Text Generation Model
Claude 5.5 Haiku
Text by Anthropic
Publisher
Anthropic
TypeText
Context Window1,000,000 tokens
ReleasedOctober 2026
Input$0.10/MTok
Output$0.50/MTok
Ready to build with Claude 5.5 Haiku?
Get Started FreeConfiguration
Parameters & options
Max Temperature1
Max Response Size128,000 tokens
ReasoningSelect
When enabled, the model uses adaptive thinking to decide when and how much to think before responding, and at lower effort it can skip thinking on simple requests. Adaptive thinking is on by default. Turning it off answers without thinking.
EffortSelect
Controls thinking depth, latency, and cost. The default is Medium. Higher effort improves quality but uses more tokens and is slower. Recommended: Low for classification, routing and extraction, Medium for general use, High or above for harder tasks. Only applies when Reasoning is enabled.
ToolsTools
Web SearchAllow models to search the web for the latest information before generating a response.
mcpServersMCP Servers
Related models
Explore similar models
Start building with Claude 5.5 Haiku
No API keys required. Create AI-powered workflows with Claude 5.5 Haiku in minutes — free.