Qwen3 VL Embedding 8B

Summary: Qwen3 VL Embedding 8B is a multimodal embedding model by Alibaba's Qwen team that generates semantic vector representations from both text and images. Supporting over 30 languages and a 32,768-token context window, this model excels in multimodal search, visual document retrieval, and cross-modal semantic matching, making it ideal for applications that require understanding across both textual and visual content such as image-text retrieval, screenshot search, and PDF document discovery.

Intelligence	Speed	Sovereignty	Input	Output
High	Medium	Medium	Text, Image	Number Vector

Central parameters

Description: Multimodal embedding model by Alibaba's Qwen team, generating 4096-dimensional vectors from text and image inputs across 30+ languages.

Model identifier: Qwen/Qwen3-VL-Embedding-8B

IONOS CLOUD AI Model Hub Lifecycle and Alternatives

IONOS Launch	End of Life	Alternative	Successor
May 12, 2026	N/A

Origin

Provider	Country	License	Flavor	Release
Qwen (Alibaba)	Community	Apache 2.0	-	January 8, 2026

Technology

Input Length	Parameters	Tensor Type	Multilingual	Further details
32768	8B	bfloat16	Yes	Hugging Face

Input and output: Each input produces one embedding vector, regardless of modality. A document can be text-only, image-only, or a combination of text and image, each produces a single vector up to 4096 dimensions.

Modalities

Text	Image	Audio
Input and output	Input	Not supported

Endpoints

Chat Completions	Embeddings	Image generation
Not supported	v1/embeddings	Not supported

Features

Streaming	Reasoning	Tool calling
Not supported	Not supported	Not supported

Usage examples

Text embeddings

The following example demonstrates how to generate text embeddings using Qwen3 VL Embedding 8B.

API Endpoint: POST https://openai.inference.de-txl.ionos.com/v1/embeddings

Request:

{
  "model": "Qwen/Qwen3-VL-Embedding-8B",
  "input": "The food was delicious and the waiter was friendly."
}

Response:

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "embedding": [
        0.0023064255,
        -0.009327292,
        0.0028842222
      ],
      "index": 0
    }
  ],
  "model": "Qwen/Qwen3-VL-Embedding-8B",
  "usage": {
    "prompt_tokens": 10,
    "total_tokens": 10
  }
}

Multimodal embeddings

The following example demonstrates how to generate embeddings from combined text and image input using Qwen3 VL Embedding 8B.

Request:

{
  "model": "Qwen/Qwen3-VL-Embedding-8B",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "image_url",
          "image_url": {
            "url": "https://example.com/image.jpg"
          }
        },
        {
          "type": "text",
          "text": "A product image showing a laptop"
        }
      ]
    }
  ],
  "encoding_format": "float"
}

Response:

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "embedding": [
        0.0023064255,
        -0.009327292,
        0.0028842222
      ],
      "index": 0
    }
  ],
  "model": "Qwen/Qwen3-VL-Embedding-8B",
  "usage": {
    "prompt_tokens": 261,
    "total_tokens": 261
  }
}

Rate limits

Rate limits ensure fair usage and reliable access to the AI Model Hub. In addition to the contract-wide rate limits, no model-specific limits apply.