Kimi K2.7 Code · Moonshot AI

What does Kimi K2.7 Code cost to run in a coding agent?

Kimi K2.7 Code costs about $0.027 per average coding-agent request on our measured traffic, at OpenRouter's listed prices of $0.671 per million input and $3.35 per million output tokens. It scores 26 on the Artificial Analysis Intelligence Index, 33rd of the 48 models we track. Source: Artificial Analysis (artificialanalysis.ai)

List prices: OpenRouter listed price, checked 2026-10-13. Request costs: Standard Compute gateway data, 79,301 coding-agent requests from 75 users, Sep 13 to Oct 12, 2026. How we compute this

Run current Claude, GPT, Gemini and open models in your agent

Or let the router send each step to the cheapest model that can do it, on providers we vet for price, uptime and speed. Plans from $19 a month.

See plans

What Kimi K2.7 Code costs per coding-agent request

Cost at list price	Kimi K2.7 Code
Prompt under 100K tokens50% of requests, 87% of input cached	$0.016
Prompt of 100K to 272K39% of requests, 88% of input cached	$0.042
Prompt over 272K tokens11% of requests, 86% of input cached	n/a
Average request	$0.027
100 requests	$2.71
Median session16 requests; a session ends after 10 idle minutes	$0.31
A month of regular usemedian of 20 users active on 5+ days	$35.08

Each logged request priced at the listed rates above for its own token counts, including cache reads and any higher rate for long prompts. Average output: 698 tokens per request. 12% of requests were larger than Kimi K2.7 Code's 262K context window and are left out of its figures.

Kimi K2.7 Code benchmarks, speed and latency

Artificial Analysis	Value	Rank
Intelligence Index10 evaluations, 0 to 100	26	33 of 48
Terminal-Bench 4.0agentic coding in a terminal	1.0%	30 of 39
Output speedmedian	75 tokens/s	28 of 44
Time to first answer tokenincludes thinking time	33 s	19 of 44

Source: Artificial Analysis (artificialanalysis.ai). Measured variant: Kimi K2.7 Code, speed on Kimi. Fetched October 13, 2026. Rank is among the models on this site, older versions included. Artificial Analysis runs Terminal-Bench 4.0 in its own setup, so its scores differ from the tbench.ai leaderboard.

What to watch for

Its 262K-token window is smaller than 12% of our coding-agent requests, which are left out of the figures above, so long agent sessions will hit the limit. The price is OpenRouter's listed rate on October 13, 2026, which can be a third-party host's; Moonshot AI's own API may charge differently. It is weak on long agentic coding tasks (see Terminal-Bench 4.0 above), so a cheap request can turn into more steps and retries.

About Kimi K2.7 Code

Kimi K2.7 Code is Moonshot AI's coding-tuned open-weight model, released June 12, 2026 with a 262K context. Moonshot built it for tool use and multi-file edits, but independent results are modest: it scores 26 on the Artificial Analysis Intelligence Index and 1.0% in Artificial Analysis's Terminal-Bench 4.0 run, at about 75 output tokens per second. At OpenRouter's listed price it costs $0.027 per request in our measurements, about four times DeepSeek V4.1 Flash, which scores higher on both. Its 262K context is smaller than 11.7% of the coding-agent requests we measured.

Sources: Artificial Analysis

Kimi K2.7 Code FAQ

How much does Kimi K2.7 Code cost per coding-agent request?

$0.027 on average at OpenRouter's listed price, $2.71 per 100 requests, and $0.31 for a median 16-request session. That is 79,301 real coding-agent requests (Sep 13 to Oct 12, 2026) priced at OpenRouter's listed rates; the median request sent 99,534 input tokens, 87% of input was read from cache, and requests returned 698 output tokens on average.

Does Kimi K2.7 Code charge more for long prompts?

No. Kimi K2.7 Code bills the same rate per token up to its 262K-token context window, which is smaller than 12% of the coding-agent requests we measured.

How fast is Kimi K2.7 Code?

Artificial Analysis measures Kimi K2.7 Code at 75 output tokens per second, with 33 seconds to the first answer token, thinking time included, on Kimi's API. Source: Artificial Analysis (artificialanalysis.ai).

Is Kimi K2.7 Code good for AI agents?

Coding agents that need an open-weight model with a coding-specific tune. On our scoring, which is calibrated to public benchmarks, it rates 4.7/10 for agentic ability and 5.8/10 for output quality. Open weights.

What is Kimi K2.7 Code's context window?

Kimi K2.7 Code has a 262K-token context window. Moonshot AI is the maker.

Is Kimi K2.7 Code open source?

Yes. Kimi K2.7 Code ships with open weights, so you can self-host it or run it through a hosted provider such as OpenRouter. Check the license before commercial use.

What are the downsides of Kimi K2.7 Code?

The main trade-offs: Weak on long agentic tasks (1.0% in Artificial Analysis's Terminal-Bench 4.0 run); 262K context, smaller than 11.7% of the coding-agent requests we measured; Throughput varies by host. It's strongest for coding agents that need an open-weight model with a coding-specific tune.