Moonshot AI

Kimi K2.7 Code — Benchmark Scores, Pricing & Performance Analysis

OPEN SOURCEMoonshot AI
Input Cost
$0.71/1M
Output Cost
$3.5/1M
Context Window
262K
Max Output
262K
Knowledge Cutoff
Jan 2025
Accepts
text, image, video

Kimi K2.7 Code is an AI model by Moonshot AI. View detailed benchmark scores, pricing data, and performance metrics on Serenities AI Models.

Specifications last checked against the provider on . Benchmark scores carry their own source, linked beside each number.

General Benchmarks

AA Intelligence Index
26.331st of 66

Artificial Analysis composite intelligence score across 10 sub-benchmarks

Artificial Analysis (via OpenRouter)

Coding Benchmarks

Design Arena ELO
125129th of 120

Human preference ELO for building things — websites, UI, games, charts, SVG

Design Arena (via OpenRouter)
AA Coding Index
60.832nd of 96

Artificial Analysis composite coding score

Artificial Analysis (via OpenRouter)
Website Arena ELO
128023rd of 108

Human preference ELO for building a working web page from a brief

Design Arena (via OpenRouter)

Reasoning Benchmarks

AA Agentic Index
22.532nd of 70

Artificial Analysis composite score for multi-step tool-using tasks

Artificial Analysis (via OpenRouter)
GPQA Diamond
81.4%55th of 140

Graduate-level science Q&A by domain experts

Papers
τ²-Bench Airline
71.8%42nd of 93

Multi-turn service agent making tool calls under strict policy constraints

OpenRouter (measured)

Cost Benchmarks

Input Cost
$0.71273rd of 413

Cost per 1M input tokens

OpenRouter API
Output Cost
$3.5286th of 413

Cost per 1M output tokens

OpenRouter API
Cached Input Cost
$0.1578th of 136

Cost per 1M cached input tokens — the price that actually applies to a long agent conversation

OpenRouter API

Context Benchmarks

Context Length
262K108th of 451

Maximum context window size

OpenRouter API

Available from 61 providers

The same model costs different amounts depending on who serves it. You can bring your own key for 10 of these — connect it here.

ProviderInput / 1MOutput / 1MCached inContextYour key
Alibaba Token Plan$0$0$0262K—
Alibaba Token Plan (China)$0$0$0262K—
Kenari$0$0—262K—
Kimi For Coding$0$0$0262K—
SCNet Token Plan$0$0$0262K—
Umans AI Coding Plan$0$0$0262K—
Volcengine Ark Coding Plan$0$0$0262K—
routing.run$0.275$1.1—200K—
CrofAI$0.55$2.25$0.05262K—
Inceptron$0.66$3.4$0.18262K—
Deep Infra$0.68$3.4$0.136262KSupported
Ambient$0.69$3.49$0.14262K—
OpenRouter$0.71$3.5$0.15262KSupported
Weights & Biases$0.71$3.5$0.15262K—
ai&$0.75$3.5—262K—
Cortecs$0.75$3.5$0.201262K—
Venice AI$0.75$3.5$0.16256K—
AKI.IO$0.86$3$0.18262K—
GreenPT$0.9006$4.389$0.1881262K—
302.AI$0.95$4—262K—
Abacus$0.95$4$0.19262K—
AIHubMix$0.95$3.9995$0.160835262K—
Azure$0.95$4$0.19262KSupported
Baseten$0.95$4$0.16262KSupported
ClinePass$0.95$4$0.19262K—
Cloudflare Workers AI$0.95$4$0.19262KSupported
Databricks$0.95$4$0.19262K—
DevPass (LLM Gateway)$0.95$4$0.19262K—
Eden AI$0.95$4$0.19262K—
EmpirioLabs AI$0.95$4$0.95256K—
Fireworks AI$0.95$4$0.19262KSupported
GitHub Copilot$0.95$4$0.19256K—
HPC-AI$0.95$4$0.19256K—
Hugging Face$0.95$4—262KSupported
Jalapeno Cloud$0.95$4—271K—
Kilo Gateway$0.95$4$0.19262K—
LLM Gateway$0.95$4$0.19262K—
Merge Gateway$0.95$4$0.19262K—
Moonshot AI$0.95$4$0.19262KSupported
Moonshot AI (China)$0.95$4$0.19262K—
NanoGPT$0.95$4$0.19262K—
Nebius Token Factory$0.95$4—262K—
Neuralwatt$0.95$4$0.095262K—
NovitaAI$0.95$4$0.19262K—
Ofox$0.95$4$0.19262K—
OpenCode Go$0.95$4$0.19262K—
OpenCode Zen$0.95$4$0.19262K—
OrcaRouter$0.95$4$0.19262K—
Perplexity Agent$0.95$4$0.19262K—
Pioneer$0.95$4$0.19256K—
Requesty$0.95$4$0.19262K—
Synthetic$0.95$4$0.95262K—
Together AI$0.95$4$0.19262KSupported
Umans AI$0.95$4$0.19262K—
Vercel AI Gateway$0.95$4$0.16256KSupported
ZenMux$0.95$4$0.16262K—
CrossModel$1$4.16$0.18262K—
OpenReason$1.0022$4.22—262K—
Charm Hyper$1.03436$4.3552$0.206872262K—
TensorX$1.25$4.5$0.3125262K—
Ollama Cloud———262K—

Kimi K2.7 Code — Benchmark Scores Overview

Scores normalized to percentage scale for visual comparison. ELO scores mapped to 0-100 range (1100-1500).

Kimi K2.7 Code — Frequently Asked Questions

How much does Kimi K2.7 Code cost?

Kimi K2.7 Code costs $0.71 per 1M input tokens and $3.5 per 1M output tokens. This is mid-range pricing for its capability level.

What is the context window of Kimi K2.7 Code?

Kimi K2.7 Code has a context window of 262K tokens. This determines how much text, conversation history, and code the model can process in a single request.

Who created Kimi K2.7 Code?

Kimi K2.7 Code was created by Moonshot AI. It is classified as a open source model in our catalogue.

Is Kimi K2.7 Code open source?

Yes, Kimi K2.7 Code is an open-source model. The model weights are publicly available for download and self-hosting.