Enterprise DNAEnterprise DNA
Moonshot AI logo

Models · Reasoning

Kimi K2 Thinking

by Moonshotai

Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning.

Visit Moonshotai ↗

Our verdict

Not reviewed yet

We have not reviewed Kimi K2 Thinking 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 Thinking

Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning.

Notes

Kimi K2 Thinking 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
$2.50 per million tokens
Checked OpenRouter models API
Price on google-vertex
$0.600 per million input tokens
Checked OpenRouter models API
Price on google-vertex
$2.50 per million output tokens
Checked OpenRouter models API
Price on novita
$0.150 per million cached input tokens
Checked OpenRouter models API
Price on novita
$0.600 per million input tokens
Checked OpenRouter models API
Price on novita
$2.50 per million output tokens
Checked OpenRouter models API
Latest version
moonshotai/kimi-k2-thinking-20251106
Checked OpenRouter models API
Time to first token (ms)
1,750
Checked Artificial Analysis
Time to first token (ms) on novita
1,474
Checked OpenRouter models API
Output speed (tokens a second)
122
Checked Artificial Analysis
Output speed (tokens a second) on novita
44
Checked OpenRouter models API

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-thinking`.

  • openrouter · moonshotai/kimi-k2-thinking · Docs

OpenRouter id: moonshotai/kimi-k2-thinking

Price

What Kimi K2 Thinking costs, over time

Input price

$0.600 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

$2.50 to $2.50

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
google-vertexInput$0.600 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
google-vertexOutput$2.50 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
novitaCached input$0.150 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
novitaInput$0.600 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
novitaOutput$2.50 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API

Usage

How much Kimi K2 Thinking is used

Tokens served a day

272M to 338.8M

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 Thinking 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 Index22indexAs of 26 Oct 2026Artificial Analysis via OpenRouter
Artificial Analysis Coding Index21indexAs of 10 Nov 2026Artificial Analysis via OpenRouter
Design Arena rating (Elo)1,109EloAs of 10 Nov 2026Design Arena via OpenRouter

Compare

Compare Kimi K2 Thinking side by side

Sources

Where this comes from

  • OpenRouter models APIRegistry

    Checked · Latest version

  • OpenRouter models APIThird party

    Checked · Price on google-vertex, Price on novita, Time to first token (ms) on novita, Output speed (tokens a second) on novita

  • OpenRouter models APIOfficial

    Checked · Input price, Output price

  • Artificial AnalysisThird party

    Checked · Time to first token (ms), Output speed (tokens a second)

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

No changes recorded yet. Releases, price changes and deprecations appear here, with their dates, once we track them for this record.

USAGE / OPENROUTER

How much Kimi K2 Thinking is used

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

Tokens, last 7 days
1.9B ▼42%
Requests, last 7 days
155K
Tool calls, last 7 days
28.8K
Average cost per request
81.8¢
Price per million tokens
$0.6 in · $2.5 out
01B2B19 Sept: 272M tokens, 16.5K requests20 Sept: 195M tokens, 11.3K requests21 Sept: 190M tokens, 13.4K requests22 Sept: 400M tokens, 25.5K requests23 Sept: 1.5B tokens, 128K requests24 Sept: 546M tokens, 57.4K requests25 Sept: 360M tokens, 26.7K requests26 Sept: 177M tokens, 13.5K requests27 Sept: 242M tokens, 19.9K requests28 Sept: 352M tokens, 25K requests29 Sept: 326M tokens, 24.4K requests30 Sept: 297M tokens, 18.8K requests1 Oct: 323M tokens, 18.5K requests2 Oct: 352M tokens, 26.5K requests3 Oct: 424M tokens, 28.4K requests4 Oct: 322M tokens, 31.3K requests5 Oct: 322M tokens, 18.4K requests6 Oct: 272M tokens, 18.6K requests7 Oct: 231M tokens, 17.7K requests8 Oct: 296M tokens, 18.5K requests9 Oct: 534M tokens, 38K requests10 Oct: 154M tokens, 9.8K requests11 Oct: 401M tokens, 25.2K requests12 Oct: 300M tokens, 13.3K requests13 Oct: 230M tokens, 13.2K requests14 Oct: 240M tokens, 16.7K requests15 Oct: 314M tokens, 16K requests16 Oct: 501M tokens, 22.1K requests17 Oct: 292M tokens, 17.8K requests18 Oct: 155M tokens, 13.1K requests19 Oct: 348M tokens, 19.7K requests20 Oct: 376M tokens, 23.8K requests21 Oct: 918M tokens, 65.3K requests22 Oct: 691M tokens, 37.8K requests23 Oct: 256M tokens, 20.2K requests24 Oct: 204M tokens, 12.7K requests25 Oct: 142M tokens, 10.3K requests26 Oct: 218M tokens, 11.8K requests27 Oct: 442M tokens, 19.7K requests28 Oct: 1.8B tokens, 41.8K requests29 Oct: 671M tokens, 40K requests30 Oct: 197M tokens, 12K requests31 Oct: 67.6M tokens, 7.6K requests1 Nov: 147M tokens, 15.8K requests2 Nov: 171M tokens, 13K requests3 Nov: 229M tokens, 20.6K requests4 Nov: 115M tokens, 11K requests5 Nov: 90.9M tokens, 9K requests6 Nov: 205M tokens, 17.4K requests7 Nov: 150M tokens, 18.4K requests8 Nov: 459M tokens, 41.6K requests9 Nov: 552M tokens, 40.6K requests10 Nov: 339M tokens, 17K requests19 Sept3 Oct17 Oct31 Oct10 NovSee where it ranks on the leaderboard →

MODEL FIELD GUIDE / SOURCE EVIDENCE

What you can do with Kimi K2 Thinking.

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

DeveloperMoonshotai
Exact model identifiermoonshotai/kimi-k2-thinking
Inputtext
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
6 Nov 2025
Listed retirement date
Not established
Inspect the sources and their scope
catalogue source ↗

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

Checked 2026-11-11
openrouter.ai ↗

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

Checked 2026-11-11
Licence source ↗

Licence declared in the moonshotai/Kimi-K2-Thinking 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.

Write a clear business documentWorkflow & starter prompt ↗Analyse a spreadsheetWorkflow & starter prompt ↗Research a companyWorkflow & 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: 21 (2026-11-09) ↗Design Arena: 1109 (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 →