Kimi K2.7 Code Highspeed
| Maker | Moonshot |
|---|---|
| Family | Kimi Code |
| Released | 2026-06-12 |
| Context | 262.1K |
| Max output | 262.1K |
|---|---|
| Open weights | Modified MIT |
| Modalities | text, image, video → text |
| Input / 1M | $1.90 |
| Output / 1M | $8.00 |
|---|---|
| Review call | $0.0691 |
| Hosts | Moonshot (Kimi) |
| Model id | kimi-k2.7-code-highspeed |
CodePanel's benchmark has not run Kimi K2.7 Code Highspeed as a pull-request reviewer yet, so this page has no recall, false-alarm or measured-cost figures for it. The methodology explains how ranked models are scored.
The newest ranked model in the Kimi Code line is Kimi K2.7 Code (Workers AI). It caught 38% [28%–47%] of the known bugs at rank 11 of 17, with a measured review cost of $0.0567. At list price, a typical review call (26.2K tokens in and 2.4K out) costs $0.0691 on Kimi K2.7 Code Highspeed and $0.0346 on Kimi K2.7 Code (Workers AI), so this model's call is 2.0× the cost of that one's.
| Host | Model id | Input / 1M | Output / 1M |
|---|---|---|---|
| Moonshot (Kimi) | kimi-k2.7-code-highspeed | $1.90 | $8.00 |
Source: Moonshot pricing, Oct 16, 2026
| Version | Released | Input / 1M | Output / 1M | Context |
|---|---|---|---|---|
| Kimi K2.7 Code | 2026-06-12 | $0.95 | $4.00 | 262.1K |
| Model | Maker | Input / 1M | Output / 1M | Review call | Context | Bugs caught |
|---|---|---|---|---|---|---|
| Grok 4.7 | xAI | $2.00 | $6.00 | $0.0669 | 500K | – |
| Qwen3.8 Max (OpenRouter) | Qwen | $2.00 | $6.00 | $0.0669 | 1M | – |
| Claude Sonnet 5.5 | Anthropic | $2.00 | $10.00 | $0.0766 | 1M | 77% |
| GPT-6.1 Sol | OpenAI | $2.00 | $10.00 | $0.0766 | 1.1M | 89% |
Updated Oct 23, 2026