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 |
|---|---|---|---|---|---|---|---|---|
| Voxtral Mini | Mistral AI | Audio | Text, Audio | Text | 32k | Hosted API only | Active | 2025-07-15 |
| Voxtral Small | Mistral AI | Audio | Text, Audio | Text | 32k | Hosted API only | Active | 2025-07-15 |
| Voxtral Mini Transcribe | Mistral AI | Audio | Audio | Text | 32k | Hosted API only | Active | 2025-07-15 |
| Devstral Medium 1.0 | Mistral AI | LLM | Text | Text | 128k | Hosted API only | Active | 2025-07-10 |
| Devstral Small 1.1 | Mistral AI | LLM | Text | Text | 128k | Hosted API only | Active | 2025-07-10 |
| Mistral Small 3.0 | Mistral AI | Multimodal | Text, Image | Text | 32,768 | Self-hosted + Hosted API | Decommissioned | 2025-06-30 |
| o4-mini-deep-research | OpenAI | LLM | Text, Image | Text | 200k | Hosted API only | Active | 2025-06-24 |
| Mistral Small 3.2 | Mistral AI | Multimodal | Text, Image | Text | 128k | Self-hosted + Hosted API | Active | 2025-06-20 |
| Gemini 2.5 Flash | Multimodal | Text, Image, Audio, Video | Text | 1,048,576 | Hosted API only | Active | 2025-06-17 | |
| Gemini 2.5 Flash Preview | Multimodal | Text, Image, Audio, Video | Text | 1,048,576 | Hosted API only | Decommissioned | 2025-06-17 |