Claude Haiku 5.5

New
AnthropicAll Anthropic models

Input

$0.10

USD / 1M tokens

Output

$0.50

USD / 1M tokens

Context

1M

tokens

Released

2026-10-07

Positioning: Fast. Price level 1 of 4 among text models. Vendor-stated speed: Fastest.

Claude's fastest tier — tiered pricing by prompt length (100K cut-off). Claude Haiku 5.5 is an Anthropic text model on ATP Token with a 1M-token context window, billed per 1M input and output tokens in input-length tiers, with a lower cached-input rate.

ThinkingToolsVision

Pricing

Pay for what you use: credits are deducted only when a request succeeds.
Prices in USD · $1 = 100 credits
Input
$0.10
Cache read
$0.01
Output
$0.50
USD / 1M tokens
Cache write · 5m TTL$0.125 / 1M
Cache write · 1h TTL$0.20 / 1M
Price by input length · USD / 1M tokens
Input lengthInputCache readOutput
≤100K$0.10$0.01$0.50
>100K$0.50$0.05$2.50

Each request's total input (cached tokens included) picks the band. That band's price covers the whole request, output too.

Anthropic · Family · USD / 1M tokens

Text models from the same vendor on ATP. Bars fill up to the family's highest price.
All Anthropic models
ModelInputOutput
Claude Fable 5claude-fable-5$10.00$50.00
Claude Fable 5.1claude-fable-5-1$10.00$50.00
Claude Opus 4.6claude-opus-4-6$5.00$25.00
Claude Opus 4.7claude-opus-4-7$5.00$25.00
Claude Opus 4.8claude-opus-4-8$5.00$25.00
Claude Opus 5claude-opus-5$5.00$25.00
Claude Opus 5.5claude-opus-5-5$4.00$20.00
Claude Sonnet 4.6claude-sonnet-4-6$3.00$15.00
Claude Sonnet 5claude-sonnet-5$2.00$10.00
Claude Sonnet 5.5claude-sonnet-5-5$2.00$10.00
Claude Haiku 4.5claude-haiku-4-5$1.00$5.00
Claude Haiku 5.5 This pageclaude-haiku-5-5$0.10$0.50

Cost per 1,000 typical requests

A quick estimate with fixed token counts per request. No caching, no retries. Try the estimator with your own numbers. All three examples fall in the first input band (≤100K).
WorkloadUSD / 1,000
Short chat turn800 / 400$0.28
RAG answer4,000 / 500$0.65
Agent step with tools20,000 / 1,500$2.75

Same controls on every model: project keys, per-project model access, credit budgets, and a log of every request.Set up your organization

Cost estimator

Plug in your usage to see roughly what a month costs.
Input context per request
0200
0100
ESTIMATE
$2.00
USD / month
200 credits / month
  • Input$1.00
  • Output$1.00

$2.00 USD / month · 200 credits / month

An estimate at our USD prices (USD 1 = 100 credits). What each request actually cost shows up in your console's request log. Cached input is billed at the lower cache-read price, so you may spend less.

Quickstart

Keep your SDK. Point it at ATP and use a project key. Read the docs
quickstart.py · OpenAI SDK
from openai import OpenAI

client = OpenAI(
  base_url="https://api.atptoken.ai/v1",
  api_key="atp-•••"
)

r = client.chat.completions.create(
  model="claude-haiku-5-5",
  messages=[{"role":"user","content":"hi"}],
)

Compare with similar models

Same type and positioning, from other vendors, closest in price first.
Compare side by side

FAQ

4
Can Claude Haiku 5.5 use tools, read images, or think before answering?
Claude Haiku 5.5 supports tool calling, vision input and extended thinking, but not audio.
How much context does Claude Haiku 5.5 take?
Anthropic lists a 1,000,000-token context window for Claude Haiku 5.5. The model list your key can see shows the limit you actually get.
How does Claude Haiku 5.5's pricing by input length work?
You pay per 1M input tokens and per 1M output tokens. The price steps with each request's total input length (≤100K / >100K). The band covers the whole request, output too. Cached input costs 10% of the normal input price. Cache writes are priced separately. You only pay when a request succeeds. $1 = 100 credits. See pricing
How do I call Claude Haiku 5.5 on ATP?
Create a project API key and point any OpenAI-compatible SDK at https://api.atptoken.ai/v1. Set model to "claude-haiku-5-5" (the API id, not the display name). Make sure the model is turned on for your project.
Get started

Start with $5. Credits never expire.

Create a project key, turn this model on, and pay only for what you use.