Skip to the page
Tecyfy

Claude Haiku 5.5 API pricing

Claude Haiku 5.5 is one of Anthropic's newest models. It costs $0.10 per million tokens it reads and $0.50 per million it writes, $0.20 on a mix of 3 read for each 1 written. Below are every price Anthropic lists for it, what 8 everyday jobs cost a month on it, and the models that do as well for less.

Input
$0.10 per million tokens read
Output
$0.50 per million tokens written
On everyday work
$0.20 per million, 3 read for each 1 written, the cheapest of the 16 newest models
Context window
1M tokens at once
Capability score
159 on the Epoch Capabilities Index, GPT-5 is 150

Every Claude Haiku 5.5 price, per million tokens

In US dollars, as Anthropic prints them on its price page.

InputTokens the model reads$0.10
Cached inputRead again from the cache$0.01
Cache writePutting text in the cache$0.125
OutputTokens it writes, thinking included$0.50
Blend 3:13 tokens read for each 1 written$0.20
Batch inputAnswers collected later$0.05
Batch output$0.25
Long prompt inputA prompt over 100K tokens$0.50
Long prompt output$2.50
Context windowTokens it holds at once1M tokens
Longest answerTokens it writes in 1 reply128K tokens

What 8 everyday jobs cost a month on Claude Haiku 5.5

Each job at its usual number of runs a day, for 30 days, at the standard price. Open any job in the cost calculator to change its size, or to set it beside every other model.

JobA runA month
A chat question300 in, 500 out, 100 a day0.028 cents84 cents
A hard question, with thinking300 in, 1,400 out, 100 a day0.073 cents$2.19
A long report, summarised60,000 in, 2,000 out, 20 a day0.7 cents$4.20
A 40-turn agent task2,800,000 in, 40,000 out, 10 a day7.3 cents$21.96
A support bot's reply4,000 in, 300 out, 2,000 a day0.037 cents$22.20
Sort a message into a category250 in, 5 out, 50,000 a day0.0028 cents$41.25
Read an invoice into fields1,500 in, 250 out, 1,000 a day0.027 cents$8.25
Review a pull request25,000 in, 4,500 out, 50 a day0.48 cents$7.13

No newest model scores as well for less

Of the newest models we list, none that scores about as well on the Epoch Capabilities Index costs less on a mix of 3 tokens read for each 1 written.

Put this price on your own site

Writing about Claude Haiku 5.5? Copy the code into your post, docs or course page and show its price as a small card. The card reads the same prices as this page, so when Claude Haiku 5.5's price changes here it changes on your page too, and you never publish an old figure. It is free and needs no account.

The short script at the end lets the frame take the card's height. Where a page cannot take scripts, choose a fixed height.

<iframe src="https://tecyfy.com/embed/model/claude-haiku-5-5" title="Claude Haiku 5.5 API price" width="100%" height="290" style="border:0;display:block" loading="lazy" allow="clipboard-write"></iframe>
<p><a href="https://tecyfy.com/prices/claude-haiku-5-5">Claude Haiku 5.5 API price</a> by Tecyfy</p>
<script>addEventListener("message",function(e){if(e.origin!=="https://tecyfy.com"||!e.data||e.data.type!=="tecyfy:height")return;var h=Number(e.data.height);if(!(h>0))return;document.querySelectorAll("iframe").forEach(function(f){if(f.contentWindow===e.source)f.style.height=Math.min(h,20000)+"px"})})</script>

How to read a model's prices

Every maker prints 2 main prices: one for the tokens a model reads (input) and one for the tokens it writes (output), each per million tokens. Writing costs more on almost every model, so a job that reads a long document and writes a line pays mostly the input price, and a chat that writes paragraphs pays mostly the output price. The blend, 3 tokens read for each 1 written, is one figure for ranking models on everyday work.

The other prices lower or raise the bill. Text read again from a cache costs a fraction of the input price, so a long system prompt or document sent with every request gets cheaper after the first. Work that can wait a day costs about half on a batch where the maker offers one. Some models charge more for every token once a prompt passes a set length.

Thinking is billed as output, and the same text is not the same number of tokens on every model, so the price per token is only the start. Each job below is priced the way the cost calculator prices it, at its usual runs a day for 30 days; open one to change its size, or compare the model with another side by side.

Questions

How much does Claude Haiku 5.5 cost?
Claude Haiku 5.5 costs $0.10 per million input tokens, the text it reads, and $0.50 per million output tokens, the text it writes, thinking included. On a mix of 3 tokens read for each 1 written, that is $0.20 per million.
How much does cached input cost on Claude Haiku 5.5?
Text Claude Haiku 5.5 reads again from the cache costs $0.01 per million tokens, against $0.10 the first time. Putting text in the cache costs $0.125 per million, so a long prompt sent again and again costs far less after the first time.
Does Claude Haiku 5.5 have a batch price?
Yes. With a batch, where you send many requests and collect the answers later instead of at once, Claude Haiku 5.5 costs $0.05 per million tokens read and $0.25 per million written.
Does a long prompt cost more on Claude Haiku 5.5?
Yes. Once a prompt passes 100K tokens, the whole request costs $0.50 per million tokens read and $2.50 per million written, against $0.10 and $0.50 below that.
What is the context window of Claude Haiku 5.5?
Claude Haiku 5.5 holds 1M tokens at once, about 1,500 pages of English text, and writes up to 128K tokens in one answer. The window holds your instructions, the files you attach, the conversation so far and the answer.
How good is Claude Haiku 5.5?
Claude Haiku 5.5 scores 159 on the Epoch Capabilities Index, an independent score from Epoch AI that combines over 50 benchmarks, with a range of doubt from 157 to 162 (GPT-5 is 150). One score is an average; test it on 10 tasks of your own.
Is there a cheaper model as good as Claude Haiku 5.5?
Not among the newest models we list: none that scores about as well on the Epoch Capabilities Index costs less on a mix of 3 tokens read for each 1 written.
Where does Claude Haiku 5.5 rank on price?
Claude Haiku 5.5 is the cheapest of the 16 newest models we list, by the price of 3 tokens read for each 1 written.
What does a support bot cost a month on Claude Haiku 5.5?
At 2,000 replies a day, each reading 4,000 tokens (50 percent of them from cache) and writing 300, a support bot costs 0.037 cents a reply on Claude Haiku 5.5, $22.20 a month.
What does an AI agent task cost on Claude Haiku 5.5?
One 40-turn task that reads 2,800,000 tokens in all, 90 percent of them from cache, and writes 40,000, costs 7.3 cents on Claude Haiku 5.5. At 10 tasks a day that is $21.96 a month.