Scan to join WeChat groupKimi K3
Kimi K3 for long-horizon coding, knowledge work, visual understanding and deep reasoning
Kimi K3 is Moonshot AI's flagship model with a 1M-token context window and native visual understanding for long-horizon coding, knowledge work and deep reasoning.
starsCapabilities
visibilityVision understandingcodeFunction callingdata_objectStructured output
paymentsContext and pricing
Context limit1,048,576
Max output—
Input price¥20/ 1M tokens
Output price¥100/ 1M tokens
Cached input price¥2/ 1M tokens
descriptionOverview
Overview
Kimi K3 is Moonshot AI's flagship model, with model ID kimi-k3, a 1,048,576-token context window, native visual understanding and always-on reasoning. Its default output limit is 131,072 tokens and the maximum configurable output is 1,048,576 tokens.
Best for
Kimi K3 is designed for long-horizon coding, end-to-end knowledge work, deep reasoning and agent workflows involving large codebases, long documents, images or video.
lightbulbUse cases
- Long-horizon coding and large codebases
- End-to-end knowledge work
- Deep reasoning and agent tasks
- Image and video understanding
thumb_upStrengths
- 1,048,576-token context window
- Native visual understanding
- Designed for long-horizon coding and knowledge work
- Configurable reasoning effort
infoLimitations
- Reasoning is always enabled
- Pricing and parameter limits follow the official Kimi documentation
- Large-context tasks still require cost and latency evaluation