Claude Haiku 5.5 is built for high-volume, latency-sensitive work such as classification, routing, extraction, and subagent tasks. It features a 1M token context window, 128K max output tokens, adaptive thinking, and strong document and vision understanding.
Modalities
In / out price
$0.10 / $0.50per 1M
Cached price
$0.01per 1M
Context
1M
Max output
128K
Providers
1 routeCompare providers by price, privacy, and speed.
| Anonymous | $0.10$0.50 over 100K, not applied yet | $0.50$2.50 over 100K, not applied yet | $0.01$0.05 over 100K, not applied yet | 1M | 128K | — | — |
Privacy
1 / 4Anonymous routing
Anonymous tier
- Anonymous
- Private
- TEE
- E2EE
Your identity is hidden from the inference provider. The inference provider can see prompt content; zero retention is not guaranteed. Learn more
Features
8Streaming
Tool calling
Reasoning
Vision
JSON/schema
Web search
Code optimized
Prompt caching
Uptime
FAQ
Common questions about Claude Haiku 5.5.