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 2.0 Flash Lite | Multimodal | Text, Image, Audio | Text | 1,048,576 | Hosted API only | Deprecated | 2025-02-05 | |
| o3-deep-research | OpenAI | LLM | Text, Image | Text | 200k | Hosted API only | Active | 2025-02-02 |
| o3-mini | OpenAI | LLM | Text | Text | 200k | Hosted API only | Active | 2025-01-31 |
| Codestral | Mistral AI | LLM | Text | Text | 256k | Hosted API only | Decommissioned | 2025-01-30 |
| gpt-realtime | OpenAI | Multimodal | Text, Image, Audio | Text, Audio | 32k | Hosted API only | Active | 2025-01-28 |
| text-moderation-stable | OpenAI | Moderation | Text | Text | — | Hosted API only | Deprecated | 2025-01-25 |
| o3 | OpenAI | LLM | Text, Image | Text | 200k | Hosted API only | Active | 2025-01-16 |
| GPT-5.1 | OpenAI | LLM | Text, Image | Text | 400k | Hosted API only | Active | 2025-01-12 |
| PaliGemma 2 (3B) | Vision | Text, Image | Text | 8k | Self-hosted only | Active | 2024-12-24 | |
| GPT-4o mini Audio | OpenAI | Multimodal | Text, Image | Text, Audio | 128k | Hosted API only | Active | 2024-12-17 |