Claude Haiku 4.5 pricing

Anthropic · API id claude-haiku-4-5-20251001 · verified 2026-10-18

Input$1.00
Cached input (cache hit)$0.10
Cache write$1.25
Output$5.00
Batch discount50%
Context window200,000 tokens
Max output64,000 tokens

USD per 1M tokens unless noted. Official source

Estimate your workload on Claude Haiku 4.5 →

What Claude Haiku 4.5 costs for real workloads

WorkloadClaude Haiku 4.5Ministral 3 8BClaude Haiku 5.5GPT-6 LunaMistral Small 4
10,000 chatbot replies
2,000 input + 400 output tokens each, 50% of the prompt cached
$31.00$2.25$3.10$3.10$4.05
One 30-step coding agent run
12K system + tools prompt, 1K output and 3K tool result per step, caching on
$0.52$0.05$0.12$0.05$0.07
1M documents classified (batch)
600 input + 20 output tokens each, batch API where available
$350$46.50$35.00$35.00$51.00

Compared with the cheapest other small models. Change the numbers in the calculator.

Billing notes

Legacy; alias claude-haiku-4-5. Now 10x the price of Haiku 5.5. Retirement "not sooner than Oct 15, 2026" - check deprecations page.

Where Claude Haiku 4.5 ranks by use case

Position by cost among all models that fit each workload (1 = cheapest).

Counting tokens for a prompt? The token counter estimates Claude Haiku 4.5 tokens (Claude 4.6 and earlier tokenizer, estimated) and input cost.

Head-to-head comparisons

Other Anthropic models

FAQ

How much does Claude Haiku 4.5 cost per 1M tokens?

Claude Haiku 4.5 costs $1.00 per 1M input tokens and $5.00 per 1M output tokens at standard rates (verified 2026-10-18).

Does Claude Haiku 4.5 support prompt caching?

Yes. Cached input is billed at $0.10 per 1M tokens, and writing to the cache costs $1.25 per 1M tokens.

Is there a batch discount for Claude Haiku 4.5?

Yes. The batch API is 50% cheaper than standard requests.

What is the context window of Claude Haiku 4.5?

200,000 tokens, with up to 64,000 output tokens.