Anthropic
Claude Haiku 5.5
Anthropic's fastest Claude model, for high-volume, latency-sensitive tasks such as classification, extraction and routing. Price for prompts up to 100,000 tokens.
USD per 1M output tokens
$0.50
- input
- $0.10
- output
- $0.50
#3 cheapest of 33 in Large language models
Visit Anthropic ↗Official pricing ↗Capabilities, explained
What this API can do, and what each capability means for your project.
Input price
$0.1
Cost of the text, images and files you send to the model.
Context window
—
How much text the model can read at once. 200K tokens ≈ a 500-page book.
Max output
—
Longest single response the model can write.
Input types
—
What kinds of input the model understands besides text.
Tool use / function calling
—
The model can request calls to your functions/APIs with structured arguments, the basis of agents.
Guaranteed JSON output
—
The API can force the response to match a JSON schema you provide.
Extended reasoning
—
The model can 'think' step by step before answering, improving hard math/coding at extra cost and latency.
Open weights
—
The model weights are downloadable, so you can self-host it or switch hosting providers without changing models.
Typical latency
—
How long until the first useful output arrives. Lower is better for interactive apps; batch jobs rarely care.
Price history
Only one price recorded so far. The chart appears once the price changes.