Skip to main content
idapt
HomeCodeAI ModelsPricing
Sign inStart free
MoonshotAI

Kimi K2

Legacy$$Standard
MoonshotAI#32 of 92
CompareChat

MoonshotAI's large MoE model — 1T total parameters, 32B active. Optimized for agentic tasks with strong tool use and long-context reasoning. Superseded by K2.5.

▼

Kimi K2 by MoonshotAI has a Capability Index of 78.2, making it comparable to the field average. It ranks #32 out of 92 models on the idapt capability leaderboard. Kimi K2 is somewhat expensive at $0.57/M tokens input and $2.30/M tokens output. The model supports a 131K context window.

Best forFrontier reasoningCost-effective

Benchmarks

CodingInsufficient data
ReasoningInsufficient data
MathInsufficient data
Sources:Epoch ECI·Epoch AI·OpenRouter· as of 2026-07-10

Category Rankings

Capability
#32of 92
Agentic
#33of 45

Specifications

Vision
Audio
Reasoning
MoE
Architecture
1T
Parameters
32B
Active
131K
Context
100K
Max output

Performance

Providers

Misc

July 11, 2025
Released
Same family
MoonshotAIKimi K2 ThinkingMoonshotAIKimi K2.6MoonshotAIKimi K2.7 Code
CompareChat with Kimi K2

Compare with

OpenAIGPT 5.6 Solvs Kimi K2OpenAIGPT 5.6 Lunavs Kimi K2AnthropicClaude Fable 5vs Kimi K2AnthropicClaude Opus 4.8vs Kimi K2AnthropicClaude Sonnet 5vs Kimi K2AnthropicClaude Haiku 4.5vs Kimi K2GoogleGemini 3.6 Flashvs Kimi K2GoogleGemini 3.5 Flashvs Kimi K2GoogleGemini 3.5 Flash-Litevs Kimi K2GoogleGemma 4 31Bvs Kimi K2xAIGrok 4.5vs Kimi K2xAIGrok Build 0.1vs Kimi K2xAIGrok 4.1 Fastvs Kimi K2MetaMuse Spark 1.1vs Kimi K2DeepSeekDeepSeek V4 Provs Kimi K2DeepSeekDeepSeek V4 Flashvs Kimi K2MiniMaxMiniMax M3vs Kimi K2MoonshotAIKimi K3vs Kimi K2MoonshotAIKimi K2.7 Codevs Kimi K2Zhipu AIGLM 5.2vs Kimi K2QwenQwen3.7 Maxvs Kimi K2QwenQwen3.7 Plusvs Kimi K2QwenQwen3 Coder Nextvs Kimi K2NVIDIANemotron 3 Ultravs Kimi K2Mistral AIMistral Small 4vs Kimi K2
Frequently Asked Questions about Kimi K2▼

When was Kimi K2 released?

▼

Kimi K2 was released on July 11, 2025.

Who created Kimi K2?

▼

Kimi K2 was created by MoonshotAI.

How capable is Kimi K2?

▼

Kimi K2 has a Capability Index of 78.2/100, making it comparable to the field average. It ranks #32 out of 92 models.

How much does Kimi K2 cost?

▼

Kimi K2 costs $0.57/M input tokens and $2.30/M output tokens.

What is Kimi K2 API pricing?

▼

The Kimi K2 API is priced at $0.57 per million input tokens and $2.30 per million output tokens. You can access Kimi K2 through idapt.app alongside 200+ other AI models in one workspace.

Is Kimi K2 a reasoning model?

▼

No, Kimi K2 is not a reasoning model. It responds directly without an extended internal thinking step. For tasks requiring deep chain-of-thought reasoning, consider models like Claude, o-series from OpenAI, or Gemini Thinking.

Does Kimi K2 support image or vision input?

▼

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

Does Kimi K2 support audio?

▼

No, Kimi K2 does not support audio input.

What is the context window of Kimi K2?

▼

Kimi K2 has a context window of 131K tokens, meaning it can process approximately 98,304 words of context at once.

Is Kimi K2 open source?

▼

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

Where can I use Kimi K2?

▼

You can chat with Kimi K2 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 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)