Skip to main content
idapt
HomeCodeAI ModelsPricing
Sign inStart free
  • 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)

Kimi K2 vs Gemini 3.5 Flash

At a glance

MoonshotAI's large MoE model — 1T total parameters, 32B active.

78131K ctx$0.57/$2.30 per M#32/92

Google's high-speed thinking model for agentic workflows, chat, and coding.

861.0M ctx$1.50/$9.00 per M#11/92
Agent Demos
All agent demos

No shared agent demos for these models yet.

AI Output
All AI outputs

No captured outputs for these models yet.

Benchmarks
See rankings
CodingInsufficient data
ReasoningInsufficient data
MathInsufficient data
Sources:Epoch ECI·Epoch AI·OpenRouter· as of 2026-07-10
Cheaper70%
Capability
CapabilityECI78.2
Reasoning & Knowledge
Graduate Science—Factual Recall—
Math
Competition Math—Research Math—
Coding
Real-World Coding—
Agentic
Terminal Tasks35.7%Novel Reasoning—Task Horizon54min
Reasoning
AgenticInsufficient data
Sources:Epoch ECI·Epoch AI·OpenRouter· as of 2026-07-10
Smarter10%
Capability
CapabilityECI10%86.2
Reasoning & Knowledge
Graduate Science92.8%Factual Recall68.4%
Math
Competition Math95.6%Research Math39.0%
Coding
Real-World Coding79.3%
Agentic
Terminal Tasks—Novel Reasoning72.1%Task Horizon—
Specs
131K
Context
100K
Max output
Jul 2025
Released
1.0M
Context
66K
Max output
May 2026
Released
Capabilities
Vision
Audio
Reasoning
Vision
Audio
Reasoning
Pricing
Live pricing, shown before you run
Input62%$0.57/M tokens
Output74%$2.30/M tokens
Live pricing, shown before you run
Input$1.50/M tokens
Output$9.00/M tokens
Reasoning$9.00/M tokens
Cache read$0.15/M tokens
Cache write$0.08/M tokens
Image input$1.50/M tokens
Audio input$3.00/M tokens
Web search$0.01/search
Chat with Kimi K2Go to model
Chat with Gemini 3.5 FlashGo to model
Frequently Asked Questions: Kimi K2 vs Gemini 3.5 Flash▼

Which is better, Kimi K2 or Gemini 3.5 Flash?

▼

Based on the Capability Index, Gemini 3.5 Flash scores higher (86.2 vs 78.2). However, "better" depends on your use case — pricing, speed, context window, and specific capability needs all matter.

Which is cheaper, Kimi K2 or Gemini 3.5 Flash?

▼

Kimi K2 has a lower blended cost. Kimi K2: $0.57 input / $2.30 output. Gemini 3.5 Flash: $1.50 input / $9.00 output.

Which has a larger context window, Kimi K2 or Gemini 3.5 Flash?

▼

Gemini 3.5 Flash has a larger context window: Kimi K2 supports 131K tokens vs Gemini 3.5 Flash at 1M tokens.

Do both Kimi K2 and Gemini 3.5 Flash support vision?

▼

Gemini 3.5 Flash supports vision/image input, but Kimi K2 does not.

What are the key differences between Kimi K2 and Gemini 3.5 Flash?

▼

Key differences: Gemini 3.5 Flash has a notably higher capability index (8.0 point gap); Kimi K2 is significantly cheaper; only Gemini 3.5 Flash supports vision input; only Gemini 3.5 Flash offers extended reasoning mode. Compare full specs on this page.

Which model should I choose for my use case?

▼

If cost is your priority, choose the cheaper option. If you need the highest intelligence for complex tasks, pick the higher-scoring model. For long documents or codebases, choose the larger context window. You can try both Kimi K2 and Gemini 3.5 Flash for free on idapt.app to see which performs better for your specific needs.

Open in App