As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/kimi-k2-7-code/

# Kimi K2.7 Code

Moonshot AI, Kimi K2 family. Status: current. Type: code model. Released: 2026-06.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Kimi API (Moonshot) | `kimi-k2.7-code` | https://api.moonshot.ai/v1 | https://platform.kimi.ai/docs/guide/kimi-k2-7-code-quickstart |
| Kimi API (Moonshot) high-speed | `kimi-k2.7-code-highspeed` | https://api.moonshot.ai/v1 | https://platform.kimi.ai/docs/models |
| OpenRouter | `moonshotai/kimi-k2.7-code` |  | https://openrouter.ai/moonshotai/kimi-k2.7-code |
| Hugging Face |  |  | https://huggingface.co/moonshotai/Kimi-K2.7-Code |
| Web app |  |  | https://www.kimi.com |

## Pricing

- Input: $0.95 per 1M tokens
- Output: $4 per 1M tokens
- Cache read: $0.19 per 1M tokens
- Unit as published: per 1M tokens (USD); kimi-k2.7-code-highspeed: 1.90 in / 8.00 out / 0.38 cache hit
- Source: https://platform.kimi.ai/docs/pricing/chat
- Last checked: 2026-09-29

## Specs

- Input: text, image, video
- Output: text
- Context window: 262,144 tokens
- Max output: not published
- Open weights: yes
- Licence: modified-mit

## Where it stands

- Newer code models in the registry since its release: 3:
  - Recursive Flint (2026-10-21) https://postcutoff.com/m/recursive-flint/
  - Mellum2.1 12B-A2.5B Thinking (2026-10-08) https://postcutoff.com/m/mellum2-1/
  - Leanstral 1.5 (2026-07-02) https://postcutoff.com/m/leanstral-1-5/
- Weights are public. Licence: Modified MIT. See the licence for commercial terms.

## What stands out

- Coding-specialized K2.6 derivative: Built on Kimi K2.6 (1T total / 32B active, MLA, 400M vision encoder) and tuned for long-horizon real-world coding. Source: https://huggingface.co/moonshotai/Kimi-K2.7-Code
- ~30% fewer thinking tokens than K2.6: Higher task success with about 30% lower thinking-token usage vs K2.6. Source: https://huggingface.co/moonshotai/Kimi-K2.7-Code
- High-speed tier: kimi-k2.7-code-highspeed outputs ~180 tok/s (up to ~260 tok/s on short context). Source: https://platform.kimi.ai/docs/models

## Notes

Dedicated coding model; pairs with Kimi Code CLI. Release day not verified (HF 2026-06-11, OpenRouter 2026-06-12). Max output not verified.

Cheaper-than-K3 coding agent model for Kimi Code CLI, Claude Code, Codex, OpenCode.

```bash
curl https://api.moonshot.ai/v1/chat/completions \
 -H "Authorization: Bearer $MOONSHOT_API_KEY" -H "Content-Type: application/json" \
 -d '{"model":"kimi-k2.7-code","messages":[{"role":"user","content":"Write a Python quicksort"}]}'
```

Sources: https://platform.kimi.ai/docs/models · https://platform.kimi.ai/docs/pricing/chat · https://huggingface.co/moonshotai/Kimi-K2.7-Code

Model page: https://postcutoff.com/m/kimi-k2-7-code/