Kimi
Kimi K3
Kimi’s flagship model for long-horizon coding and end-to-end knowledge work, with a 1M-token context window.
Kimi model releasesModel Snapshot
TypeLanguage
ReleaseJul 16, 2026
Context1,048,576
Tagsreasoning, tool-use, implicit-caching, file-input
Overall
Rank #5 across 589
57.1
Coding
Rank #8 across 252
76.2
Blended Price
Rank #332 across 369
$6.00/M
Strength Profile
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Benchmark Percentiles
Higher bars mean stronger relative placement.
Model Details
Runtime
Output Speed38.4 tok/s
First Token5.79s
Max Output131,072
Pricing
Blended$6.00/M
Input$3.00/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 57.1 | #5 |
| Artificial Analysis Coding Index | coding | 76.2 | #8 |
| LiveBench Mathematics | math | 84.4% | #23 |
| GPQA | reasoning | 93.5% | #4 |