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
API PRICING GUIDE · VERIFIED OCTOBER 8, 2026
Claude Haiku 5.5
Pricing
The complete cost guide for both prompt-length tiers, cache reads and writes, Batch API and US-only inference—with worked examples you can audit.
$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 category | Prompt ≤100K | Prompt >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 calculator02 / THE 100K RULE
The threshold applies to each request.
It is not a monthly volume threshold.
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.
10K input + 1K output in the short tier: 10,000 × $0.10/MTok + 1,000 × $0.50/MTok.
100K input + 20K output in the short tier. At 1,000 requests, that is $20.
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 costsMultiply 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.
Batch API discount on input and output tokens for asynchronous processing.
Haiku cache-hit multiplier versus the applicable base input rate.
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 / 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
- Regional or data-residency multipliers
- Cloud-provider-specific pricing
- Your own infrastructure and review costs
06 / 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.
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 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?
Yes. Anthropic documents a 50% input and output token discount for asynchronous Batch API workloads.
Are AWS Bedrock and Google Cloud prices identical?
Do not assume so. Partner-operated platforms can have their own regional pricing. Check the provider’s current rate card before budgeting.
What is the Haiku 5.5 model ID?
claude-haiku-5-5 on the Claude Platform.
Method and sources. Rates and rules were verified on October 8, 2026 against Anthropic’s official Haiku 5.5 announcement and Claude Platform pricing documentation. This independent guide is not affiliated with Anthropic. Model announcement · Pricing documentation.