192 | Hosted API only | Deprecated | 2025-02-05 |