Text Embeddings

Turn text into vector representations for semantic search / clustering / similarity.

POST /v1/embeddings

Auth: {'type': 'bearer', 'prefix': 'sk-', 'description': 'API Key, 使用 `Authorization: Bearer sk-xxx` 鉴权'}

OpenAI-compatible Embeddings endpoint. Turns text into vectors for semantic search / clustering / similarity. **text-embedding-v4** is a multilingual text embedding model covering Chinese / English and more, outputting **1024 dimensions** by default. Use the `dimensions` parameter to truncate to a smaller size. `input` accepts a single string or an array of strings (batch). The returned `data` array maps to the inputs in `index` order. Zero client changes: point your OpenAI SDK base URL to `https://api.router.ai`.

Request body

`model`	string	required	向量模型 ID。可选: `text-embedding-v4` (多语言, 默认 1024 维, 支持自定义维度) / `text-embedding-004` / `gemini-embedding-001` / `gemini-embedding-2-preview` / `voyage-4-large` / `voyage-4` / `voyage-4-lite` (Voyage, 默认 1024 维, 支持 256/512/1024/2048)
`input`	string	required	待向量化的文本, 或字符串数组 (批量)。数组长度按需分片, 返回向量按 `index` 顺序对应。
`encoding_format`	string		向量编码格式, 省略走默认 `float`。
`dimensions`	integer		(可选) 自定义输出向量维度。`text-embedding-v4` 默认 1024 维, 可传该参数截断到更小维度 (省略走模型默认)。

Responses

200 — 返回向量数组

Example

curl https://api.router.ai/v1/embeddings \
  -H "Authorization: Bearer sk-xxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-v4",
    "input": "Router 是一个多模型聚合 API 平台"
  }'

API reference