Kimi

Kimi K2 Thinking

moonshotai
Chat

Kimi K2 Thinking is Moonshot AI's open-weight thinking model, a Mixture-of-Experts model with about 1 trillion total parameters and 32 billion active per token. It takes text input and produces text output, with a 256K-token context window. It is built to interleave step-by-step reasoning with function calls, and is designed to stay goal-directed across 200 to 300 sequential tool calls for research, coding and writing tasks.

Modalities

In / out price

$0.69 / $2.90per 1M

Context

256K

Max output

16K

Updated

Nov 5, 2026

Providers

3 routes

Compare providers by price, privacy, and speed.

Amazon Bedrock
Private$0.69$2.90—256K16K——
Cheaper Inference
Anonymous$0.61$2.60$0.18256K98K——
Surplus Intelligence
Anonymous$0.84$3.50$0.21256K66K——

Privacy

2 / 4

Private routing

Private tier

  1. Anonymous
  2. Private
  3. TEE
  4. E2EE

Prompt and response content is not retained after the request. Request content is visible to the inference runtime while it is being processed. Learn more

Features

3
Streaming
Tool calling
Reasoning

Uptime

FAQ

Common questions about Kimi K2 Thinking.