Skip to main content
idapt
HomeAI ModelsPricing
Sign inStart free

Kimi K2.7 Code vs Claude 3.5 Haiku

At a glance
MoonshotAIKimi K2.7 Code

MoonshotAI's coding-focused Kimi model for end-to-end software engineering.

82262K ctx$0.74/$3.50 per M#20/92
AnthropicClaude 3.5 Haiku

Fast and accurate with enhanced coding and tool use capabilities.

61200K ctx$0.80/$4.00 per M#68/92
AI Output
All AI outputs

No captured outputs for these models yet.

Benchmarks
See rankings
MoonshotAIKimi K2.7 Code
Reasoning
CodingInsufficient data
AgenticInsufficient data
Sources:Epoch ECI·Epoch AI·OpenRouter· as of 2026-07-10
SmarterCheaper
Capability
CapabilityECI81.8
Reasoning & Knowledge
Graduate Science89.5%Factual Recall39.2%
Math
Math Problems—Competition Math96.4%Research Math—
Coding
Code Editing—
AnthropicClaude 3.5 Haiku
CodingInsufficient data
AgenticInsufficient data
Sources:Epoch ECI·Epoch AI·OpenRouter· as of 2026-07-10
Capability
CapabilityECI61.4
Reasoning & Knowledge
Graduate Science38.1%Factual Recall6.7%
Math
Math Problems46.4%Competition Math4.3%Research Math0.3%
Coding
Code Editing28.0%
Specs
MoonshotAIKimi K2.7 Code
262K
Context
16K
Max output
Jun 2026
Released
AnthropicClaude 3.5 Haiku
200K
Context
8K
Max output
Nov 2024
Released
Capabilities
MoonshotAIKimi K2.7 Code
Vision
Audio
Reasoning
AnthropicClaude 3.5 Haiku
Vision
Audio
Reasoning
Pricing
MoonshotAIKimi K2.7 Code
Live pricing, shown before you run
Input$0.74/M tokens
Output$3.50/M tokens
Cache read$0.15/M tokens
AnthropicClaude 3.5 Haiku
Live pricing, shown before you run
Input$0.80/M tokens
Output$4.00/M tokens
Cache read$0.08/M tokens
Cache write$1.00/M tokens
Web search$0.01/search
Chat with Kimi K2.7 CodeGo to model
Chat with Claude 3.5 HaikuGo to model
Frequently Asked Questions: Kimi K2.7 Code vs Claude 3.5 Haiku▼

Which is better, Kimi K2.7 Code or Claude 3.5 Haiku?

▼

Based on the Capability Index, Kimi K2.7 Code scores higher (81.8 vs 61.4). However, "better" depends on your use case — pricing, speed, context window, and specific capability needs all matter.

Which is cheaper, Kimi K2.7 Code or Claude 3.5 Haiku?

▼

Kimi K2.7 Code has a lower blended cost. Kimi K2.7 Code: $0.74 input / $3.50 output. Claude 3.5 Haiku: $0.80 input / $4.00 output.

Which has a larger context window, Kimi K2.7 Code or Claude 3.5 Haiku?

▼

Kimi K2.7 Code has a larger context window: Kimi K2.7 Code supports 262K tokens vs Claude 3.5 Haiku at 200K tokens.

Do both Kimi K2.7 Code and Claude 3.5 Haiku support vision?

▼

Yes, both Kimi K2.7 Code and Claude 3.5 Haiku support vision/image input.

What are the key differences between Kimi K2.7 Code and Claude 3.5 Haiku?

▼

Key differences: Kimi K2.7 Code has a notably higher capability index (20.4 point gap); only Kimi K2.7 Code 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 K2.7 Code and Claude 3.5 Haiku for free on idapt.app to see which performs better for your specific needs.

Open in App
  • 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
  • Secrets
  • Sharing
  • Workspaces
  • Tasks
  • Memory
  • Agents
  • Subagents
  • Automations
  • Skills
  • Code Execution
  • Computers
  • Computer Use
  • Cloud Computers
  • Local AI
  • AI Gateway
  • API & SDK
  • CLI
  • MCP
  • Tunnels
  • All features →
  • Blog
  • Use cases
  • Comparisons
  • Best of
  • Learn
  • Free tools
  • Prompts
  • Templates
  • Changelog
  • Help center
  • FAQ
  • Privacy
  • Compare all models
  • Support
  • Developers
  • Quickstarts
  • API reference
  • API pricing
  • CLI
  • MCP
  • Downloads
  • Desktop
  • Badges and embeds
© idapt[email protected]TermsPrivacy PolicyLegal noticeReport content
X (Twitter)