TechCompare LogoTechCompare

Claude Haiku 4.5 API Pricing & Cost Calculator

Claude Haiku 4.5 is perfect for low-latency tasks. Caching drops input costs to $0.10 per million, making high-volume agent tasks extremely cost-effective.

Claude Haiku 4.5 is Anthropic's fastest, most lightweight model, optimized for low latency and high frequency.

By TechCompare · Updated

Input tokens
20,000
per request
Output tokens
2,000
per request
Volume
500 / monthly
Standard API

Calculator

Cost Comparison

Based on 20,000 input tokens (50% cached), 2,000 output tokens, and 500 requests.

Same 20,000 in / 2,000 out (50% cached) scenario, pre-loaded. Adjust tokens, caching, or swap models.
Edit in the full tool

How this is calculated

Claude Haiku 4.5 is priced at $1.00 per million input tokens and $5.00 per million output tokens, supporting a 90% caching discount ($0.10 per million) and a 50% batch discount ($0.50 per million inputs, $2.50 per million outputs).

Verdict

The base rates are $1/M input and $5/M output, already the lightest of Anthropic's lineup, and the 90% cache discount strips input to $0.10/M while the 50% batch discount halves both rows to $0.50/M input and $2.50/M output. A representative 100K + 5K call lands at roughly $0.125 before discounts and close to $0.035 with a 90% cache hit. That makes Haiku 4.5 the right tier for high-frequency classification, structured-output formatting, and tool-routing loops where output cost stays modest and the cache reuse rate is high.

More API Standalones scenarios

GPT-5.5 Pricing
Single-model gpt-5.5 cost estimate
View details ➜
GPT-5.4 Pricing
Single-model gpt-5.4 cost estimate
View details ➜
Claude Opus 4.8 Pricing
Single-model claude-opus-4.8 cost estimate
View details ➜

Related guides

Token cost calculator
How per-token counts turn into API costs.
View guide ➜
Prompt optimization
Cutting tokens is the cheapest way to cut cost.
View guide ➜

Frequently asked questions

Does Claude Haiku 4.5 support prompt caching?
Yes, Anthropic offers a 90% discount on cached input tokens, reducing the input price to $0.10 per million for matches.
How much does Claude Haiku 4.5 cost per million output tokens?
Claude Haiku 4.5 charges $5.00 per million output tokens at standard pricing. With the 50% batch discount, that drops to $2.50 per million. The 90% prompt caching discount brings cached input to $0.10 per million, which makes high-frequency agent tasks and routing workloads remarkably cheap.
Is Claude Haiku 4.5 worth it over GPT-5.4 Mini?
Probably not on cost alone. GPT-5.4 Mini charges $0.75/M input and $4.50/M output, beating Haiku's $1.00/$5.00 across the board. Pick Haiku if your stack is already Anthropic and you value its structured-data formatting. Otherwise, Mini is the better cost choice at this tier.

Related tools

LLM VRAM Calculator

Calculate the VRAM needed to run or fine-tune any LLM at any quantization.

Use tool ➜

Power Cost Estimator

Estimate annual electricity costs for your PC, Server, or TV.

Use tool ➜

Data Transfer Calculator

Estimate transfer times for files over USB, WiFi, Ethernet, and more.

Use tool ➜

JSON Formatter

Validate, format, and minify JSON data with syntax highlighting.

Use tool ➜