Kimi K2 Thinking

Kimi K2 Thinking is an open-source model that operates as a "thinking agent," reasoning step-by-step while using tools to achieve state-of-the-art performance on various benchmarks. It is capable of executing up to 200-300 sequential tool calls without human intervention, allowing it to solve complex problems across a wide range of tasks. The model uses Quantization-Aware Training (QAT) to support INT4 inference, which provides a roughly 2x improvement in generation speed.

Managed API (MaaS) specifications

View model card in Model Garden

Model ID kimi-k2-thinking-maas
Launch stage GA
Supported inputs & outputs
  • Inputs:
    Text, Documents
  • Outputs:
    Text
Capabilities
Usage types
Versions
  • Kimi K2 Thinking
    • Launch stage: GA
    • Release date: Nov 13, 2025
Supported regions

Model availability
  • Region
    • global

ML processing
  • Region
    • Multi-region
Limits

global:

  • Max output: 262144
  • Context length: 262144
Pricing See Pricing.

Deploy as a self-deployed model

To self-deploy the model, navigate to the Kimi K2 Thinking model card in the Model Garden console and click Deploy model. For more information about deploying and using partner models, see Deploy a partner model and make prediction requests.