Skip to main content
idapt
HomeAI ModelsExploreResourcesPricing
Sign inUse for Free
  • Home
  • Pricing
  • AI Models
  • Skills
  • Image models
  • Voice models
  • Video models
  • Rankings
  • Multi-Model Chat
  • Agents
  • Computers
  • Drive
  • Automations
  • AI Gateway
  • All features →
  • Blog
  • About
  • Comparisons
  • Benchmarks
  • Model Match
  • Demos
  • Help center
  • FAQ
  • Privacy
  • Support
  • Developers
  • Quickstarts
  • API reference
  • API pricing
  • CLI
  • MCP
  • Migrate
  • Downloads
  • Desktop
© idapt[email protected]TermsPrivacy PolicyLegal noticeReport content
X (Twitter)Discord

Kimi K2 (0905) vs Claude Haiku 5.5

At a glance

September 2025 checkpoint of Kimi K2 with improved capabilities.

262K ctx$0.60/$2.50 per M

Anthropic's fast, low-cost Claude Haiku for high-volume work, succeeding Claude Haiku 4.5.

1M ctx$0.10/$0.50 per M
Demos
All demos

No shared demos for these models yet.

AI Output
All AI outputs

No captured outputs for these models yet.

Benchmarks
See rankings
CodingInsufficient data
AgenticInsufficient data
ReasoningInsufficient data
MathInsufficient data
Sources:OpenRouter
Reasoning
CodingInsufficient data
AgenticInsufficient data
ReasoningInsufficient data
MathInsufficient data
Sources:OpenRouter
Cheaper81%
Specs
262K
Context
98K
Max output
Sep 2025
Released
1M
Context
128K
Max output
Oct 2026
Released
Capabilities
Vision
Audio
Reasoning
Vision
Audio
Reasoning
Pricing
Live pricing, shown before you run
Input$0.60/M tokens
Output$2.50/M tokens
Live pricing, shown before you run
Input83%$0.10/M tokens
Output80%$0.50/M tokens
Cache read$0.01/M tokens
Cache write$0.13/M tokens
Web search$0.01/search
Chat with Kimi K2 (0905)Go to model
Chat with Claude Haiku 5.5Go to model
Frequently Asked Questions: Kimi K2 (0905) vs Claude Haiku 5.5▼

Which is better, Kimi K2 (0905) or Claude Haiku 5.5?

▼

Both Kimi K2 (0905) and Claude Haiku 5.5 are capable AI models. The best choice depends on your specific use case: consider pricing, context window, speed, and which capabilities (vision, reasoning, audio) you need.

Which is cheaper, Kimi K2 (0905) or Claude Haiku 5.5?

▼

Claude Haiku 5.5 has a lower blended cost. Kimi K2 (0905): $0.60 input / $2.50 output. Claude Haiku 5.5: $0.10 input / $0.50 output.

Which has a larger context window, Kimi K2 (0905) or Claude Haiku 5.5?

▼

Claude Haiku 5.5 has a larger context window: Kimi K2 (0905) supports 262K tokens vs Claude Haiku 5.5 at 1M tokens.

Do both Kimi K2 (0905) and Claude Haiku 5.5 support vision?

▼

Claude Haiku 5.5 supports vision/image input, but Kimi K2 (0905) does not.

What are the key differences between Kimi K2 (0905) and Claude Haiku 5.5?

▼

Key differences: Claude Haiku 5.5 is significantly cheaper; only Claude Haiku 5.5 supports vision input; only Claude Haiku 5.5 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 (0905) and Claude Haiku 5.5 for free on idapt.app to see which performs better for your specific needs.

Open in App