ST
Compare- Context window
- 1M
- Input
- Image · Text · Video
- Output
- Text
- Released
- 2026-09-20
- Max output
- 64K
- Model parameters
- 600B
- Active parameters
- 27B
IN
¥7.00
CNY / 1,000,000 token
Cache read
¥0.35 – ¥0.70
CNY / 1,000,000 token
¥0.35 · CNY/1M tokens; all users before 2026-10-14 00:30 Asia/Shanghai, and grandfathered users who used the pay-as-you-go API before that time thereafter
¥0.70 · CNY/1M tokens; effective from 2026-10-14 00:30 Asia/Shanghai for users who had not called the pay-as-you-go API before that time
OUT
¥20.00
CNY / 1,000,000 token
Performance
Overall capability
57.0/100
- Coding
- 59.6
- Reasoning
- 50.2
- Professional work
- 58.6
- Knowledge & language
- 59.7
| Humanity’s Last ExamStep 5 Preview | Reasoning | Artificial Analysis | 2026-11-05 | |
| AutomationBench-AAStep 5 Preview | Professional work | Artificial Analysis | 2026-11-05 | |
| AA-LCRStep 5 Preview | Knowledge & language | Artificial Analysis | 2026-11-05 | |
| MysteryMechanism | Reasoning | Vals AI | 2026-11-05 | |
| AA-OmniscienceStep 5 Preview | Knowledge & language | Artificial Analysis | 2026-11-05 | |
| Terminal-Bench 4.0 (AA rerun)Step 5 Preview | Coding | Artificial Analysis | 2026-11-05 | |
| Harvey Legal Agent Benchmark | Professional work | Vals AI / Harvey | 2026-11-05 | |
| Finance Agent | Professional work | Vals AI | 2026-11-05 |
Providers
No providers found
ModelRegistry · Catalog updated 2026-11-05