Claude 3 Haiku
by
Anthropic
Model ID:
claude-3-haiku-20240307
Overview
Claude 3 Haiku is designed as the fastest and most compact model in the Claude 3 lineup. It prioritizes speed and efficiency without significantly compromising on capability, making it ideal for applications requiring quick responses or high-volume processing.
Specializations
Fastest and most compact model in the Claude 3 family.
Optimized for quick, accurate responses.
Cost-effective for high-volume applications.
Capable of processing both text and image inputs.
Integration Guide (Javascript)
To use this model through Portkey, follow these steps:
1. Install Portkey SDK:
npm install --save portkey-ai
2. Set up client with Portkey:
import Portkey from 'portkey-ai'
const portkey = new Portkey({
apiKey: "PORTKEY_API_KEY",
virtualKey: "VIRTUAL_KEY" // Your Anthropic Virtual Key
})
3. Make a request:
const chatCompletion = await portkey.chat.completions.create({
messages: [{ role: 'user', content: 'Say this is a test' }],
model: 'claude-3-haiku-20240307',
maxTokens: 250 // Required field for Anthropic
});
console.log(chatCompletion.choices[0].message.content);
Live API Statistics and Performace Metrics
LMSys Arena Elo Score:
1179
Arena Score
LMSys Leaderboard Rank:
48
Arena Rank
Evaluates LLMs through a combination of user feedback and automated scoring systems.
HumanEval Leaderboard Score:
Leaderboard Score
75.9
%
A specific benchmark score measuring the model's accuracy in executing code generations.
Uptime:
Uptime Reliability
99.983
%
The percentage of time the model is operational and available for use, reflecting its reliability.
Model Specifications
Release Date:
7/3/2024
Max. Context Tokens:
200K
Max. Output Tokens:
4K
Knowledge Cut-Off Date:
August 2023
MMLU:
75.2
%
License:
Proprietary
Technical Report/Model Card:
LMSys Elo Score
1179
Berkeley Function Calling Ability Score:
NaN
Pricing
$/Million Input Tokens
$
0.25
$/Million Output Tokens
$
1.25
Live updates via Portkey Pricing API. Coming Soon...
© 2024 Portkey, Inc. All rights reserved