# Kimi K2.7 Code Usage, Cost & Rank | OpenCode Data

> Kimi K2.7 Code ranked #21 by tokens across OpenCode last week, with 0.2% of tokens over the past two months. Kimi K2.7 Code costs $0.95 per 1M input tokens and $4.00 per 1M output tokens.

Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking

- Page: https://opencode.ai/data/moonshotai/kimi-k2-7-code
- JSON: https://opencode.ai/data/moonshotai/kimi-k2-7-code.json
- Model ID: moonshotai/kimi-k2.7-code
- Lab: Moonshot
- Updated: 2026-10-02T08:39:37.000Z

## Model facts

| Fact | Value |
| --- | --- |
| Context window | 262K |
| Max output | 262K |
| Knowledge cutoff | 2025-01 |
| Release date | 2026-06-12 |
| Input modalities | text, image, video |
| Output modalities | text |
| Reasoning | Yes |
| Tool calling | Yes |
| Open weights | Yes |
| Weights | [Hugging Face](https://huggingface.co/moonshotai/Kimi-K2.7-Code) |

## Pricing: USD per 1M tokens

| Input | Output | Cached input | Cache write |
| --- | --- | --- | --- |
| $0.95 | $4.00 | $0.19 | - |

## OpenCode usage: past 2 months

| Metric | Value |
| --- | --- |
| Rank by tokens last week | #21 |
| Tokens | 1.5T |
| Share of all tokens | 0.2% |
| Change vs previous 2 months | -55% |
| Unique users | 232K |
| Completed sessions | 423,838 |
| Average tokens per session | 3.6M |
| Average cost per session | $0.8954 |
| Total spend | $379,514 |
| Input tokens served from cache | 95.2% |
| Weekly retention | 55.0% |

## Daily usage: past 2 months

| Date | Tokens | Unique users | Sessions |
| --- | --- | --- | --- |
| 2026-08-08 | 25B | 4.1K | 6,901 |
| 2026-08-09 | 21B | 3.8K | 5,290 |
| 2026-08-10 | 37B | 5.5K | 9,467 |
| 2026-08-11 | 34B | 7K | 4,118 |
| 2026-08-12 | 45B | 6.1K | 194 |
| 2026-08-13 | 43B | 6.3K | 207 |
| 2026-08-14 | 36B | 8.1K | 231 |
| 2026-08-15 | 29B | 6.9K | 160 |
| 2026-08-16 | 29B | 5.4K | 175 |
| 2026-08-17 | 52B | 9.7K | 304 |
| 2026-08-18 | 49B | 7.9K | 9,013 |
| 2026-08-19 | 44B | 7.3K | 10,067 |
| 2026-08-20 | 41B | 8.6K | 8,839 |
| 2026-08-21 | 35B | 8.5K | 7,693 |
| 2026-08-22 | 23B | 4.7K | 5,408 |
| 2026-08-23 | 21B | 3.8K | 4,728 |
| 2026-08-24 | 36B | 6.7K | 9,457 |
| 2026-08-25 | 33B | 5.5K | 8,803 |
| 2026-08-26 | 30B | 4.8K | 7,502 |
| 2026-08-27 | 30B | 4.4K | 6,524 |
| 2026-08-28 | 27B | 3.7K | 5,681 |
| 2026-08-29 | 18B | 2.6K | 4,034 |
| 2026-08-30 | 19B | 2.4K | 3,901 |
| 2026-08-31 | 31B | 4K | 7,040 |
| 2026-09-01 | 28B | 3.8K | 6,365 |
| 2026-09-02 | 26B | 3.6K | 6,315 |
| 2026-09-03 | 27B | 3.8K | 6,493 |
| 2026-09-04 | 24B | 3.4K | 6,295 |
| 2026-09-05 | 16B | 2.3K | 4,524 |
| 2026-09-06 | 17B | 2.3K | 4,704 |
| 2026-09-07 | 29B | 3.4K | 9,053 |
| 2026-09-08 | 29B | 3.3K | 10,675 |
| 2026-09-09 | 26B | 3.1K | 8,965 |
| 2026-09-10 | 25B | 3.3K | 9,996 |
| 2026-09-11 | 21B | 2.9K | 8,878 |
| 2026-09-12 | 18B | 2.2K | 7,257 |
| 2026-09-13 | 17B | 2.2K | 6,968 |
| 2026-09-14 | 30B | 3.5K | 12,170 |
| 2026-09-15 | 30B | 3.6K | 11,732 |
| 2026-09-16 | 28B | 3.4K | 13,175 |
| 2026-09-17 | 26B | 3.4K | 10,274 |
| 2026-09-18 | 27B | 3.1K | 10,638 |
| 2026-09-19 | 21B | 2.6K | 9,765 |
| 2026-09-20 | 19B | 2.5K | 8,922 |
| 2026-09-21 | 34B | 3.6K | 11,877 |
| 2026-09-22 | 28B | 3.3K | 11,052 |
| 2026-09-23 | 24B | 2.9K | 9,663 |
| 2026-09-24 | 23B | 2.8K | 9,418 |
| 2026-09-25 | 18B | 2.3K | 10,664 |
| 2026-09-26 | 16B | 2K | 8,749 |
| 2026-09-27 | 16B | 2K | 6,814 |
| 2026-09-28 | 29B | 3.2K | 15,258 |
| 2026-09-29 | 26B | 3.2K | 12,784 |
| 2026-09-30 | 23B | 3K | 12,389 |
| 2026-10-01 | 21B | 2.7K | 13,253 |
| 2026-10-02 | 5.1B | 1K | 3,016 |

