Vertex

Kimi K2 Thinking — Benchmark Scores, Pricing & Performance Analysis

OPEN SOURCE
Input Cost
$0.60/1M
Output Cost
$2.5/1M
Context Window
262K
Max Output
262K
Knowledge Cutoff
Aug 2024
Accepts
text

Kimi K2 Thinking is an AI model by Vertex. 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
112578th of 120

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

Design Arena (via OpenRouter)
AA Coding Index
2174th of 96

Artificial Analysis composite coding score

Artificial Analysis (via OpenRouter)
Website Arena ELO
112577th of 108

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

Design Arena (via OpenRouter)

Reasoning Benchmarks

GPQA Diamond
83.4%45th of 140

Graduate-level science Q&A by domain experts

Papers
τ²-Bench Airline
69.2%51st of 93

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

OpenRouter (measured)

Cost Benchmarks

Input Cost
$0.60258th of 413

Cost per 1M input tokens

OpenRouter API
Output Cost
$2.5265th 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 21 providers

The same model costs different amounts depending on who serves it. You can bring your own key for 5 of these — connect it here.

ProviderInput / 1MOutput / 1MCached inContextYour key
OpenCode Zen$0.4$2.5$0.4262K
Vercel AI Gateway$0.47$2$0.141216KSupported
Helicone$0.48$2256K
IO.NET$0.55$2.25$0.27533K
302.AI$0.575$2.3262K
Amazon Bedrock$0.6$2.5262KSupported
Charm Hyper$0.6$2.5$0.3262K
DevPass (LLM Gateway)$0.6$2.5$0.06262K
Eden AI$0.6$2.5128K
Hugging Face$0.6$2.5$0.15262KSupported
Kilo Gateway$0.6$2.5$0.15262K
LLM Gateway$0.6$2.5$0.06262K
Meganova$0.6$2.6262K
Merge Gateway$0.6$2.5262K
NanoGPT$0.6$2.5$0.15262K
NovitaAI$0.6$2.5$0.15262K
OpenRouter$0.6$2.5$0.15262KSupported
Vertex$0.6$2.5$0.06262KSupported
ZenMux$0.6$2.5$0.15262K
Poe256K
Qiniu256K

Kimi K2 Thinking — Benchmark Scores Overview

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

Kimi K2 Thinking — Frequently Asked Questions

How much does Kimi K2 Thinking cost?

Kimi K2 Thinking costs $0.60 per 1M input tokens and $2.5 per 1M output tokens. This is mid-range pricing for its capability level.

What is the context window of Kimi K2 Thinking?

Kimi K2 Thinking 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 Thinking?

Kimi K2 Thinking was created by Vertex. It is classified as a open source model in our catalogue.

Is Kimi K2 Thinking open source?

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