Side-by-side comparison · models
Kimi K2.5 vs Kimi K2.6
What we have checked about each, line by line. Every value shows where it came from and when we last confirmed it.
Models
Kimi K2.5
Kimi multimodal agent model for visual understanding, coding, and planning.
Models
Kimi K2.6
Kimi multimodal agent model for visual understanding, coding, and planning.
Checked facts
Line by line
| Measure | Kimi K2.5 | Kimi K2.6 |
|---|---|---|
| Input price | $0.532 per million tokens | $0.650 per million tokens |
| Output price | $3.33 per million tokens | $3.41 per million tokens |
| Price on amazon-bedrock | $0.600 per million input tokens | Not checked yet |
| Price on amazon-bedrock | $3.00 per million output tokens | Not checked yet |
| Price on atlas-cloud | $0.200 per million cached input tokens | $0.160 per million cached input tokens |
| Price on atlas-cloud | $0.490 per million input tokens | $0.950 per million input tokens |
| Price on atlas-cloud | $2.50 per million output tokens | $4.00 per million output tokens |
| Price on novita | $0.095 per million cached input tokens | $0.160 per million cached input tokens |
| Price on novita | $0.570 per million input tokens | $0.800 per million input tokens |
| Price on novita | $2.85 per million output tokens | $3.40 per million output tokens |
| Price on siliconflow | $0.150 per million cached input tokens | $0.140 per million cached input tokens |
| Price on siliconflow | $0.500 per million input tokens | $0.770 per million input tokens |
| Price on siliconflow | $2.50 per million output tokens | $3.40 per million output tokens |
| Price on venice | $0.209 per million cached input tokens | $0.160 per million cached input tokens |
| Price on venice | $0.532 per million input tokens | $0.750 per million input tokens |
| Price on venice | $3.33 per million output tokens | Not checked yet |
| Price on baidu | Not checked yet | $0.066 per million cached input tokens |
| Price on baidu | Not checked yet | $0.390 per million input tokens |
| Price on baidu | Not checked yet | $1.64 per million output tokens |
| Price on chutes | Not checked yet | $0.039 per million cached input tokens |
| Price on chutes | Not checked yet | $0.390 per million input tokens |
| Price on chutes | Not checked yet | $1.80 per million output tokens |
| Price on cloudflare | Not checked yet | $0.160 per million cached input tokens |
| Price on cloudflare | Not checked yet | $0.950 per million input tokens |
| Price on cloudflare | Not checked yet | $4.00 per million output tokens |
| Price on coreweave | Not checked yet | $0.150 per million cached input tokens |
| Price on coreweave | Not checked yet | $0.650 per million input tokens |
| Price on coreweave | Not checked yet | $3.41 per million output tokens |
| Price on crusoe | Not checked yet | $0.350 per million cached input tokens |
| Price on crusoe | Not checked yet | $0.700 per million input tokens |
| Price on crusoe | Not checked yet | $3.50 per million output tokens |
| Price on deepinfra | Not checked yet | $0.150 per million cached input tokens |
| Price on deepinfra | Not checked yet | $0.750 per million input tokens |
| Price on deepinfra | Not checked yet | $3.50 per million output tokens |
| Price on digitalocean | Not checked yet | $0.114 per million cached input tokens |
| Price on digitalocean | Not checked yet | $0.570 per million input tokens |
| Price on digitalocean | Not checked yet | $2.40 per million output tokens |
| Price on gmicloud | Not checked yet | $0.144 per million cached input tokens |
| Price on gmicloud | Not checked yet | $0.855 per million input tokens |
| Price on gmicloud | Not checked yet | $3.60 per million output tokens |
| Price on inceptron | Not checked yet | $0.209 per million cached input tokens |
| Price on inceptron | Not checked yet | $0.799 per million input tokens |
| Price on inceptron | Not checked yet | $3.75 per million output tokens |
