How much does Claude 3.5 Haiku cost?

Claude 3.5 Haiku costs $0.8 per million input tokens and $4 per million output tokens. The blended average is $2.40 per million tokens.

What is the context window of Claude 3.5 Haiku?

Claude 3.5 Haiku supports a context window of 200K tokens (200,000 tokens) and can generate up to 8K output tokens per request.

What is Claude 3.5 Haiku best for?

Claude 3.5 Haiku is best for: Speed & cost. It supports chat, vision, code, function_calling capabilities.

Claude 3.5 Haiku — Pricing, Benchmarks & Specs

Claude 3.5 Haiku

Anthropicfast-20%

Anthropic's fastest model. Ultra-low latency for real-time applications and high-volume tasks.

Context Window

200K

tokens

Max Output

tokens

Input Price

$0.8

per 1M tokens

Output Price

per 1M tokens

Speed

172

tokens/sec

Released

Oct 2024

2024-10-22

Blended Cost

$2.40

per 1M tokens

Value Score

31.3

quality per $

Capabilities

ChatVisionCode GenerationFunction Calling

Benchmarks

Quality Index

MMLU Pro

84.2

HumanEval (Coding)

88.1

MATH

69.3

Arena ELO

1230

Pricing History

Oct 22, 2024$1 / $5(launch)

Feb 1, 2025$0.8 / $4current

Try in Playground Use via Swfte Connect Anthropic Docs

Compare With

GPT-4o Mini

Quality: 72·$0.38/1M

Claude Opus 4

Quality: 95·$45.00/1M

About Claude 3.5 Haiku

Claude 3.5 Haiku is a fast AI model by Anthropic, released on October 22, 2024. It supports a context window of 200K tokens and can generate up to 8K output tokens.

At $0.8 per million input tokens and $4 per million output tokens, its blended cost of $2.40/1M tokens puts it in the mid-range pricing tier. Its value score of 31.3 reflects the balance of quality and cost.

Using Claude 3.5 Haiku with Swfte

Access Claude 3.5 Haiku through Swfte Connect, our unified LLM gateway. Connect gives you a single API for 50+ models, with automatic routing, cost optimization, and fallback handling. You can also try Claude 3.5 Haiku in our AI Playground before integrating.