Models
| Provider | Model | Checkpoint | Notes |
|---|---|---|---|
| OpenAI | GPT-5.6 Luna | gpt-5.6-luna | Default |
| GPT-5.4 | gpt-5.4-2026-03-05 | Deprecated | |
| GPT-5.2 | gpt-5.2-2025-12-11 | Deprecated | |
| GPT-5 | gpt-5-chat-latest | Deprecated | |
| GPT-4.1 | gpt-4.1-2025-04-14 | Deprecated | |
| GPT-4o | gpt-4o-2024-11-20 | Deprecated | |
| Anthropic | Claude Opus 4.8 | claude-opus-4-8 | |
| Claude Sonnet 4.5 | claude-sonnet-4-5-20250929 | Deprecated | |
| Claude Sonnet 4.0 | claude-sonnet-4-20250514 | Deprecated | |
| Gemini 3.5 Flash | gemini-3.5-flash | ||
| Gemini 3.1 Pro | gemini-3.1-pro-preview | Deprecated | |
| Gemini 3 Pro | gemini-3-pro-preview | Deprecated | |
| Gemini 2.5 Pro | gemini-2.5-pro | Deprecated |
How to choose
| Models | Speed | Answer Streaming |
|---|---|---|
| GPT-5.6 Luna | Fast | ✅ |
| Gemini 3.5 Flash | Fast | ✅ |
| Claude Opus 4.8 | Slow | ✅ |
- GPT-5.6 Luna and Gemini 3.5 Flash are the fastest and start returning answers soonest.
- Claude Opus 4.8 is the most capable but the slowest, so it takes a bit longer before the answers start to show up.
How are models updated
- When a new model is released, it will be 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