modelgrep
A

Anthropic: Claude 3 Haiku

anthropic/claude-3-haiku

159th smartest of 178ToolsVision
Use via OpenRouter ↗
Intelligence
12.3
159th of 178
Design Elo
Speed
68
116th fastest
Latency
542ms
first token
Input price
$0.250
115th cheapest
Context
200K
4K max out

How it compares

Smarter than11%
of all ranked models
Faster than61%
of all ranked models
Cheaper than61%
of all ranked models

Overview

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

Benchmarks

independent · via OpenRouter
Artificial Analysis11th percentile
Intelligence Index
12.3
Coding Index
6.7
Agentic Index
7.0
GPQA Diamond
37%
Humanity's Last Exam
4%
SciCode
19%
Tau²-Bench (agentic)
21%

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
Amazon Bedrock$0.250$1.25100%

Specifications

Context window200K
Max output4K
Knowledge cutoffAug 2023
Input modalitiestext, image
Output modalitiestext
Prompt caching
Cache read price$0.030/M
ModeratedYes

Claude 3 Haiku FAQ

How much does Claude 3 Haiku cost?

Claude 3 Haiku costs $0.250 per million input tokens and $1.25 per million output tokens via OpenRouter, making it 115th cheapest of 298 paid models.

How smart is Claude 3 Haiku?

Claude 3 Haiku scores 12.3 on the Artificial Analysis Intelligence Index, ranking 159th of 178 benchmarked models, with a GPQA Diamond score of 37%.

How fast is Claude 3 Haiku?

Claude 3 Haiku generates around 68 tokens per second with 542ms time-to-first-token (p50), the 116th fastest tracked model.

What is Claude 3 Haiku's context window?

Claude 3 Haiku supports a 200K-token context window and can output up to 4K tokens. It accepts text, image input.

Compare head-to-head