LPLLM Price CalcIndependent guide

API PRICING GUIDE · VERIFIED OCTOBER 11, 2026

Claude Haiku 5.5
Pricing

The complete cost guide for both prompt-length tiers, cache reads and writes, Amazon Bedrock, Batch API and regional inference—with worked examples you can audit.

THE SHORT ANSWER

$0.10 input and $0.50 output per million tokens—until the prompt exceeds 100K.

For prompts over 100,000 tokens, Haiku 5.5 rises to $0.50 per million input tokens and $2.50 per million output tokens. The threshold is evaluated per request, not from your monthly token total.

01 / OFFICIAL RATE CARD

Two tiers, including cache pricing.

USD per one million tokens on the Claude Platform.

Token categoryPrompt ≤100KPrompt >100K
Input$0.10$0.50
Output$0.50$2.50
Cache read / hit$0.01$0.05
Cache write · 5 minutes$0.125$0.625
Cache write · 1 hour$0.20$1.00

The short-prompt tier is one fifth of the long-prompt tier for each token category. Cache hits are one tenth of the tier’s base input rate.

Open the interactive calculator
02 / THE 100K RULE

The threshold applies to each request.

It is not a monthly volume threshold.

At or below 100K

  • Input: $0.10 / MTok
  • Output: $0.50 / MTok
  • Cache read: $0.01 / MTok
  • Best unit economics for short, high-volume work

Over 100K

  • Input: $0.50 / MTok
  • Output: $2.50 / MTok
  • Cache read: $0.05 / MTok
  • Still lower list price than Haiku 4.5 at equal token counts
Boundary case:

Anthropic describes the lower tier as prompts “up to 100,000 tokens” and the higher tier as prompts “over 100,000 tokens.” Exactly 100,000 prompt tokens therefore remain in the lower tier.

03 / WORKED EXAMPLES

From tokens to dollars.

Standard global pricing, before any cache or Batch adjustments.

$0.0015

10K input + 1K output in the short tier: 10,000 × $0.10/MTok + 1,000 × $0.50/MTok.

$0.0200

100K input + 20K output in the short tier. At 1,000 requests, that is $20.

$0.2250

200K input + 50K output in the long tier. At 1,000 requests, that is $225.

request cost = (input ÷ 1M × input rate) + (output ÷ 1M × output rate) + cache costs

Multiply the request result by request volume. Add any paid server-side tool usage separately.

04 / DISCOUNTS & MODIFIERS

Three settings can change the bill.

Pricing modifiers may stack, so model the full request configuration.

−50%

Batch API discount on input and output tokens for asynchronous processing.

0.1×

Haiku cache-hit multiplier versus the applicable base input rate.

1.1×

US-only inference multiplier for Claude 4.6 and later models; global routing uses standard pricing.

A five-minute cache write costs 1.25× the base input rate and a one-hour write costs 2×. Caching pays off when reused prompt content avoids repeated full-price input processing.

05 / AMAZON BEDROCK

Bedrock Global uses the base rate; Geo routing is 1.1×.

Amazon Bedrock bills Haiku 5.5 through AWS Marketplace. These figures are USD per one million tokens and were checked against AWS pricing data on October 11, 2026.

Token categoryGlobal ≤100KUS Geo ≤100KGlobal >100KUS Geo >100K
Input$0.10$0.11$0.50$0.55
Output$0.50$0.55$2.50$2.75
Cache read$0.01$0.011$0.05$0.055
Cache write · 5 min$0.125$0.1375$0.625$0.6875
Cache write · 1 hour$0.20$0.22$1.00$1.10

Bedrock identifiers

  • Base model: anthropic.claude-haiku-5-5
  • Global profile: global.anthropic.claude-haiku-5-5
  • US Geo profile: us.anthropic.claude-haiku-5-5
  • EU, AU and JP Geo profiles are also documented

Current Bedrock constraints

  • Standard service tier is supported
  • Batch, Priority, Flex and Reserved are currently marked unsupported
  • Messages, Converse and Invoke APIs are supported
  • Charges appear under the model provider in AWS billing
Do not mix the two AWS products:

Amazon Bedrock uses Bedrock model or inference-profile IDs and AWS-managed features. Claude Platform on AWS provides Anthropic’s native API and console experience with AWS billing and authentication; its model ID remains claude-haiku-5-5.

06 / COST CHECKLIST

What your estimate should include.

Token costs

  • Normal input and output tokens
  • Cache creation and cache-read tokens
  • Tool definitions and tool-result content
  • Retries and multi-turn context growth

Non-token costs

  • Paid server-side tools such as web search
  • Global versus Geo routing scope
  • Provider-specific feature availability
  • Your own infrastructure and review costs
07 / FAQ

Claude Haiku 5.5 pricing questions

How much does Claude Haiku 5.5 cost?

Prompts up to 100K cost $0.10 per million input tokens and $0.50 per million output tokens. Prompts over 100K cost $0.50 input and $2.50 output at the Global base rate.

Does exactly 100K use the lower tier?

Yes. Anthropic’s rate card says “up to 100,000 tokens” for the lower tier and “over 100,000 tokens” for the higher tier.

How much does prompt caching cost?

In the Global short tier, a five-minute write is $0.125/MTok, a one-hour write is $0.20/MTok and a cache hit is $0.01/MTok. In the long tier they are $0.625, $1.00 and $0.05 respectively.

Does Batch API cut the price?

On the Claude Platform, yes: Anthropic documents a 50% input and output discount. The current Amazon Bedrock model card marks Batch unsupported for Haiku 5.5, so do not apply the discount to Bedrock workloads.

How much is Haiku 5.5 on Amazon Bedrock?

Global cross-Region inference uses the base rates. US Geo cross-Region inference is 1.1×: for prompts up to 100K, that is $0.11 input and $0.55 output per million tokens; above 100K, $0.55 input and $2.75 output.

Are Amazon Bedrock and Claude Platform on AWS the same?

No. Bedrock is AWS-managed model access with Bedrock IDs and features. Claude Platform on AWS is Anthropic’s native API and console experience with AWS billing and authentication.

What is the Haiku 5.5 model ID?

Use claude-haiku-5-5 on the Claude Platform and anthropic.claude-haiku-5-5 on Bedrock. Cross-Region Bedrock profiles add a scope prefix such as global. or us..

Method and sources. Rates and rules were verified on October 11, 2026 against the official Claude Platform model page, Amazon Bedrock model card and AWS Bedrock pricing page. This independent guide is not affiliated with Anthropic or AWS. Claude model page · AWS model card · AWS pricing.