qwen/qwen3-vl-embedding-2b - VLM Run

The full model card is on the website: qwen/qwen3-vl-embedding-2b.

Request

from openai import OpenAI

client = OpenAI(
    base_url="https://gateway.vlm.run/v1/openai",
    api_key="<VLMRUN_API_KEY>",
)

response = client.embeddings.create(
    model="qwen/qwen3-vl-embedding-2b",
    input="Extract a vector representation for this text.",
)

print(len(response.data[0].embedding))

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://gateway.vlm.run/v1/openai",
  apiKey: process.env.VLMRUN_API_KEY,
});

const response = await client.embeddings.create({
  model: "qwen/qwen3-vl-embedding-2b",
  input: "Extract a vector representation for this text.",
});

console.log(response.data[0].embedding.length);

vlmrun gw embed -t "Extract a vector representation for this text." \
  -m qwen/qwen3-vl-embedding-2b

curl https://gateway.vlm.run/v1/openai/embeddings \
  -X POST \
  -H "Authorization: Bearer $VLMRUN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3-vl-embedding-2b",
    "input": "Extract a vector representation for this text."
  }'