Side-by-side comparison · models
Kimi K2 0905 vs Kimi K2 Thinking
What we have checked about each, line by line. Every value shows where it came from and when we last confirmed it.
Models
Kimi K2 0905
Kimi K2 0905 is the September update of Kimi K2 0711.
Models
Kimi K2 Thinking
Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning.
Checked facts
Line by line
| Measure | Kimi K2 0905 | Kimi K2 Thinking |
|---|---|---|
| Input price | $0.600 per million tokens | $0.600 per million tokens |
| Output price | $2.50 per million tokens | $2.50 per million tokens |
| Price on novita | $0.600 per million input tokens | $0.600 per million input tokens |
| Price on novita | $2.50 per million output tokens | $2.50 per million output tokens |
| Price on google-vertex | Not checked yet | $0.600 per million input tokens |
| Price on google-vertex | Not checked yet | $2.50 per million output tokens |
| Price on novita | Not checked yet | $0.150 per million cached input tokens |
| Latest version | moonshotai/kimi-k2-0905 | moonshotai/kimi-k2-thinking-20251106 |
| Time to first token (ms) | 1,680 | 1,750 |
| Time to first token (ms) on novita | 827 | 1,474 |
| Output speed (tokens a second) | 41.2 | 122 |
| Output speed (tokens a second) on novita | 38 | 44 |
| Tokens served on OpenRouter in a day | 492.6M (for 10 Nov 2026) | 338.8M (for 10 Nov 2026) |
| Tool calls on OpenRouter in a day | 4.6K (for 10 Nov 2026) | 4.4K (for 10 Nov 2026) |
| Artificial Analysis Intelligence Index | 15.3 | 22 |
| Design Arena rating (Elo) | 1,103 | 1,109 |
| Artificial Analysis Coding Index | Not checked yet | 21 |
A line appears only when at least one record has a value we confirmed from a source. Values we have not confirmed are left out, never guessed. Records of different types share fewer lines.
Add a third
Compare with one more record
How this works
Share it, or build your own
This page works for any two or three records in the directory, of any type. The link stays the same whichever order you name them in, so you can share it as it is. Change the records in the address, for example /directories/vs/claude-code-vs-cursor, or start from our editorial comparisons.