Moonshot AI

Kimi K2.6 — Benchmark Scores, Pricing & Performance Analysis

OPEN SOURCEMoonshot AI
Input Cost
$0.95/1M
Output Cost
$4.0/1M
Context Window
262K
Max Output
262K
Knowledge Cutoff
Jan 2025
Accepts
text, image, video

Kimi K2.6 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.

Coding Benchmarks

Design Arena ELO
126025th of 120

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

Design Arena (via OpenRouter)
AA Coding Index
61.831st of 96

Artificial Analysis composite coding score

Artificial Analysis (via OpenRouter)
Website Arena ELO
128220th of 108

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

Design Arena (via OpenRouter)

Reasoning Benchmarks

AA Agentic Index
22.133rd of 70

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

Artificial Analysis (via OpenRouter)
GPQA Diamond
83.3%48th of 140

Graduate-level science Q&A by domain experts

Papers
τ²-Bench Airline
73.7%32nd of 93

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

OpenRouter (measured)

Cost Benchmarks

Input Cost
$0.95290th of 413

Cost per 1M input tokens

OpenRouter API
Output Cost
$4.0294th of 413

Cost per 1M output tokens

OpenRouter API
Cached Input Cost
$0.1686th 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 65 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—
Nvidia$0$0—262K—
SCNet Token Plan$0$0$0262K—
routing.run$0.275$1.1—200K—
Vultr$0.3$1.2—262K—
CrofAI$0.5$1.99$0.05262K—
NanoGPT$0.5$2.6$0.125256K—
Inceptron$0.53$3.39$0.17262K—
DevPass (LLM Gateway)$0.6$3.05$0.13262K—
LLM Gateway$0.6$3.05$0.13262K—
Weights & Biases$0.65$3.41$0.15262K—
Crusoe$0.7$3.5$0.35262K—
Lilac$0.7$3.5$0.2262K—
Infomaniak$0.74$3.72—256K—
Deep Infra$0.75$3.5$0.15262KSupported
FastRouter$0.75$3.5—262K—
Venice AI$0.75$3.5$0.16256K—
GreenPT$0.7524$4.275$0.2508262K—
Cortecs$0.773$3.38$0.193262K—
Kilo Gateway$0.8$3.4$0.16262K—
NovitaAI$0.8$3.4$0.16262K—
GMI Cloud$0.855$3.6$0.14466K—
EmpirioLabs AI$0.8939$3.7131$0.1788256K—
EBCloud$0.9286$3.8571—262K—
302.AI$0.95$4—262K—
Abacus$0.95$4$0.19262K—
AIHubMix$0.95$4$0.16262K—
Ambient$0.95$4$0.2262K—
Auriko$0.95$4$0.16262K—
Azure$0.95$4—262KSupported
Azure Cognitive Services$0.95$4—262K—
Baseten$0.95$4$0.16262KSupported
Clarifai$0.95$4—262K—
ClinePass$0.95$4$0.16262K—
Cloudflare Workers AI$0.95$4$0.16262KSupported
DigitalOcean$0.95$4$0.19262K—
Eden AI$0.95$4$0.16262K—
Fireworks AI$0.95$4$0.16262KSupported
FrogBot$0.95$4$0.16256K—
Hugging Face$0.95$4$0.16262KSupported
Merge Gateway$0.95$4$0.16262K—
Moonshot AI$0.95$4$0.16262KSupported
Moonshot AI (China)$0.95$4$0.16262K—
Ofox$0.95$4$0.16262K—
OpenCode Go$0.95$4$0.16262K—
OpenCode Zen$0.95$4$0.16262K—
OpenRouter$0.95$4$0.16262KSupported
OrcaRouter$0.95$4$0.16262K—
Pioneer$0.95$4$0.34262K—
Requesty$0.95$4$0.95256K—
TokenGo$0.95$4$0.16262K—
Vercel AI Gateway$0.95$4$0.16262KSupported
ZenMux$0.95$4$0.16262K—
Poe$0.96$4.04$0.16262K—
CrossModel$1$4.16$0.18262K—
TensorX$1$4$0.25262K—
Charm Hyper$1.03436$4.3552$0.174208262K—
Wafer$1.14$4.8$0.19262K—
Together AI$1.2$4.5$0.2262KSupported
UnoRouter$1.2675$5.3368—262K—
evroc$1.4375$5.75—262K—
Privatemode AI$1.791$8.9436$0.1733256K—
Ollama Cloud———262K—

Kimi K2.6 — Benchmark Scores Overview

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

Kimi K2.6 — Frequently Asked Questions

How much does Kimi K2.6 cost?

Kimi K2.6 costs $0.95 per 1M input tokens and $4.0 per 1M output tokens. This is mid-range pricing for its capability level.

What is the context window of Kimi K2.6?

Kimi K2.6 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 K2.6?

Kimi K2.6 was created by Moonshot AI. It is classified as a open source model in our catalogue.

Is Kimi K2.6 open source?

Yes, Kimi K2.6 is an open-source model. The model weights are publicly available for download and self-hosting.