Qwen 3 Embedding 4B qwen3-embedding-4b

Multilingual text embedding model with truncatable dimensions for retrieval and RAG. Input longer than the context length is rejected with a 400 (context_length_exceeded).

From the live catalog

View .md

Tokens

$0.05 / 1M tokens

Context

32K tokens

region SJC quantization fp16 Hugging Face Qwen/Qwen3-Embedding-4B

Inputs

Input	Accepts
`text`	context 32K tokens

Parameters

Parameter	Type	Values
`encoding_format`	string	float, base64
`dimensions`	integer	at least 1
`input_type`	string	search_query, search_document

Endpoints

POST/v1/embeddings Create Embeddings

A request

curl https://api.vultrinference.com/v1/embeddings \
  -H "Authorization: Bearer $VULTR_INFERENCE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3-embedding-4b",
    "input": [
      "What is the capital of France?"
    ],
    "input_type": "search_query"
  }'

import os
import requests

response = requests.post(
    "https://api.vultrinference.com/v1/embeddings",
    headers={"Authorization": f"Bearer {os.environ['VULTR_INFERENCE_API_KEY']}"},
    json={
        "model": "qwen3-embedding-4b",
        "input": [
            "What is the capital of France?",
        ],
        "input_type": "search_query",
    },
)
print(response.json())

const response = await fetch("https://api.vultrinference.com/v1/embeddings", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.VULTR_INFERENCE_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "qwen3-embedding-4b",
    "input": [
      "What is the capital of France?"
    ],
    "input_type": "search_query"
  }),
});
console.log(await response.json());