Claude 3 Haiku | Anthropic Fastest LLM API

Name: Claude 3 Haiku API
Brand: anthropic
Price: 0.25 USD
Availability: InStock

anthropic/claude-3-haiku

发布时间: 2024-03-13

200,000 context · $0.25/M input tokens · $1.25/M output tokens

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 #multimodal

定价

按量付费

无需预付费用，仅按实际使用量付费

输入$0.25 / M Tokens

输出$1.25 / M Tokens

Cache Read$0.03 / M Tokens

Cache Write$0.30 / M Tokens

试用模型

anthropic/claude-3-haiku

在线

你好！我是乐于助人的 AI 助手。需要我帮你做什么？

准备在本地编码 Agent 中使用这个模型吗？Agent 配置

API 使用

使用以下代码示例接入我们的 API：

import OpenAI from 'openai';

if (!process.env.WAVESPEED_API_KEY) throw new Error('Set WAVESPEED_API_KEY');
const client = new OpenAI({
  apiKey: process.env.WAVESPEED_API_KEY,
  baseURL: 'https://llm.wavespeed.ai/v1',
  timeout: 120_000,
  maxRetries: 2,
});

try {
  const response = await client.chat.completions.create({
    model: 'anthropic/claude-3-haiku',
    messages: [{ role: 'user', content: 'Hello!' }],
  });
  console.log(response.choices[0]?.message?.content ?? '');
} catch (error) {
  console.error('LLM request failed:', error);
  process.exitCode = 1;
}

import OpenAI from 'openai';

if (!process.env.WAVESPEED_API_KEY) throw new Error('Set WAVESPEED_API_KEY');
const client = new OpenAI({
  apiKey: process.env.WAVESPEED_API_KEY,
  baseURL: 'https://llm.wavespeed.ai/v1',
  timeout: 120_000,
  maxRetries: 2,
});

try {
  const response = await client.chat.completions.create({
    model: 'anthropic/claude-3-haiku',
    messages: [{ role: 'user', content: 'Hello!' }],
  });
  console.log(response.choices[0]?.message?.content ?? '');
} catch (error) {
  console.error('LLM request failed:', error);
  process.exitCode = 1;
}

模型介绍

Anthropic claude-3-haiku

anthropic claude-3-haiku

Why It Looks Great

Large Language Model architecture for efficient processing
200000 context window for long document handling
Competitive pricing at $0.3/$1.4 per million tokens

Key Features

Context Window: 200000 tokens
Max Output: 4096 tokens
Vision: Supported
Function Calling: Supported

Specifications

Specification	Value
Provider	Anthropic
Model Type	Large Language Model (LLM)
Architecture	N/A
Context Window	200000 tokens
Max Output	4096 tokens
Input	Text
Output	Text
Vision	Supported
Function Calling	Supported

Pricing

Token Type	Cost per Million Tokens
Input	$0.3
Output	$1.4

How to Use

Write your prompt — describe the task, provide context, and specify desired output format.
Submit — the model processes your request and returns the response.

API Integration

Base URL: https://llm.wavespeed.ai/v1 API Endpoint: chat/completions Model ID: anthropic/claude-3-haiku

API Usage

Python SDK

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://llm.wavespeed.ai/v1"
)

response = client.chat.completions.create(
    model="anthropic/claude-3-haiku",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)

print(response.choices[0].message.content)

cURL

curl https://llm.wavespeed.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "anthropic/claude-3-haiku",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Notes

Model: anthropic/claude-3-haiku
Provider: Anthropic

信息

提供商anthropic

类型llm

支持功能

输入

文本图像

输出

文本

上下文200,000

最大输出4,096

视觉✓ 支持

函数调用✓ 支持

API 访问指南

Base URLhttps://llm.wavespeed.ai/v1

API 端点chat/completions

Model IDanthropic/claude-3-haiku

关于 Claude 3 Haiku 的常见问题

Claude 3 Haiku API 多少钱?+

WaveSpeedAI 定价:输入每百万 token $0.25,输出每百万 token $1.25。Prompt 缓存和批处理单独计费,可显著降低长上下文、高重复任务的实际成本。

Claude 3 Haiku 的上下文窗口是多大?+

Claude 3 Haiku 单次请求最多支持 200K 上下文 token,输出最多 4K token。

Claude 3 Haiku 是否兼容 OpenAI?+

WaveSpeedAI 通过 https://llm.wavespeed.ai/v1 的 OpenAI 兼容 Chat Completions 接口提供 Claude 3 Haiku。大多数 OpenAI SDK 客户端只需更换 base URL 和 API Key；可选字段取决于具体模型。

如何开始使用 Claude 3 Haiku?+

登录 WaveSpeedAI，在 Access Keys 中创建 API Key，然后使用上方显示的 model id 向 https://llm.wavespeed.ai/v1/chat/completions 发送请求。模型可用性、能力和价格请以当前模型目录为准。

定价