anthropic/claude-opus-5.5
发布时间: 2026-09-22
1,000,000 context · $4.00/M input tokens · $20.00/M output tokens
Claude Opus 5.5 supports coding, document analysis, and multi-step tasks with text and image inputs.
按量付费
无需预付费用,仅按实际使用量付费
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-opus-5.5',
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-5.5',
messages: [{ role: 'user', content: 'Hello!' }],
});
console.log(response.choices[0]?.message?.content ?? '');
} catch (error) {
console.error('LLM request failed:', error);
process.exitCode = 1;
}Claude Opus 5.5 supports coding, document analysis, and multi-step tasks with text and image inputs.
Use model anthropic/claude-opus-5.5 with https://llm.wavespeed.ai/v1/chat/completions.
Adaptive thinking is always enabled. Use automatic tool selection; forced tool calls and manual thinking budgets are not supported.
Standard input: $4 per million tokens. Output: $20 per million tokens. Cache reads: $0.2 per million tokens.
anthropic/claude-opus-5.5
Claude Opus 5.5 supports coding, document analysis, and multi-step tasks with text and image inputs.
输入
$4 /M
输出
$20 /M
上下文
1000K
最大输出
128K
Vision
支持
工具调用
支持
通过我们的统一 API 接入 Claude Opus 5.5 — 兼容 OpenAI、无冷启动、透明计费。
WaveSpeedAI 定价:输入每百万 token $4.00,输出每百万 token $20.00。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 Opus 5.5 单次请求最多支持 1000K 上下文 token,输出最多 128K token。
WaveSpeedAI 通过 https://llm.wavespeed.ai/v1 的 OpenAI 兼容 Chat Completions 接口提供 Claude Opus 5.5。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。
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。