| Price on moonshotai | Not checked yet | $0.160 per million cached input tokens |
| Price on moonshotai | Not checked yet | $0.950 per million input tokens |
| Price on moonshotai | Not checked yet | $4.00 per million output tokens |
| Price on parasail | Not checked yet | $0.160 per million cached input tokens |
| Price on parasail | Not checked yet | $0.750 per million input tokens |
| Price on parasail | Not checked yet | $3.50 per million output tokens |
| Price on phala | Not checked yet | $0.370 per million cached input tokens |
| Price on phala | Not checked yet | $1.09 per million input tokens |
| Price on phala | Not checked yet | $4.60 per million output tokens |
| Price on streamlake | Not checked yet | $0.101 per million cached input tokens |
| Price on streamlake | Not checked yet | $0.599 per million input tokens |
| Price on streamlake | Not checked yet | $2.52 per million output tokens |
| Latest version | moonshotai/kimi-k2.5-0127 | moonshotai/kimi-k2.6-20260420 |
| Time to first token (ms) | 1,900 | 3,020 |
| Time to first token (ms) on amazon-bedrock | 1,420 | Not checked yet |
| Time to first token (ms) on atlas-cloud | 864 | 1,363 |
| Time to first token (ms) on novita | 1,715 | 3,680 |
| Time to first token (ms) on siliconflow | 1,655 | 1,102 |
| Time to first token (ms) on venice | 928 | 1,123 |
| Output speed (tokens a second) | 51.7 | 42.5 |
| Output speed (tokens a second) on amazon-bedrock | 91 | Not checked yet |
| Output speed (tokens a second) on atlas-cloud | 42.5 | 28 |
| Output speed (tokens a second) on novita | 37 | 24.5 |
| Output speed (tokens a second) on siliconflow | 23 | 22 |
| Output speed (tokens a second) on venice | 44 | 15 |
| Time to first token (ms) on baidu | Not checked yet | 784 |
| Time to first token (ms) on chutes | Not checked yet | 1,763 |
| Time to first token (ms) on cloudflare | Not checked yet | 725 |
| Time to first token (ms) on coreweave | Not checked yet | 355 |
| Time to first token (ms) on crusoe | Not checked yet | 404 |
| Time to first token (ms) on deepinfra | Not checked yet | 1,430 |
| Time to first token (ms) on digitalocean | Not checked yet | 1,289 |
| Time to first token (ms) on inceptron | Not checked yet | 850 |
| Time to first token (ms) on moonshotai | Not checked yet | 3,120 |
| Time to first token (ms) on parasail | Not checked yet | 1,290 |
| Time to first token (ms) on phala | Not checked yet | 2,642 |
| Time to first token (ms) on streamlake | Not checked yet | 1,877 |
| Output speed (tokens a second) on baidu | Not checked yet | 81 |
| Output speed (tokens a second) on chutes | Not checked yet | 27 |
| Output speed (tokens a second) on cloudflare | Not checked yet | 83 |
| Output speed (tokens a second) on coreweave | Not checked yet | 134 |
| Output speed (tokens a second) on crusoe | Not checked yet | 83 |
| Output speed (tokens a second) on deepinfra | Not checked yet | 13 |
| Output speed (tokens a second) on digitalocean | Not checked yet | 29.5 |
| Output speed (tokens a second) on inceptron | Not checked yet | 68 |
| Output speed (tokens a second) on moonshotai | Not checked yet | 27 |
| Output speed (tokens a second) on parasail | Not checked yet | 59 |
| Output speed (tokens a second) on phala | Not checked yet | 25 |
| Output speed (tokens a second) on streamlake | Not checked yet | 36 |
| Tokens served on OpenRouter in a day | 2.6B (for 7 Nov 2026) | 12.1B (for 7 Nov 2026) |
| Tool calls on OpenRouter in a day | 18.9K (for 7 Nov 2026) | 174.7K (for 7 Nov 2026) |
| Artificial Analysis Intelligence Index | 23.5 | 27 |
| Artificial Analysis Coding Index | 46.8 | 61.8 |
| LMArena text rating (Elo) | 1,445 | 1,456 |
| LMArena web development rating (Elo) | 1,436 | 1,509 |
| LMArena vision rating (Elo) | 1,269 | 1,282 |
| Design Arena rating (Elo) | 1,247 | 1,276 |
| Artificial Analysis Agentic Index | Not checked yet | 20.5 |
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.