Skip to content
  • Models
  • Rankings
  • Ori
Sign Up
Sign Up
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Collections
  • Providers
  • Pricing
  • Business
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Trust Center
  • Support
  • Works With OR
  • Data
  • Brand

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube

By subscribing you agree to receive the OpenRouter newsletter: model usage data, product updates, and research reports, about one email a week. Unsubscribe anytime via the link in every email. See our Privacy Policy.

Favicon for moonshotai

MoonshotAI: Kimi K2.7 Code

moonshotai/kimi-k2.7-code

Model weights
Compare

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 architecture that accepts text and image input, and it always operates in a thinking mode, preserving full reasoning content across multi-turn conversations. With a 256K-token context window, it targets long-horizon coding, agentic task decomposition, and multi-turn dialogue. The model activates 32B parameters out of roughly 1T total.

Modalities

In / Out Price

$0.68 / $3.40per 1M

Context

262K

Released

Jun 12, 2026

Compare
ProvidersPricingPerformanceUptimeBenchmarksAppsActivityFAQExplore

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick — Balanced (price + speed), Nitro (fastest), or Exacto (highest tool-calling accuracy).

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Benchmarks

Scores on standardized evaluations. Higher percentages are better — and rank percentile shows where this model lands among all models on OpenRouter.

Benchmark score summary for MoonshotAI: Kimi K2.7 Code (Artificial Analysis and Design Arena)
SourceBenchmarkScore
Artificial AnalysisKimi K2.7 Code Intelligence Index26.3
Artificial AnalysisKimi K2.7 Code Coding Index60.8
Artificial AnalysisKimi K2.7 Code Agentic Index22.5
Artificial AnalysisKimi K2.7 Code GPQA Diamond89.6%
Artificial AnalysisKimi K2.7 Code HLE35.0%
Artificial AnalysisKimi K2.7 Code IFBench63.1%
Artificial AnalysisKimi K2.7 Code τ²-Bench Telecom90.1%
Artificial AnalysisKimi K2.7 Code AA-LCR79.3%
Artificial AnalysisKimi K2.7 Code GDPval-AA30.7%
Artificial AnalysisKimi K2.7 Code CritPt10.0%
Artificial AnalysisKimi K2.7 Code SciCode47.8%
Artificial AnalysisKimi K2.7 Code Terminal-Bench Hard44.7%
Artificial AnalysisKimi K2.7 Code AA-Omniscience Accuracy39.6%
Artificial AnalysisKimi K2.7 Code AA-Omniscience Non-Hallucination Rate17.6%
Design ArenaKimi K2.7 Code Agents Arena Agenticgamedev Elo1130
Design ArenaKimi K2.7 Code Agents Arena Androidnative Elo1151
Design ArenaKimi K2.7 Code Agents Arena Full Stack Elo1185
Design ArenaKimi K2.7 Code Agents Arena Godotgamedev Elo1185
Design ArenaKimi K2.7 Code Agents Arena Htmlslides Elo1204
Design ArenaKimi K2.7 Code Agents Arena Mobile Apps Elo1172
Design ArenaKimi K2.7 Code Agents Arena Python-Pptxslides Elo1154
Design ArenaKimi K2.7 Code Agents Arena Webapps Elo1190
Design ArenaKimi K2.7 Code Models Arena 3D Elo1270
Design ArenaKimi K2.7 Code Models Arena Asciiart Elo1220
Design ArenaKimi K2.7 Code Models Arena Code Categories Elo1271
Design ArenaKimi K2.7 Code Models Arena Data Visualization Elo1238
Design ArenaKimi K2.7 Code Models Arena Game Development Elo1243
Design ArenaKimi K2.7 Code Models Arena SVG Elo1202
Design ArenaKimi K2.7 Code Models Arena UI Component Elo1280
Design ArenaKimi K2.7 Code Models Arena Website Elo1280

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Activity

Token volume and request traffic to this model over time.

Quick Start

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Explore more models

AI Models with Vision: Multimodal LLMs for Image UnderstandingCollectionAI Model RankingsRanking

Frequently asked questions

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 architecture that accepts text and image input, and it always operates in a thinking mode, preserving full reasoning content across multi-turn conversations.

Kimi K2.7 Code costs $0.68/M input tokens and $3.40/M output tokens, with separate rates for Cache Read at $0.136/M tokens.

Kimi K2.7 Code has a 262,144 token context window. It supports up to 16,384 completion tokens.

Yes. Kimi K2.7 Code accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

Kimi K2.7 Code accepts text and images as input and returns text.

Kimi K2.7 Code is served by 14 providers on OpenRouter: DeepInfra, Inceptron, CoreWeave, StreamLake, Venice, ModelRun [by Modular], SiliconFlow, NovitaAI and 6 more. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

Kimi K2.7 Code was released on June 12, 2026.