## Top countries: past 2 months

| Rank | Country | Tokens | Share |
| --- | --- | --- | --- |
| 1 | United States | 156B | 10.2% |
| 2 | China | 113B | 7.4% |
| 3 | Brazil | 88B | 5.8% |
| 4 | Germany | 73B | 4.8% |
| 5 | Spain | 72B | 4.7% |
| 6 | India | 60B | 3.9% |
| 7 | Colombia | 56B | 3.7% |
| 8 | Argentina | 47B | 3.1% |
| 9 | Indonesia | 42B | 2.7% |
| 10 | Mexico | 40B | 2.6% |
| 11 | France | 38B | 2.5% |
| 12 | Russia | 37B | 2.4% |
| 13 | Japan | 37B | 2.4% |
| 14 | United Kingdom | 36B | 2.3% |
| 15 | Netherlands | 27B | 1.8% |

## Nearby models by tokens last week

| Rank | Model | Lab | Tokens |
| --- | --- | --- | --- |
| 17 | [qwen3.8-flash](https://opencode.ai/data/alibaba/qwen3-8-flash.md) | Qwen | 256B |
| 18 | [gpt-5.6-luna](https://opencode.ai/data/openai/gpt-5-6-luna.md) | OpenAI | 195B |
| 19 | [minimax-m3](https://opencode.ai/data/minimax/minimax-m3.md) | MiniMax | 181B |
| 20 | [mai-experimental-test](https://opencode.ai/data/unknown/mai-experimental-test.md) | - | 180B |
| 21 | [kimi-k2.7-code](https://opencode.ai/data/moonshotai/kimi-k2-7-code.md) | Moonshot | 136B |
| 22 | [glm-5.3](https://opencode.ai/data/zhipuai/glm-5-3.md) | Zhipu | 95B |
| 23 | [fledge-alpha](https://opencode.ai/data/unknown/fledge-alpha.md) | - | 90B |
| 24 | [qwen3.7-plus](https://opencode.ai/data/alibaba/qwen3-7-plus.md) | Qwen | 76B |
| 25 | [glm-5.2](https://opencode.ai/data/zhipuai/glm-5-2.md) | Zhipu | 61B |
| 26 | [kimi-k3](https://opencode.ai/data/moonshotai/kimi-k3.md) | Moonshot | 45B |

## Benchmarks

| Benchmark | Score | Metric | Source |
| --- | --- | --- | --- |
| Kimi Code Bench | 62 |  | https://huggingface.co/moonshotai/Kimi-K2.7-Code |
| Program Bench | 53.6 |  | https://huggingface.co/moonshotai/Kimi-K2.7-Code |
| MLS Bench Lite | 35.1 |  | https://huggingface.co/moonshotai/Kimi-K2.7-Code |
| MCP Atlas | 76 | success rate | https://huggingface.co/moonshotai/Kimi-K2.7-Code |
| MCP Mark Verified | 81.1 | success rate | https://huggingface.co/moonshotai/Kimi-K2.7-Code |
| Kimi Claw 24/7 Bench | 46.9 |  | https://huggingface.co/moonshotai/Kimi-K2.7-Code |

## Methodology

- Updates: Aggregated every hour. Days and weeks use UTC.
- Tokens: Input, output, reasoning, and cached tokens for each request.
- Users and sessions: Approximate counts of distinct users and OpenCode sessions.
- Cost: Session cost is the average cost per OpenCode session. Token prices are list prices from the OpenCode model catalog.
- Retention: The share of a model's users in one week who use it again the next week.
- Citation: Cite OpenCode Data (opencode.ai/data) with the update time shown at the top of the page.