AI Model Radar
中文 EN

Kimi K2.7 Code

Moonshot AI / Kimi
Model overview

kimi-k2.7-code

Moonshot's current coding model for software-engineering agents with image/video input and tool use.

general LLMreasoningcodingvision-languageagentlong contextcode generationsoftware engineering agentlocal inferenceenterprise access
External observationsCross-model riskCompareCompanyRankingsPublic signals
Model risk

Current observations

1current adverse observations
Negative / riskAPI / serviceRuntime behaviorOfficial · Current risk

The coding endpoint is always-thinking, so latency and output tokens cannot be estimated like a standard chat model

Moonshot's quickstart describes K2.7 Code as an always-thinking tool-use model, which can increase end-to-end latency and output cost in long agent loops.

Kimi K2.7 Code quickstartHigh confidenceObserved 2026-06-11Source as of 2026-07-15 Action

Measure completion time and total tokens on real repository tasks, not only single-response speed.

Open source
Representative version

kimi-k2.7-code

CompanyMoonshot AI / Kimi
Release2026-06-12
Release typeModel release
ParametersNot disclosed
ArchitectureNot disclosed
Context262,144
Input modalitiestext / image / video
Output modalitiestext / code / tool_call
Tool use / function callingConfirmed: Tool use, Function calling
Structured output / reasoningConfirmed: Reasoning
Vision / audio / videoConfirmed: Vision, Video
Open weights / LicenseWeights available / Modified MIT (license source pending verification)
moonshot-kimi-kimi-k2-7-code-current · License source pending verification
Vendor APIAvailable
Kimi Code what's newmoonshot-kimi-kimi-k2-7-code-current · 2026-06-12
OpenRouterOpenRouter listed
PricingOpenRouter · 2026-08-11: $0.7 / $3.5
input / output, per 1M tokens
BenchmarkNo reliable public source
Public signalsNo reliable public source
Use casesSoftware engineering agents / Repository-scale coding / Visual coding tasks / local inference
Claim evidenceRelease eventKimi Code what's newkimi-k2.7-code · 2026-06-12
Model specifications / Weight checkpointKimi K2.7 Code quickstartKimi K2.7 Code · kimi-k2.7-code · kimi-k2.7-code
OpenRouter context / capabilities / pricingOpenRouter public models APImoonshotai/kimi-k2.7-code · 2026-08-11T06:28:09.895Z
OpenRouter

Pricing / context / availability

OpenRouterOpenRouter listed
OpenRouter listingmoonshotai/kimi-k2.7-code
Mapped versionkimi-k2.7-code
moonshot-kimi-kimi-k2-7-code-current
PricingOpenRouter · 2026-08-11: $0.7 / $3.5
input / output, per 1M tokens
Context262144
Speed/LatencyNo reliable public source
Snapshot time2026-08-11T06:28:09.895Z
SourceView source
Verified limitations

Usage boundaries

  • The model runs in an always-thinking mode; latency and token use should be measured on real agent loops.
Missing public information

Public information not yet available

Parameter scale not disclosedNo reliable benchmark sourceNo public model-card activity countersNo linkable model-specific reviewSpeed/latency not disclosed