OP
Compare- Context window
- 400K
- Input
- Image · Text
- Output
- Text
- Released
- 2025-11-13
- Max output
- 128K
- Knowledge cutoff
- 2024-09-30
- Weights
- Closed
- Capabilities
- Attachments, Reasoning, Structured, Tool call
IN
$1.25
USD / 1,000,000 token
Cache read
$0.125
USD / 1,000,000 token
OUT
$10.00
USD / 1,000,000 token
Performance
| Humanity’s Last Exam(Artificial Analysis) | Reasoning | Artificial Analysis | — | |
| BullshitBench v2 | Knowledge | BullshitBench | — | |
| GDPval-AA | Professional | Artificial Analysis | — | |
| AA-Omniscience(Artificial Analysis) | Knowledge | Artificial Analysis | — | |
| CritPt(Artificial Analysis) | Reasoning | Artificial Analysis | — | |
| IFBench(Artificial Analysis) | Knowledge | Artificial Analysis | — | |
| Chess Puzzles | Reasoning | Epoch AI | — | |
| SimpleQA Verified | Knowledge | Epoch AI | — |
Providers
| Cache write | |||||||
|---|---|---|---|---|---|---|---|
| OpenAI | gpt-5.1 | Openai responses | global | - | |||
| OpenRouter | openai/gpt-5.1 | Openai chat | global | - |
ModelRegistry · Catalog updated 2026-11-05