Claude Opus 4.8 API 多少錢?

WaveSpeedAI 定價:輸入每百萬 token $4.75,輸出每百萬 token $23.75。Prompt 快取與批次處理分別計費,可顯著降低長上下文、高重複任務的實際成本。

Claude Opus 4.8 的上下文視窗有多大?

Claude Opus 4.8 每次請求最多支援 1000K 上下文 token,輸出最多 128K token。

Claude Opus 4.8 是否相容 OpenAI?

WaveSpeedAI 透過 https://llm.wavespeed.ai/v1 的 OpenAI 相容 Chat Completions 介面提供 Claude Opus 4.8。大多數 OpenAI SDK 用戶端只需更換 base URL 和 API Key；選用欄位取決於具體模型。

如何開始使用 Claude Opus 4.8?

登入 WaveSpeedAI，在 Access Keys 中建立 API Key，然後使用上方顯示的 model id 向 https://llm.wavespeed.ai/v1/chat/completions 發送請求。模型可用性、能力和價格請以目前模型目錄為準。

Claude Opus 4.8 API Pricing & Performance

Name: Claude Opus 4.8 API
Brand: anthropic
Price: 4.75 USD
Availability: InStock

anthropic/claude-opus-4.8

發布時間: 2026-05-28

1,000,000 context · $5.00/M input$4.75/M input · $25.00/M output$23.75/M output5% off

Claude Opus 4.8 is Anthropic’s most capable generally available Opus model, built for complex reasoning, long-horizon agentic coding, and high-autonomy professional workflows. It supports text, image, and file inputs with text output, a 1M-token context window, up to 128K output tokens, adaptive thinking, tool use, and structured outputs. It is especially strong for advanced coding, browser and computer-use agents, enterprise knowledge work, financial and legal analysis, and multi-step tasks that require sustained judgment and reliability.

定價

按用量付費

無需預付費用，僅按實際使用量付費

輸入

$5.00 / M Tokens$4.75 / M Tokens

輸出

$25.00 / M Tokens$23.75 / M Tokens

Cache Read

$0.50 / M Tokens$0.47 / M Tokens

Cache Write

$6.25 / M Tokens$5.94 / M Tokens

試用模型

anthropic/claude-opus-4.8

線上

嗨！我是樂於助人的 AI 助理。有什麼可以幫你的嗎？

準備在本機編碼 Agent 中使用這個模型嗎？Agent 設定

API 使用

使用以下程式碼範例整合我們的 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-opus-4.8',
    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-opus-4.8',
    messages: [{ role: 'user', content: 'Hello!' }],
  });
  console.log(response.choices[0]?.message?.content ?? '');
} catch (error) {
  console.error('LLM request failed:', error);
  process.exitCode = 1;
}

模型介紹

Anthropic: Claude Opus 4.8

Why It Looks Great

Anthropic’s most capable generally available Opus model
1M-token context window for large codebases, long documents, and extended multi-turn workflows
Up to 128K output tokens for long-form reasoning, coding, analysis, and structured generation
Strong fit for professional software engineering, complex agentic workflows, and enterprise knowledge work
Improved long-horizon coding reliability, tool triggering, and long-context quality
Adaptive thinking support for balancing speed, cost, and reasoning depth
Vision and file input support for screenshots, diagrams, PDFs, documents, and multimodal analysis
Function calling and tool-use support for agentic application workflows
Structured output support for JSON responses and schema-constrained generation

Key Features

Context Window: 1,000,000 tokens
Max Input: 872,000 tokens
Max Output: 128,000 tokens
Input: Text, Image, File
Output: Text
Vision: Supported
File Input: Supported
Function Calling: Supported
Structured Outputs: Supported
Adaptive Thinking: Supported
Image Generation: Not listed
Audio Input: Not listed
Supported Parameters: include_reasoning, max_tokens, reasoning, response_format, stop, structured_outputs, tool_choice, tools, verbosity

Specifications

Specification	Value
Provider	anthropic
Model Type	Chat Completions model
Architecture	text+image+file->text
Context Window	1,000,000 tokens
Max Input	872,000 tokens
Max Output	128,000 tokens
Input	Text, Image, File
Output	Text
Vision	Supported
File Input	Supported
Function Calling	Supported
Structured Outputs	Supported
Adaptive Thinking	Supported
Release	May 28, 2026

How to Use

Write your prompt - describe the task, provide context, and specify the 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-opus-4.8

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-opus-4.8",
    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-opus-4.8",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Notes

Model: anthropic/claude-opus-4.8
Provider: anthropic
Best suited for long-horizon coding, complex reasoning, enterprise knowledge work, legal and financial analysis, browser/computer-use agents, and high-autonomy tool workflows

資訊

提供商anthropic

類型llm

支援功能

輸入

文字影像

輸出

文字

上下文1,000,000

最大輸出128,000

視覺✓ 支援

函式呼叫✓ 支援

API 存取指南

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

API 端點chat/completions

Model IDanthropic/claude-opus-4.8

定價