Anthropic · Efficient
Claude Haiku 5.5
Anthropic's fast tier for classification, extraction and routing, now with a 1M-token window. The only current Claude model priced by prompt length: ten cents in and fifty cents out per million tokens up to 100,000 prompt tokens, five times that above.
Model ID: claude-haiku-5-5
What that means
A worked example
Per-token pricing is hard to feel. Take a moderately chatty production workload: 100 calls a day, roughly 10,000 tokens in and 2,000 out each time. On Claude Haiku 5.5 that comes to about:
$6 / month
Before caching, batching or volume discounts, all of which move this number a long way. Illustrative only.
Strong at
- -Very low cost under 100K tokens
- -Speed
- -1M context
Typical use
- -Classification
- -Extraction
- -Subagent workers
Watch out for
- -Sampling parameters, budget_tokens thinking and assistant prefill return a 400 error
- -Long prompts cost five times the short-prompt rate
Same tier
What else to look at
| Model | Developer | Context | In / 1M | Out / 1M |
|---|---|---|---|---|
| Claude Haiku 4.5 | Anthropic | 200K | $1 | $5 |
| GPT-6 Luna | OpenAI | 1.05M | $0.10 | $0.50 |
| GPT-5.6 Luna | OpenAI | 1.05M | $0.20 | $1.20 |
| Gemini 3.5 Flash-Lite | 1.05M | $0.30 | $2.50 | |
| DeepSeek V4.1 Flash | DeepSeek | 1M | $0.30 | $1.20 |
Verified 2026-10-11.