Kimi K2 Thinking is a text-based AI model by Kimi. It features 89 tok/s output speed, $0.60/1M input tokens pricing. It scores 40.9 on the intelligence index.
Output Speed
89 tok/s
Latency (TTFT)
0.66s
Blended Price
$1.07/M
| Input (Prompt) | $0.60 |
| Output (Completion) | $2.50 |
| Cache Read | Free |
| Cache Write | Free |
| Context Length | N/A |
| Max Output Tokens | N/A |
| Input Modalities | Text |
| Output Modalities | Text |
| Tokenizer | N/A |
Kimi K2 Thinking costs $0.60/1M input tokens and $2.50/1M output tokens.
Kimi K2 Thinking has a moderate coding score of 34.8. It can handle basic programming tasks but may not be the best for complex coding.
Kimi K2 Thinking generates output at 89 tok/s. Time to first token is 0.66s.
No, Kimi K2 Thinking is a paid model. Check the free models page for zero-cost alternatives.
Last updated:
See the alternatives section above for models with similar capabilities. You can also compare Kimi K2 Thinking head-to-head with any model on our comparison page.