Home › LLM Pricing › Claude Haiku 5.5

Anthropic pricing

Claude Haiku 5.5 Pricing

Claude Haiku 5.5 is Anthropic's fast, low-cost model for high-volume work such as classification, routing and extraction. Its price depends on prompt length.

Quick answer

Claude Haiku 5.5 costs $0.10 per 1M input tokens and $0.50 per 1M output tokens. 1,000 typical requests cost about $0.40.

Claude Haiku 5.5 API pricing

Price typeNow (USD per 1M tokens)
Input$0.10
Cache reads$0.01
Cache writes, 5 minutes$0.125
Cache writes, 1 hour$0.20
Output$0.50
Batch input$0.05
Batch output$0.25

Prices for prompts up to 100,000 tokens. Above that: $0.50 input, $0.05 cache reads, $2.50 output, and $0.25 / $1.25 on the Batch API.

What Claude Haiku 5.5 costs in practice

Take a typical request with 2,000 input tokens and 400 output tokens. On Claude Haiku 5.5:

Cost calculator

Monthly cost, standard–
With your cache share–
On the Batch API–
Per 1,000 requests–
With apicuts: at least 20% less, after our fee–

Uses Claude Haiku 5.5's standard prices checked October 30, 2026. Cache writes, thinking tokens and long-context tiers aren't included.

How to pay less for Claude Haiku 5.5

apicuts switches these on for you, routes each request to the lowest-cost route that passes your quality checks, and guarantees at least 20% lower cost after our fee. See pricing.

Compare Claude Haiku 5.5

See every model side by side in the LLM API pricing comparison, or read Claude Haiku 5.5 vs GPT-6 Luna, or read Gemini 3.8 Flash vs Claude Haiku 5.5.

Frequently asked questions

How much does Claude Haiku 5.5 cost?

Claude Haiku 5.5 costs $0.10 per 1M input tokens and $0.50 per 1M output tokens at standard prices, according to Anthropic's pricing page (checked October 30, 2026).

How much do 1,000 Claude Haiku 5.5 requests cost?

About $0.40, for requests of 2,000 input and 400 output tokens without caching.

Is there a cheaper way to use Claude Haiku 5.5?

Yes: caching repeated prompt prefixes, moving work that can wait to the Batch API at half price, capping output length, and sending simpler requests to a cheaper model.

Sources: Anthropic's pricing page. Checked October 30, 2026.

Want us to find your 20%?

Book a free 15-minute API cost teardown. Bring last month's provider usage and we'll show you your biggest waste and the first fix we'd ship.

Get a Free 15-Minute API Cost Teardown

Related