anthropic logo

Anthropic

Claude Haiku 4.5

Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models.

At a glance

Input / 1M
$1
Output / 1M
$5
Context
200K
Max output
64K
Intelligence
16.9
Released
Oct 2025
Text inputImage inputFile inputReasoningTool calling

Pricing

Claude Haiku 4.5 API pricing

Per-token rates, plus what common tasks actually cost.

Input tokensPer 1M tokens$1
Output tokensPer 1M tokens$5
Cached input (read)Per 1M tokens$0.10
Cache writePer 1M tokens$1.25
Web searchPer request$0.01

Chat message

2K in, 500 out

$4.50

per 1,000 requests

Coding task

30K in, 4K out

$50

per 1,000 requests

Long document summary

150K in, 2K out

$160

per 1,000 requests

Benchmarks

Claude Haiku 4.5 benchmark scores

Independent scores from Artificial Analysis. Higher is better.

Intelligence index

16.9

Coding index

43.9

Agentic index

8

Specs

Context window and capabilities

What it can read, what it can write, and which API features it supports.

Context window
200K tokens
Max output
64K tokens
Input types
File, Image, Text
Output types
Text
Reasoning effort
Not available
Release date
October 15, 2025
  • Tool calling
  • Structured outputs
  • JSON mode
  • Reasoning
  • Temperature
  • Stop sequences
  • Deterministic seed
  • Verbosity control

FAQ

Frequently asked questions

How much does Claude Haiku 4.5 cost?

Claude Haiku 4.5 costs $1 per 1M input tokens and $5 per 1M output tokens through the API. A typical chat message costs about $4.50 per 1,000 messages.

What is the context window of Claude Haiku 4.5?

Claude Haiku 4.5 accepts up to 200K tokens of input and can write up to 64K tokens in a single response.

What is the best alternative to Claude Haiku 4.5?

Claude Sonnet 4.5 from Anthropic is a strong alternative. It offers: higher intelligence score, larger 1m context.

Can I use Claude Haiku 4.5 alongside other models?

Yes. Shortcut Chat sends one prompt to Claude Haiku 4.5 and any other models you pick at the same time, so you can compare answers side by side.

anthropic logo

Try Claude Haiku 4.5 next to every other model.

Use Claude Haiku 4.5 alongside all the other models. Use one at a time, or multiple together. Get the best answer from every AI.