from openai import OpenAI

client = OpenAI(
    base_url="https://gateway.vlm.run/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/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/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."
  }'

{
  "id": "embd-00306e5928f441b6a8df9c4c40eea55",
  "object": "list",
  "created": 1792567663,
  "model": "qwen/qwen3-vl-embedding-2b:text",
  "served_model_id": "qwen/qwen3-vl-embedding-2b",
  "backend": "vllm",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [0.009509848430752754, -0.03051667846739292, 0.023419776931405067, /* ... 2048 values in total */]
    }
  ],
  "usage": {
    "prompt_tokens": 9,
    "total_tokens": 9,
    "cost": 0.0
  }
}

{
  "detail": [
    {
      "type": "missing",
      "loc": ["body", "input"],
      "msg": "Field required",
      "input": {
        "model": "qwen/qwen3-vl-embedding-2b"
      }
    }
  ]
}