Claude Haiku 4.5 API Pricing

Claude Haiku 4.5 by Anthropic costs $1.00 per million input tokens and $5.00 per million output tokens.

Price verified from Anthropic's pricing page.

Rates and limits

Input / 1M
$1.00
Output / 1M
$5.00
Cached input / 1M
$0.10
Cache write / 1M
$1.25
Batch discount
50% off
Context window
200K tokens
Max output
64K tokens
Knowledge cutoff
July 2025
Released
October 2025

What Claude Haiku 4.5 costs per month

Token volume split 3:1 between input and output, with no prompt caching.

Tokens per monthInput / outputStandardBatch API
1M750K / 250K$2.00$1.00
10M7.5M / 2.5M$20.00$10.00
100M75M / 25M$200.00$100.00
Estimate your own workload with Claude Haiku 4.5

Where to run Claude Haiku 4.5

Prices above are Anthropic's direct rates. Cloud platforms can charge differently; the cloud platform view compares them.

Benchmarks reported by Anthropic

MMLU
82.4%
HumanEval
86.5%
GPQA
56.2%
AIME
38.1%
SWE-bench Verified
48%
MMMU
65.2%

Claude Haiku 4.5 pricing FAQ

How much does Claude Haiku 4.5 cost per million tokens?

Claude Haiku 4.5 costs $1.00 per million input tokens and $5.00 per million output tokens, as listed on Anthropic's pricing page on October 5, 2026.

How much does Claude Haiku 4.5 cost for 10 million tokens a month?

About $20.00 a month, assuming 7.5 million input and 2.5 million output tokens with no prompt caching, or $10.00 through the batch API.

What is the context window of Claude Haiku 4.5?

Claude Haiku 4.5 accepts up to 200,000 tokens of context and returns up to 64,000 output tokens per request.

Does Claude Haiku 4.5 support prompt caching?

Yes. Cached input tokens cost $0.10 per million, 90% less than the standard input rate. Writing a prefix to the cache costs $1.25 per million tokens.

Is there a batch discount for Claude Haiku 4.5?

Yes. Requests sent through the batch API cost 50% less: $0.50 per million input tokens and $2.50 per million output tokens.

Where can I use the Claude Haiku 4.5 API?

Claude Haiku 4.5 is available through Anthropic API, AWS Bedrock, Google Cloud Vertex AI, and OpenRouter.

Prices shown as input / output per million tokens. All model prices · Side-by-side comparison