Enterprise DNAEnterprise DNA
LModelsLong context
Moonshot AI logo

Kimi K2 0711

by Moonshotai

Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. I

KK

Models

Kimi K2 0711

Added 10 July 2026

#moonshotai

Overview

Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...

How to use / API access

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

  • openrouter · moonshotai/kimi-k2 Docs

OpenRouter id: moonshotai/kimi-k2

Benchmarks

  • Intelligence Index (artificial-analysis): 12.7 index
  • Design Arena codecategories (other): 1035 elo · #115
  • Design Arena dataviz (other): 1018 elo · #112
  • Design Arena gamedev (other): 975 elo · #122
  • Design Arena uicomponent (other): 1030 elo · #108

Notes

Kimi K2 0711 is listed in the EDNA Models directory from the OpenRouter catalogue.

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.

USAGE / OPENROUTER

How much Kimi K2 0711 is used

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

Tokens, last 7 days
2.5B ▲34.4%
Requests, last 7 days
458K
Tool calls, last 7 days
68.6K
Intelligence score
12.7
Average cost per request
56.4¢
Price per million tokens
$0.57 in · $2.3 out
0500M1B19 Sept: 431M tokens, 49.8K requests20 Sept: 537M tokens, 46.2K requests21 Sept: 541M tokens, 84.8K requests22 Sept: 509M tokens, 60.6K requests23 Sept: 331M tokens, 46.6K requests24 Sept: 248M tokens, 52.7K requests25 Sept: 203M tokens, 43.4K requests26 Sept: 229M tokens, 81.2K requests27 Sept: 215M tokens, 53.6K requests28 Sept: 391M tokens, 61.3K requests29 Sept: 357M tokens, 92.2K requests30 Sept: 408M tokens, 117K requests1 Oct: 440M tokens, 88.7K requests2 Oct: 335M tokens, 68.2K requests3 Oct: 375M tokens, 48.3K requests4 Oct: 248M tokens, 72.3K requests5 Oct: 218M tokens, 50.8K requests6 Oct: 451M tokens, 80.6K requests7 Oct: 270M tokens, 53.5K requests8 Oct: 261M tokens, 45.7K requests9 Oct: 232M tokens, 64.5K requests10 Oct: 218M tokens, 49.6K requests11 Oct: 210M tokens, 39.6K requests12 Oct: 571M tokens, 84.1K requests13 Oct: 476M tokens, 83.1K requests14 Oct: 394M tokens, 67.7K requests15 Oct: 346M tokens, 53.3K requests16 Oct: 325M tokens, 68.8K requests17 Oct: 199M tokens, 58K requests18 Oct: 191M tokens, 43.4K requests19 Sept3 Oct17 Oct18 OctSee where it ranks on the leaderboard →

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.

Check the source

Price date: 2026-10-18. 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.

Intelligence Index: 12.7 (2026-10-18) ↗
Compare this model with alternatives →