Claude 3 Haiku

Claude 3 Haiku is Anthropic's fastest and most compact model for near-instant responsiveness. Quick and accurate targeted performance. See the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-haiku) #multimodal

by Anthropic

Overview

Quick stats across all benchmark runs.

Score

43%

282 benchmarks

Avg Latency

3.5s

757 requests

Pricing

$0.25 in / $1.25 out

per 1M tokens

Context

200K

tokens

Alternatives

Models with similar or better quality but different tradeoffs

Same Quality, Cheaper

Models with similar or better performance at a lower cost per token.

Model	Cost
Llama 4 Scout	-64%
Ministral 3 8B 2512	-59%
gpt-oss-20b	-43%
Gemini 2.0 Flash	-42%
Ministral 3 14B 2512	-29%

Same Quality, Faster

Models with similar or better performance but lower latency.

No alternatives found

Same Cost, Better

Models at a similar price point with higher benchmark scores.

Model	Score
Gemini 2.5 Flash Lite	+10%
gpt-oss-20b	+8%
DeepSeek V3.2	+6%
Gemini 2.0 Flash	+5%
DeepSeek V3 0324	+5%

Benchmark Performance

How this model performs across different benchmarks

Benchmark	Score	Rank
Explain Like I'm 5	96%	7 / 47
Spatial Reasoning: Germany	93%	14 / 29
Venture Capital Terms Benchmark	83%	7 / 21
Character Frequency Bench	60%	23 / 29
German Memelord Bench	51%	7 / 29
Money Boy Cultural Literacy Test	49%	36 / 107
Niederstetten Benchmark	48%	18 / 35
Categorization Bench	31%	44 / 54

Price vs Performance

Compare cost efficiency across all models

Current model (baseline)

Other models (relative score)

Y-axis shows score difference from shared benchmarks. X-axis uses log scale.

Score Over Time

Performance trends across all benchmark runs

Benchmark Activity

Number of benchmark runs over time

Quickstart

View on OpenRouter

Get started with this model using OpenRouter

import { OpenRouter } from "@openrouter/sdk";

const openrouter = new OpenRouter({
  apiKey: "<OPENROUTER_API_KEY>"
});

const completion = await openrouter.chat.completions.create({
  model: "anthropic/claude-3-haiku",
  messages: [
    {
      role: "user",
      content: "Hello!"
    }
  ]
});

console.log(completion.choices[0].message.content);

Get your API key at openrouter.ai/keys

Other Models from Anthropic

Compare performance with other models from the same creator

Model	Latency	Cost/1M	Score
Claude Sonnet 4.5	20.4s	$9.00	75%
Claude Opus 4.6	4.2s	$15.00	72%
Claude Opus 4.5	28.8s	$15.00	58%
Claude Sonnet 4.6	5.0s	$9.00	57%
Claude Opus 4.7	3.5s	$15.00	53%
Claude Haiku 4.5	11.1s	$3.00	47%
Claude 3.5 Haiku	7.4s	$2.40	26%
Claude Sonnet 4	28.3s	$9.00	—
Claude Opus 4	60.9s	$45.00	—
Claude Opus 4.1	79.9s	$45.00	—
Claude 3.5 Haiku (2024-10-22)	—	$2.40	—
Claude Opus 4.7 (Fast)	—	$90.00	—
Claude Opus 4.6 (Fast)	—	$90.00	—
Claude 3.5 Sonnet	17.7s	$18.00	—
Claude 3.7 Sonnet	16.3s	$9.00	—