Claude Haiku 5.5 API Pricing

Claude Haiku 5.5 by Anthropic costs $0.10 per million input tokens and $0.50 per million output tokens.

Price verified from Anthropic's pricing page.

Rates and limits

Input / 1M
$0.10
Output / 1M
$0.50
Cached input / 1M
$0.01
Cache write / 1M
$0.125
Batch discount
50% off
Context window
1M tokens
Max output
128K tokens
Knowledge cutoff
June 2026
Released
October 2026

Rates by prompt length

Claude Haiku 5.5 bills each request by the length of its prompt, counting cache reads and cache writes. A prompt of over 100,000 tokens reprices the whole request at the higher rates below. A dash means no such rate is listed.

Prompt lengthInput / 1MOutput / 1MCached input / 1MCache write / 1MBatch input / 1MBatch output / 1M
100,000 tokens or less$0.10$0.50$0.01$0.125$0.05$0.25
Over 100,000 tokens$0.50$2.50$0.05$0.625$0.25$1.25

Pricing note: Priced by prompt length, per request. Standard (prompt of 100K tokens or less): $0.10 in / $0.01 cached / $0.50 out. Over 100K tokens (counting cache reads and writes), the whole request is billed at $0.50 in / $0.05 cached / $2.50 out. Batch is 50% off both tiers: $0.05 in / $0.25 out standard, $0.25 in / $1.25 out over 100K. Cache writes: 5-minute TTL $0.125/MTok standard and $0.625 over 100K; 1-hour TTL $0.20 standard and $1 over 100K. US-only inference (inference_geo: "us") is billed at 1.1x, including the over-100K prices.

What Claude Haiku 5.5 costs per month

Token volume split 3:1 between input and output, with no prompt caching. These figures assume prompts of 100,000 tokens or less (the standard rates). A prompt over that length bills the whole request at $0.50 per million input tokens and $2.50 per million output tokens, so long-prompt workloads cost more.

Tokens per monthInput / outputStandardBatch API
1M750K / 250K$0.20$0.10
10M7.5M / 2.5M$2.00$1.00
100M75M / 25M$20.00$10.00
Estimate your own workload with Claude Haiku 5.5

Where to run Claude Haiku 5.5

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

Cite this data

Vanta Calc, Claude Haiku 5.5 API Pricing, https://www.vantacalc.com/technology/llm-pricing/claude-haiku-5-5/, last updated 13 October 2026

Last updated

Reuse licensing is awaiting owner confirmation. For licensing enquiries, use our contact form.

Claude Haiku 5.5 pricing FAQ

How much does Claude Haiku 5.5 cost per million tokens?

Claude Haiku 5.5 costs $0.10 per million input tokens and $0.50 per million output tokens for prompts of up to 100,000 tokens. A request with a longer prompt costs $0.50 and $2.50 per million, as listed on Anthropic's pricing page on October 13, 2026.

How much does Claude Haiku 5.5 cost for 10 million tokens a month?

About $2.00 a month, assuming 7.5 million input and 2.5 million output tokens with no prompt caching, or $1.00 through the batch API.

What is the context window of Claude Haiku 5.5?

Claude Haiku 5.5 accepts up to 1,000,000 tokens of context and returns up to 128,000 output tokens per request.

Does Claude Haiku 5.5 support prompt caching?

Yes. Cached input tokens cost $0.01 per million, 90% less than the standard input rate. Writing a prefix to the cache costs $0.125 per million tokens.

Is there a batch discount for Claude Haiku 5.5?

Yes. Requests sent through the batch API cost 50% less: $0.05 per million input tokens and $0.25 per million output tokens.

Does Claude Haiku 5.5 cost more for long prompts?

Yes. A request whose prompt is over 100,000 tokens (cache reads and writes included) is billed at $0.50 per million input tokens and $2.50 per million output tokens for the whole request, instead of $0.10 and $0.50. Each request is priced on its own.

Where can I use the Claude Haiku 5.5 API?

Claude Haiku 5.5 is available through Anthropic API, AWS Bedrock, Google Cloud Vertex AI, Azure AI Foundry, OpenRouter, and Databricks Mosaic AI.

All Claude API prices

Prices shown as input / output per million tokens. Models with a prompt-length tier are shown at their standard rates and marked with the prompt size they apply to; longer prompts cost more, and the “similarly priced” ranking compares standard rates. All model prices · Side-by-side comparison