Claude Haiku 5.5

Claude Haiku 5.5 is the lowest-priced model in Anthropic's current lineup, aimed at high-volume, latency-sensitive tasks such as classification, extraction, routing and sub-agent work. Released October 7, 2026, it has the same 1M-token context window as the larger Claude 5.5 models, with prices that rise for long prompts.

By AnthropicReleased October 7, 2026Data checked October 10, 2026

CurrentClosedEfficient

Specifications

Context window: 1Mabout 750,000 words, or 1,500 pages
Max output: 125Ktokens per response
Input price: $0.10per 1M tokens
Output price: $0.50per 1M tokens
Cached input: $0.01per 1M tokens
Weights: ClosedProprietary
Parameters: Undisclosed
Input types: Text, Images, PDF
Output types: Text
Reasoning mode: Yes
Tool calling: Yes
Released: Oct 7, 2026Current

Rates for prompts up to 100K tokens. A prompt over 100K tokens is billed at $0.50 input, $2.50 output and $0.05 cache read for the whole request. Batch API 50% off. US-only inference adds 1.1x.

What it costs in practice

Workload	Monthly cost at list price
Support chatbot30,000 conversations a month, 2,000 input and 400 output tokens each	$12
Document summaries2,000 documents a month, 12,000 input and 800 output tokens each	$3.20
Coding agent1,000 tasks a month, 60,000 input and 6,000 output tokens each	$9.00

Standard rates, no caching or batch discounts. Run your own numbers.

Strengths

$0.10 input and $0.50 output per million tokens for prompts up to 100K tokens
1M-token context window and 128K-token output limit
Adaptive thinking with adjustable effort

Trade-offs to weigh

Prompts over 100K tokens cost five times the base rates
Its newer tokenizer counts about 30% more tokens than Claude Haiku 4.5 for the same text

Where it fits

Anthropic positions Claude Haiku 5.5 for:

high volumelow latencydata extractioncustomer supportagents

Where you can use it

API
Claude apps
Amazon Bedrock
Google Vertex AI
Microsoft Azure AI Foundry
Claude Platform on AWS

Alternatives to consider

Model	Tier	Context	Input / output per 1M
GPT-6 LunaOpenAI	Efficient	1.05M	$0.10 / $0.50	Compare
Ministral 3 14BMistral AI	Efficient	256K	$0.20 / $0.20	Compare
GLM-5.3-FlashZ.ai (Zhipu AI)	Efficient	1M	$0.15 / $0.50	Compare
Gemma 4 31BGoogle	Efficient	256K	$0.20 / $0.40	Compare

Frequently asked questions

How much does Claude Haiku 5.5 cost?

Claude Haiku 5.5 lists at $0.10 per million input tokens and $0.50 per million output tokens, with cached input at $0.01 (checked October 10, 2026). Rates for prompts up to 100K tokens. A prompt over 100K tokens is billed at $0.50 input, $2.50 output and $0.05 cache read for the whole request. Batch API 50% off. US-only inference adds 1.1x. Confirm current rates on the provider's pricing page before you commit.

What is the context window of Claude Haiku 5.5?

Claude Haiku 5.5 accepts up to 1,000,000 tokens of context (about 750,000 words, or 1,500 pages), and it can write up to 125K tokens in a single response. Long prompts cost more and can be slower, so most apps send only what the task needs.

Is Claude Haiku 5.5 open source?

No. Claude Haiku 5.5 is a proprietary model from Anthropic; its weights aren't published. You can use it through the Anthropic API and through Claude apps, Amazon Bedrock, Google Vertex AI, Microsoft Azure AI Foundry, Claude Platform on AWS.

What is Claude Haiku 5.5 best for?

Anthropic positions Claude Haiku 5.5 for high volume, low latency, data extraction, customer support. It accepts text, images, pdf as input, has a reasoning (thinking) mode and supports tool calling. Test it on a sample of your own tasks before you choose it for production.

Sources

Facts checked against these pages on October 10, 2026. Spot an error? Tell us.

Still choosing a model?

Send us your use case and constraints. We'll come back with a shortlist and an evaluation plan you can run on your own data.

Free and vendor-neutral: no model provider pays for placement.
Your details go only to partners you agree to.