modelgrep
M

MoonshotAI: Kimi K2.7 Code

moonshotai/kimi-k2.7-code

ReasoningToolsJSONVision
Use via OpenRouter ↗
Intelligence
Design Elo
1332
3D
Speed
33
226th fastest
Latency
988ms
first token
Input price
$0.750
186th cheapest
Context
262K
262K max out

How it compares

Faster than26%
of all ranked models
Cheaper than38%
of all ranked models

Overview

MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...

Benchmarks

independent · via OpenRouter
Design Arena · Elo2,103 tournaments
3D
1332
Website
1322
codecategories
1316
Game Dev
1294
Data Viz
1274
UI Component
1266
fullstack
1207

Providers & pricing (9)

ProviderIn $/MOut $/MUptime
Ambientint4$0.750$3.5098.1%
Parasailint4$0.750$3.5099.4%
Moonshot AIint4$0.950$4.00100%
Novita$0.950$4.00100%
Cloudflare$0.950$4.0091.9%
Io Netint4$0.950$4.00
AtlasCloudint4$0.950$4.0097.6%
Together$0.950$4.0099.8%
AkashMLint4$0.950$4.00

Specifications

Context window262K
Max output262K
Knowledge cutoff
Input modalitiestext, image
Output modalitiestext
Prompt caching
Cache read price$0.160/M
ModeratedNo

Kimi K2.7 Code FAQ

How much does Kimi K2.7 Code cost?

Kimi K2.7 Code costs $0.750 per million input tokens and $3.50 per million output tokens via OpenRouter, making it 186th cheapest of 298 paid models.

How fast is Kimi K2.7 Code?

Kimi K2.7 Code generates around 33 tokens per second with 988ms time-to-first-token (p50), the 226th fastest tracked model.

What is Kimi K2.7 Code's context window?

Kimi K2.7 Code supports a 262K-token context window and can output up to 262K tokens. It accepts text, image input.

Compare head-to-head