Models
| Provider | Model | Checkpoint | Notes |
|---|---|---|---|
| OpenAI | GPT-5.2 | gpt-5.2-2025-12-11 | Default |
| GPT-4o | gpt-4o-2024-11-20 | Deprecated | |
| GPT-4.1 | gpt-4.1-2025-04-14 | Deprecated | |
| GPT-5 | gpt-5-chat-latest | Deprecated | |
| Anthropic | Claude Sonnet 4.5 | claude-sonnet-4-5-20250929 | |
| Claude Sonnet 4.0 | claude-sonnet-4-20250514 | Deprecated | |
| Gemini 3 Pro | gemini-3-pro-preview | ||
| Gemini 2.5 Pro | gemini-2.5-pro |
How to choose
| Models | Speed | Answer Streaming |
|---|---|---|
| GPT models | Fast | ✅ |
| Gemini models | Slow | ✅ |
| Claude models | Slow | ❌ |
- GPT models are the fastest.
- Gemini and Claude models are also good, but they are slow.
- GPT and Gemini models can stream back the answers.
- This means you can see the answers as they are being generated.
- Claude models do not support streaming, so you have to wait until all the answers are generated.
- Although Gemini models can stream back the answers, they are still slower than GPT models. So it will take some time before the answers start to show up.
How are models updated
- When a new model is released, it will added within one or two weeks.
- If a new model is in preview stage or not stable, its previous stable generation will be kept.
Last updated on