Enterprise DNAEnterprise DNA
Moonshot AI logo

Models · Best coding

Kimi K2.7 Code

by Moonshotai

MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts.

Visit Moonshotai ↗

Our verdict

Not reviewed yet

We have not reviewed Kimi K2.7 Code yet

No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.

How we review records

From the listing

About Kimi K2.7 Code

MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts.

Notes

Kimi K2.7 Code is listed in the EDNA Models directory from the OpenRouter catalogue.

Key facts

What we have checked

Input price
$0.600 per million tokens
Checked OpenRouter models API
Output price
$3.50 per million tokens
Checked OpenRouter models API
Price on cloudflare
$0.190 per million cached input tokens
Checked OpenRouter models API
Price on cloudflare
$0.950 per million input tokens
Checked OpenRouter models API
Price on cloudflare
$4.00 per million output tokens
Checked OpenRouter models API
Price on coreweave
$0.120 per million cached input tokens
Checked OpenRouter models API
Price on coreweave
$0.600 per million input tokens
Checked OpenRouter models API
Price on coreweave
$3.00 per million output tokens
Checked OpenRouter models API
Price on gmicloud
$0.190 per million cached input tokens
Checked OpenRouter models API
Gpqa diamond
87.9% (for 12 June 2026)
Checked Epoch AI (CC BY 4.0)
Frontiermath tiers 1 3 v2 private
54% (for 12 June 2026)
Checked Epoch AI (CC BY 4.0)
Simpleqa verified
36.5% (for 12 June 2026)
Checked Epoch AI (CC BY 4.0)

Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.

API access

How to call it

Call via OpenRouter with model id `moonshotai/kimi-k2.7-code`.

  • openrouter · moonshotai/kimi-k2.7-code · Docs

OpenRouter id: moonshotai/kimi-k2.7-code

Price

What Kimi K2.7 Code costs, over time

Input price

$0.660 to $0.600

US dollars per million input tokens. 3 Sept 2026 to 10 Nov 2026, 44 days.

Source: OpenRouter models API. Checked .

Output price

$3.40 to $3.50

US dollars per million output tokens. 3 Sept 2026 to 10 Nov 2026, 44 days.

Source: OpenRouter models API. Checked .

Prices by host

HostPriceOver timeChecked
cloudflareCached input$0.190 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
cloudflareInput$0.950 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
cloudflareOutput$4.00 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
coreweaveCached input$0.120 per million cached input tokensSince 27 Oct 20261 changeOpenRouter models API
coreweaveInput$0.600 per million input tokensSince 27 Oct 20261 changeOpenRouter models API
coreweaveOutput$3.00 per million output tokensSince 27 Oct 20261 changeOpenRouter models API
gmicloudCached input$0.190 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
gmicloudInput$0.950 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
gmicloudOutput$4.00 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
inceptronCached input$0.160 per million cached input tokensSince 7 Nov 20261 changeOpenRouter models API
inceptronInput$0.600 per million input tokensSince 30 Oct 20262 changesOpenRouter models API
inceptronOutput$3.50 per million output tokensSince 30 Oct 20262 changesOpenRouter models API
moonshotaiCached input$0.190 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
moonshotaiInput$0.950 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
moonshotaiOutput$4.00 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
nebiusCached input$0.150 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
nebiusInput$0.950 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
nebiusOutput$4.00 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
novitaCached input$0.182 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
novitaInput$0.912 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
novitaOutput$3.84 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
qwenCached input$0.190 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
qwenInput$0.950 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
qwenOutput$4.00 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
siliconflowCached input$0.180 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
siliconflowInput$0.859 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
siliconflowOutput$3.80 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
streamlakeCached input$0.142 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
streamlakeInput$0.713 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
streamlakeOutput$3.00 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
veniceCached input$0.160 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
veniceInput$0.750 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
veniceOutput$3.50 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API

Usage

How much Kimi K2.7 Code is used

Tokens served a day

6.2B to 6.2B

tokens a day on OpenRouter. 19 Sept 2026 to 10 Nov 2026, 53 readings.

Source: OpenRouter model activity (748 of 748 series). Checked .

Scores

How Kimi K2.7 Code scores

Each score comes from the named source and shows when we last confirmed it. A flag means the score needs care.

