向量POST

curl https://api.tokentosea.com/v1/embeddings \
  -H "Authorization: Bearer $TOKENTOSEA_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "model": "text-embedding-v4",
    "input": ["向量检索通过向量相似度查找相关内容。", "今天的午餐是米饭。"]
  }'

import os
import uuid

import requests

response = requests.post(
    "https://api.tokentosea.com/v1/embeddings",
    headers={
        "Authorization": "Bearer " + os.environ["TOKENTOSEA_API_KEY"],
        "Idempotency-Key": str(uuid.uuid4()),
    },
    json={
        "model": "text-embedding-v4",
        "input": ["向量检索通过向量相似度查找相关内容。", "今天的午餐是米饭。"],
    },
    timeout=120,
)
response.raise_for_status()
body = response.json()
vectors = [item["embedding"] for item in body["output"]["embeddings"]]  # 千问原生结构
print(len(vectors), len(vectors[0]), body["usage"])

import { randomUUID } from 'node:crypto';

const response = await fetch('https://api.tokentosea.com/v1/embeddings', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.TOKENTOSEA_API_KEY}`,
    'Content-Type': 'application/json',
    'Idempotency-Key': randomUUID(),
  },
  body: JSON.stringify({
    model: 'text-embedding-v4',
    input: ['向量检索通过向量相似度查找相关内容。', '今天的午餐是米饭。'],
  }),
});
if (!response.ok) throw new Error(`HTTP ${response.status}: ${await response.text()}`);
const body = await response.json();
const vectors = body.output.embeddings.map((item) => item.embedding); // 千问原生结构
console.log(vectors.length, vectors[0].length, body.usage);

{ "model": "embedding-3", "input": ["你好世界"] }

{ "model": "doubao-embedding-vision-251215", "input": [{ "type": "text", "text": "你好世界" }] }

{ "model": "qwen3-vl-embedding", "input": [{ "text": "你好世界" }] }

{ "model": "text-embedding-async-v1", "file_url": "https://example.com/lines.txt", "parameters": { "text_type": "document" } }