Anthropic · all models ›

AClaude 3 HaikuAPI

Claude 3 Haiku is Anthropic's fastest and most compact model for near-instant responsiveness.

200KContext window · tokens
$0.25Input price · per M tokens
$1.25Output price · per M tokens
AnthropicProvider

Prices update automatically — checked daily against provider list prices.

See open-source alternatives → Compare all model prices

Benchmarks & performance

Independent benchmark scores for Claude 3 Haiku, measured by Artificial Analysis. Higher is better.

Intelligence index3.5
GPQA37.4%
Humanity's Last Exam4.1%
Long Context Reasoning25%
LiveCodeBench15.4%
SciCode18.6%
MATH-50039.4%
AIME1%
IFBench36.1%
τ²-Bench21.1%
Terminal-Bench Hard0.8%
💰 Blended price$0.5 / 1M tokens
📈 Value7 intelligence points per $
vs. models measured heretop 97%
Scores higher than 3% of the 273 models measured by Artificial Analysis and tracked here.
Models at this level cost $0.38 per 1M tokens (median of 11) — this one costs $0.5.
Cheaper and better on this index: GLM 5.3 Flash · Gemini 3.7 Flash (batch) · GPT-5.6 Luna and 83 more
Benchmark data by Artificial Analysis

About this model

Claude 3 Haiku is a commercial AI model by Anthropic. The specifications below are tracked automatically: pricing is refreshed daily from public list prices, so the numbers on this page reflect the current cost of using the model through its API.

Frequently asked questions

What is Claude 3 Haiku?

Claude 3 Haiku is an AI language model from Anthropic. It is a proprietary model, available through an API. It scores 3.5 on the Artificial Analysis intelligence index.

Is Claude 3 Haiku free?

Claude 3 Haiku is not free: it costs $0.25 per million input tokens and $1.25 per million output tokens. Open-weight alternatives can be self-hosted at no per-token cost.

What is Claude 3 Haiku good at?

Independent benchmarks from Artificial Analysis give it GPQA 37.4%, Humanity's Last Exam 4.1%, Long Context Reasoning 25%, LiveCodeBench 15.4%, SciCode 18.6%, MATH-500 39.4%, AIME 1%, IFBench 36.1%, τ²-Bench 21.1%, Terminal-Bench Hard 0.8%.

Related models

Claude Opus 4.7 (Fast)AnthropicClaude Opus 4.1AnthropicClaude Opus 4AnthropicClaude Fable 5AnthropicClaude Opus 5 (Fast)AnthropicClaude Opus 4.8 (Fast)Anthropic