ScoreValueSourceChecked
Artificial Analysis Intelligence Index25.8indexAs of 26 Oct 2026Artificial Analysis via OpenRouter
Artificial Analysis Coding Index60.8indexAs of 10 Nov 2026Artificial Analysis via OpenRouter
Artificial Analysis Agentic Index21indexAs of 10 Nov 2026Artificial Analysis via OpenRouter
LMArena web development rating (Elo)1,474EloAs of 10 Nov 2026LMArena (CC-BY-4.0), published 2026-11-09
Design Arena rating (Elo)1,259EloAs of 10 Nov 2026Design Arena via OpenRouter
Apex agents (best-across-versions)37.6percentAs of 12 June 2026Epoch AI (CC BY 4.0)
Chess puzzles (best-across-versions)14percentAs of 12 June 2026Epoch AI (CC BY 4.0)
Frontiercode (best-across-versions)30.1percentAs of 12 June 2026Epoch AI (CC BY 4.0)
Frontiermath tier 4 v2 private (best-across-versions)12.2percentAs of 12 June 2026Epoch AI (CC BY 4.0)
Frontiermath tiers 1 3 v2 private (best-across-versions)54percentAs of 12 June 2026Epoch AI (CC BY 4.0)
Gpqa diamond (best-across-versions)87.9percentAs of 12 June 2026Epoch AI (CC BY 4.0)
Otis mock aime 2024 2025 (best-across-versions)Saturated95.6percentAs of 12 June 2026Epoch AI (CC BY 4.0)
Show 4 more scores
ScoreValueSourceChecked
Simplebench (best-across-versions)57.9percentAs of 12 June 2026Epoch AI (CC BY 4.0)
Simpleqa verified (best-across-versions)36.5percentAs of 12 June 2026Epoch AI (CC BY 4.0)
Surface evolver bench (best-across-versions)48.8percentAs of 12 June 2026Epoch AI (CC BY 4.0)
Weirdml (best-across-versions)54.1percentAs of 12 June 2026Epoch AI (CC BY 4.0)
Saturated
Top models score close to the maximum, so this test no longer separates them.

Sources

Where this comes from

A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.

Changelog

What changed

  1. Price changed

    cached input per mtok: 0.15 to 0.16

    Source: OpenRouter models API

  2. Price changed

    output per mtok: 3.1 to 3.5

    Source: OpenRouter models API

  3. Price changed

    input per mtok: 0.56 to 0.6

    Source: OpenRouter models API

  4. Price changed

    output per mtok: 3.1 to 3.5

    Source: OpenRouter models API

  5. Price changed

    input per mtok: 0.56 to 0.6

    Source: OpenRouter models API

  6. Price changed

    output per mtok: 3.35 to 3.1

    Source: OpenRouter models API

  7. Price changed

    input per mtok: 0.6712 to 0.56

    Source: OpenRouter models API

  8. Price changed

    cached input per mtok: 0.15 to 0.12

    Source: OpenRouter models API

  9. Price changed

    output per mtok: 3.5 to 3

    Source: OpenRouter models API

  10. Price changed

    input per mtok: 0.71 to 0.6

    Source: OpenRouter models API

  11. Price changed

    output per mtok: 3.35 to 3.1

    Source: OpenRouter models API

  12. Price changed

    input per mtok: 0.6712 to 0.56

    Source: OpenRouter models API

  13. Price changed

    output per mtok: 3.3 to 3.35

    Source: OpenRouter models API

  14. Price changed

    input per mtok: 0.6562 to 0.6712

    Source: OpenRouter models API

  15. Price changed

    output per mtok: 3.21 to 3.3

    Source: OpenRouter models API

  16. Price changed

    input per mtok: 0.7062 to 0.6562

    Source: OpenRouter models API

  17. Price changed

    output per mtok: 3.5 to 3.21

    Source: OpenRouter models API

  18. Price changed

    input per mtok: 0.71 to 0.7062

    Source: OpenRouter models API

  19. Price changed

    output per mtok: 3.4 to 3.5

    Source: OpenRouter models API

  20. Price changed

    input per mtok: 0.66 to 0.71

    Source: OpenRouter models API

USAGE / OPENROUTER

How much Kimi K2.7 Code is used

Tokens processed through OpenRouter each day. It shows what developers actually run, not every company's private traffic.

