Models / Compare /Kimi K2.6 vs Kimi K2.7 Code
Head to head
Kimi K2.6 vs Kimi K2.7 Code
Compared on live catalog data — pricing synced daily, benchmark scores with provenance.
The short version
- Kimi K2.6 is cheaper to run hosted: $2.48/M output vs $3.50/M for Kimi K2.7 Code (1.4× difference at the cheapest tracked provider).
- Kimi K2.6 scores 70.54 via Thinking on LiveBench vs 68.41 for Kimi K2.7 Code.
- Kimi K2.6 scores 46.92 via Thinking on LiveBench Agentic Coding vs 45.66 for Kimi K2.7 Code.
| Spec | ||
|---|---|---|
| Vendor | Moonshot AI | Moonshot AI |
| Parameters | 1.1T / 32B | 1.1T / 32B |
| 262K | 262K | |
| Weights | OPEN* | OPEN* |
| License | Custom licence | Custom licence |
| Modality | text+image->text | text+image->text |
| Released | Apr 14, 2026 | Jun 11, 2026 |
| 667.5 GBest | 667.5 GBest | |
| Cheapest hosted | $0.59 / $2.48 per 1M (OpenRouter) | $0.73 / $3.50 per 1M (OpenRouter) |
| Tracked providers | 26 | 20 |
Kimi K2.6 — our take
Kimi K2.6 is a large mixture-of-experts model from Moonshot AI that accepts text and images and handles up to 262,144 tokens in a single request. It is the strongest coder in our measured set, with a coding score well above its general chat rating, though its creative writing lags behind both.
full breakdown →Kimi K2.7 Code — our take
Moonshot's very large coding model can be downloaded. At over a trillion parameters it is an unusually large model to be downloadable at all, aimed at agentic coding workloads where scale matters.
full breakdown →Need more columns? Use theinteractive comparison to add up to four models.