Claude Haiku 5.5
Small, fast Claude model for high-volume, latency-sensitive tasks.
From $0.10 in / $0.50 out per 1M tokensRouting, extraction and computer-use helpers on a budget
For prompts up to 100,000 tokens. Longer prompts cost $0.50 / $2.50. Checked 2026-10-14.
Quick start
Create an API key, store it in an environment variable, and send one small test request before wiring the model into your app.
Good and not so good
- Very low price
- Fast
- Price jumps for prompts over 100k tokens
Use cases with Claude Haiku 5.5
No use cases yet. Add an agent use case.