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 |
|---|---|---|---|---|---|---|---|---|
| Claude Sonnet 4.6 | Anthropic | LLM | Text | Text | 200k | Hosted API only | Active | 2026-02-17 |
| Claude Opus 4.6 | Anthropic | Multimodal | Text, Image | Text | 200k | Hosted API only | Active | 2026-02-05 |
| Voxtral Mini Transcribe 2 | Mistral AI | Audio | Audio | Text | — | Hosted API only | Active | 2026-02-04 |
| Voxtral Mini Transcribe Realtime | Mistral AI | Audio | Audio | Text | — | Hosted API only | Active | 2026-02-04 |
| GPT-5.1-Codex-Max | OpenAI | LLM | Text, Image | Text | 400k | Hosted API only | Active | 2025-12-19 |
| GPT-5.2-codex | OpenAI | LLM | Text, Image | Text | 400k | Hosted API only | Active | 2025-12-18 |
| OCR 3 | Mistral AI | Vision | Image, Document | Text | — | Hosted API only | Active | 2025-12-18 |
| GPT Image 1.5 | OpenAI | Audio | Text, Image | Text, Image | — | Hosted API only | Active | 2025-12-16 |
| chatgpt-image-latest | OpenAI | Vision | Text, Image | Text, Image | — | Hosted API only | Active | 2025-12-16 |
| text-embedding-ada-002 | OpenAI | LLM | Text | Text | — | Hosted API only | Active | 2025-12-15 |