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 |
|---|---|---|---|---|---|---|---|---|
| Gemini 3 Pro Image Preview | Vision | Text, Image | Text, Image | — | Hosted API only | Active | 2025-11-20 | |
| Gemini 3 Pro Preview | Multimodal | Text, Image, Audio, Video, Document | Text | 1,048,576 | Hosted API only | Active | 2025-11-18 | |
| Gemini 3 Flash Preview | Multimodal | Text, Image, Audio, Video, Document | Text | 1,048,576 | Hosted API only | Active | 2025-11-17 | |
| GPT-5.1 Codex mini | OpenAI | LLM | Text, Image | Text | 400k | Hosted API only | Active | 2025-11-13 |
| GPT-5.1 Codex | OpenAI | LLM | Text, Image | Text | 400k | Hosted API only | Active | 2025-11-11 |
| GPT-4o Transcribe Diarize | OpenAI | Audio | Text, Audio | Text | 16k | Hosted API only | Active | 2025-10-18 |
| Claude Haiku 4.5 | Anthropic | Multimodal | Text, Image | Text | 200k | Hosted API only | Active | 2025-10-15 |
| gpt-audio | OpenAI | Audio | Text, Audio | Text, Audio | 128k | Hosted API only | Active | 2025-10-06 |
| gpt-image-1-mini | OpenAI | Vision | Text, Image | Image | — | Hosted API only | Active | 2025-10-06 |
| Gemini 2.5 Flash Image | Vision | Text, Image | Text, Image | — | Hosted API only | Active | 2025-10-02 |