Tokens, last 7 days
49.6B ▲14.6%
Requests, last 7 days
1.1M
Tool calls, last 7 days
511K
Average cost per request
$1.64
Price per million tokens
$0.6 in · $3.5 out
010B20B19 Sept: 6.2B tokens, 193K requests20 Sept: 6.9B tokens, 163K requests21 Sept: 8.6B tokens, 195K requests22 Sept: 10.1B tokens, 240K requests23 Sept: 9.7B tokens, 239K requests24 Sept: 8.6B tokens, 201K requests25 Sept: 9B tokens, 219K requests26 Sept: 5.5B tokens, 191K requests27 Sept: 4.9B tokens, 149K requests28 Sept: 7B tokens, 193K requests29 Sept: 8.9B tokens, 246K requests30 Sept: 9B tokens, 235K requests1 Oct: 7.5B tokens, 224K requests2 Oct: 8B tokens, 225K requests3 Oct: 4.2B tokens, 138K requests4 Oct: 7.5B tokens, 194K requests5 Oct: 8.3B tokens, 220K requests6 Oct: 7.7B tokens, 194K requests7 Oct: 6.8B tokens, 187K requests8 Oct: 5.9B tokens, 148K requests9 Oct: 7.7B tokens, 171K requests10 Oct: 9.1B tokens, 251K requests11 Oct: 6.2B tokens, 150K requests12 Oct: 10.5B tokens, 229K requests13 Oct: 10.5B tokens, 200K requests14 Oct: 9.3B tokens, 182K requests15 Oct: 11.7B tokens, 212K requests16 Oct: 6.3B tokens, 151K requests17 Oct: 6B tokens, 180K requests18 Oct: 10.8B tokens, 187K requests19 Oct: 6.7B tokens, 168K requests20 Oct: 7.4B tokens, 168K requests21 Oct: 8.6B tokens, 192K requests22 Oct: 8.9B tokens, 172K requests23 Oct: 7.7B tokens, 161K requests24 Oct: 5.7B tokens, 145K requests25 Oct: 4.3B tokens, 121K requests26 Oct: 5.9B tokens, 148K requests27 Oct: 6.6B tokens, 177K requests28 Oct: 7.2B tokens, 169K requests29 Oct: 7B tokens, 153K requests30 Oct: 6.3B tokens, 142K requests31 Oct: 4.3B tokens, 136K requests1 Nov: 4B tokens, 106K requests2 Nov: 6.7B tokens, 153K requests3 Nov: 7.8B tokens, 165K requests4 Nov: 6B tokens, 146K requests5 Nov: 6.2B tokens, 155K requests6 Nov: 5.6B tokens, 137K requests7 Nov: 6B tokens, 133K requests8 Nov: 9B tokens, 153K requests9 Nov: 10.7B tokens, 204K requests10 Nov: 6.2B tokens, 160K requests19 Sept3 Oct17 Oct31 Oct10 NovSee where it ranks on the leaderboard →

MODEL FIELD GUIDE / SOURCE EVIDENCE

What you can do with Kimi K2.7 Code.

Listed specifications; no EDNA task evaluation has been run. Sources checked 2026-11-05. Hosting routes and app features can differ.

DeveloperMoonshotai
Exact model identifiermoonshotai/kimi-k2.7-code
Inputtext, image
Outputtext
Tool calling
Listed support
Structured output
Listed support
Reasoning controls
Listed support
Availability
available
Price basis
token
Licence verification
modified-mit, open weights
Context length
262K tokens
Knowledge cutoff
Not established
Developer release date
Not established
First seen in the catalogue
12 Jun 2026
Listed retirement date
Not established
Inspect the sources and their scope
catalogue source ↗

moonshotai/kimi-k2.7-code: listed route capabilities, availability and prices; provider endpoints can differ.

Checked 2026-11-05
openrouter.ai ↗

Source for reasoning controls, first seen, tool calling, context length, input, output, structured output.

Checked 2026-11-05
Licence source ↗

Licence declared in the moonshotai/Kimi-K2.7-Code model repository on Hugging Face, which holds the weights files. Read the licence terms before use.

Checked 2026-11-07
How to evaluate a model for your work →

FROM SPECIFICATIONS TO YOUR WORK

Is this the right model for your job?

Start with a realistic sample. These workflows match the model’s listed capabilities, not a verified result on your task.

Build an appWorkflow & starter prompt ↗Extract document dataWorkflow & starter prompt ↗Run a reliable agentWorkflow & starter prompt ↗

What would it cost?

Pick a common job and how many times a month you run it. Token sizes are our assumption for a typical run, shown under the result.

Working out the cost...

Token prices only. Per-request, image, tool, storage and subscription fees are not included. One token is about three quarters of an English word. Real counts vary by model and language. How tokens are counted ↗

Check the source

Price date: 10 Nov 2026, from OpenRouter models API. Prices are USD API token rates. Your app subscription, uploads, browsing and tools are separate.

Model source & availability ↗

Understand the evidence

Listed capabilities and third-party benchmark scores do not establish Enterprise DNA task-test results. Validate accuracy and total cost on your own sample.

Coding Index: 60.8 (2026-11-09) ↗Agentic Index: 21 (2026-11-09) ↗Design Arena: 1260 (2026-11-09) ↗
Compare this model with alternatives →
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

← Back to ModelsSubmit your own entry →