| Item | Price per million tokens |
|---|---|
| Input | $0.1 |
| Output (incl. thinking) | $0.5 |
| Cache write, 5 minutes | $0.125 |
| Cache write, 1 hour | $0.2 |
| Cache read | $0.01 |
| Batch API input / output | $0.05 / $0.25 |
| Prompts over 100,000 tokens: input / output | $0.5 / $2.5 |
Model id: claude-haiku-5-5
What it costs in practice
| Request | One request | 1,000 requests | One request, Batch API |
|---|---|---|---|
| Short chat reply 2,000 in / 300 out | $0.00035 | $0.350 | $0.00017 |
| Agent turn with tools and history 12,000 in / 800 out | $0.0016 | $1.60 | $0.00080 |
| Summarize a 40-page document 30,000 in / 1,000 out | $0.0035 | $3.50 | $0.0018 |
Prompt caching example
An agent sends the same 10,000-token system prompt and tool list on every call, plus 1,000 new tokens, and gets 500 tokens back. Over 20 calls inside a 5-minute cache window:
- Without caching: $0.027
- With caching (one cache write, then 19 cache reads): $0.010, about 62% less
Compared with other Claude models
- Claude Fable 5.2: $8 / $40, about 80× the price of Haiku 5.5 for the same tokens.
- Claude Opus 5.5: $4 / $20, about 40× the price of Haiku 5.5 for the same tokens.
- Claude Sonnet 5.5: $2 / $10, about 20× the price of Haiku 5.5 for the same tokens.
Side-by-side pages with worked examples:
Input + output price per million tokens, compared as a simple sum. Your real ratio depends on how many input versus output tokens your workload uses; the calculator compares models on your own numbers.
What a typical app costs on Claude Haiku 5.5: chatbot, support bot, coding agent, document q&a (rag), document summarization, classification & extraction.
Questions
How much does Claude Haiku 5.5 cost?
$0.1 per million input tokens and $0.5 per million output tokens. Prompt cache reads cost $0.01 per million tokens; cache writes cost $0.125 (5-minute) or $0.2 (1-hour) per million tokens.
What is the Claude Haiku 5.5 model id?
Use "claude-haiku-5-5" as the model parameter in the Messages API.
Is there a cheaper way to run Claude Haiku 5.5?
Yes. Batch API requests cost 50% of the normal price, and prompt caching cuts the cost of repeated context. In the caching example on this page, 20 calls that share a 10,000-token prefix cost about 62% less with caching.
Does Claude Haiku 5.5 cost more for long prompts?
Yes. When a prompt is over 100,000 tokens, the whole request is billed at $0.5 input and $2.5 output per million tokens.