Skip to main content
idapt
HomeCodeAI ModelsPricing
Sign inStart free
MoonshotAI

Kimi K2 Thinking

$$Standard
MoonshotAI
CompareChat

Kimi K2 with always-on extended reasoning for complex problem solving. MoE model with visible thinking chains. Strong at math, coding, and agentic tasks requiring deep reasoning.

▼

Kimi K2 Thinking is somewhat expensive at $0.60/M tokens input and $2.50/M tokens output. Cached input reads are priced at $0.15/M tokens, making repeated context cheaper. The model supports extended reasoning, a 262K context window.

Best forCost-effective

Benchmarks

No benchmarks available

This model hasn't been evaluated by Artificial Analysis yet. Benchmark scores will appear once they're published.

Specifications

Vision
Audio
Reasoning
MoE
Architecture
262K
Context
100K
Max output

Performance

Providers

Misc

November 6, 2025
Released
Same family
MoonshotAIKimi K2.6MoonshotAIKimi K2.7 CodeMoonshotAIKimi K2
CompareChat with Kimi K2 Thinking

Compare with

OpenAIGPT 5.6 Solvs Kimi K2 ThinkingOpenAIGPT 5.6 Lunavs Kimi K2 ThinkingAnthropicClaude Fable 5vs Kimi K2 ThinkingAnthropicClaude Opus 4.8vs Kimi K2 ThinkingAnthropicClaude Sonnet 5vs Kimi K2 ThinkingAnthropicClaude Haiku 4.5vs Kimi K2 ThinkingGoogleGemini 3.6 Flashvs Kimi K2 ThinkingGoogleGemini 3.5 Flashvs Kimi K2 ThinkingGoogleGemini 3.5 Flash-Litevs Kimi K2 ThinkingGoogleGemma 4 31Bvs Kimi K2 ThinkingxAIGrok 4.5vs Kimi K2 ThinkingxAIGrok Build 0.1vs Kimi K2 ThinkingxAIGrok 4.1 Fastvs Kimi K2 ThinkingMetaMuse Spark 1.1vs Kimi K2 ThinkingDeepSeekDeepSeek V4 Provs Kimi K2 ThinkingDeepSeekDeepSeek V4 Flashvs Kimi K2 ThinkingMiniMaxMiniMax M3vs Kimi K2 ThinkingMoonshotAIKimi K3vs Kimi K2 ThinkingMoonshotAIKimi K2.7 Codevs Kimi K2 ThinkingZhipu AIGLM 5.2vs Kimi K2 ThinkingQwenQwen3.7 Maxvs Kimi K2 ThinkingQwenQwen3.7 Plusvs Kimi K2 ThinkingQwenQwen3 Coder Nextvs Kimi K2 ThinkingNVIDIANemotron 3 Ultravs Kimi K2 ThinkingMistral AIMistral Small 4vs Kimi K2 Thinking
Frequently Asked Questions about Kimi K2 Thinking▼

When was Kimi K2 Thinking released?

▼

Kimi K2 Thinking was released on November 6, 2025.

Who created Kimi K2 Thinking?

▼

Kimi K2 Thinking was created by MoonshotAI.

How much does Kimi K2 Thinking cost?

▼

Kimi K2 Thinking costs $0.60/M input tokens and $2.50/M output tokens.

What is Kimi K2 Thinking API pricing?

▼

The Kimi K2 Thinking API is priced at $0.60 per million input tokens and $2.50 per million output tokens. You can access Kimi K2 Thinking through idapt.app alongside 200+ other AI models in one workspace.

Is Kimi K2 Thinking a reasoning model?

▼

Yes, Kimi K2 Thinking is a reasoning model. It can think step-by-step through complex problems before providing an answer, often yielding better results on difficult tasks like math, coding, and multi-step logic.

Does Kimi K2 Thinking support image or vision input?

▼

No, Kimi K2 Thinking does not currently support image or vision input. It is a text-only model.

Does Kimi K2 Thinking support audio?

▼

No, Kimi K2 Thinking does not support audio input.

What is the context window of Kimi K2 Thinking?

▼

Kimi K2 Thinking has a context window of 262K tokens, meaning it can process approximately 196,608 words of context at once.

Is Kimi K2 Thinking open source?

▼

Kimi K2 Thinking is a proprietary model developed by MoonshotAI. The model weights and training data are not publicly available.

Where can I use Kimi K2 Thinking?

▼

You can chat with Kimi K2 Thinking on idapt.app — no separate API key required. idapt is an AI workspace with 200+ models, agents, computers, and tasks. You can also access Kimi K2 Thinking through MoonshotAI's own API or platform.

  • Home
  • Pricing
  • AI Models
  • Image models
  • Voice models
  • Video models
  • Rankings
  • New models
  • Model status
  • Multi-Model Chat
  • Voice Mode
  • Voice HUD
  • Web Search
  • Image Generation
  • Video Generation
  • Audio Generation
  • Transcription
  • Drive
  • Credentials
  • Sharing
  • Workspaces
  • Tasks
  • Memory
  • Agents
  • Subagents
  • Automations
  • Skills
  • idapt Code
  • Code Execution
  • Computers
  • Computer Use
  • Computer Assist · Soon
  • Containers · Soon
  • Cloud Computers
  • Local AI
  • AI Gateway
  • API & SDK
  • CLI
  • MCP
  • Tunnels
  • All features →
  • LLM cost calculator
  • Token counter
  • Context window checker
  • Can I run it
  • Model picker quiz
  • Savings finder
  • Video cost estimator
  • Text to speech cost
  • Transcription cost
  • API endpoint tester
  • All free tools →
  • Blog
  • Use cases
  • Comparisons
  • Best of
  • Skills
  • Learn
  • Changelog
  • Help center
  • FAQ
  • Privacy
  • Compare all models
  • Support
  • idapt Code
  • Developers
  • Quickstarts
  • API reference
  • API pricing
  • CLI
  • MCP
  • Downloads
  • Desktop
  • Badges and embeds
© idapt[email protected]TermsPrivacy PolicyLegal noticeReport content
X (Twitter)