Kimi K3

Name: Kimi K3
Author: Moonshot AI

by Moonshot AIKimi

APIAvailable through a hosted API — pay per token, no self-hosting required

Released July 20261049K context≈ 786,432 words2.8T params

Moonshot AI top-tier reasoning model competing with frontier closed-source systems. Excels at long-context tasks, agentic coding, and structured output generation. First Kimi model to ship at the 1M-token context tier with flat pricing.

Capabilities

Capability scores are AI-generated based on model documentation, benchmarks, and technical specifications. Learn more

Flagship text generation

Exceptional

1M token context

Exceptional

Long-horizon coding

Use Case Fit

Fit scores are AI-generated based on model capabilities, intended use, and technical specifications. Learn more

Exceptional

Strong

Kimi K3

by Moonshot AIKimi

APIAvailable through a hosted API — pay per token, no self-hosting required

Released July 20261049K context≈ 786,432 words2.8T params

Moonshot AI top-tier reasoning model competing with frontier closed-source systems. Excels at long-context tasks, agentic coding, and structured output generation. First Kimi model to ship at the 1M-token context tier with flat pricing.

Capabilities

Capability scores are AI-generated based on model documentation, benchmarks, and technical specifications. Learn more

Flagship text generation

Exceptional

1M token context

Exceptional

Long-horizon coding

Use Case Fit

Fit scores are AI-generated based on model capabilities, intended use, and technical specifications. Learn more

Exceptional

Strong

Glossary

AgenticA model designed to act autonomously by making decisions, selecting actions, and using tools to accomplish multi-step tasks.Agentic CodingAn approach where an AI model autonomously plans and executes multi-step coding tasks, making decisions about which files to modify and how to structure solutions.Long-ContextThe ability of a model to process and understand very long sequences of text while maintaining coherence across distant parts of the input.ReasoningThe model's ability to work through multi-step logical problems and provide justified answers rather than just pattern-matching.Reasoning ModelA model trained to show explicit step-by-step reasoning and problem-solving logic before producing final answers, rather than jumping directly to conclusions.Structured OutputResponses formatted in a consistent, machine-readable way (like JSON or XML) rather than free-form text.Structured Output GenerationThe ability to produce outputs in specific formats like JSON or XML rather than just free-form text.TokenA small unit of text (a word, subword, or punctuation mark) that a language model breaks input into for processing.