Qwen3 VL Embedding 8B TL5

TL5 §203Open weights

Cross-modal search for text, images, and video with 4,096-dimensional embeddings

Pricing

Prices for this trust level. Input images are priced per MPx and input text per 1M tokens. Output is not priced.

Trust levels for this model
Trust Level Region Context Max outputInput image / MPxInput token / 1M§203
TL5 DE 16K — - - 0.10 € 0.11 $ §203

USD prices are converted from EUR at the ECB reference rate of 1 EUR = 1.1014 USD (2026-11-16). EUR prices are authoritative.

Prices as of 16.11.2026.

About this model

Qwen3-VL-Embedding-8B is Alibaba's open-weight multimodal embedding model built on Qwen3-VL for semantic retrieval across text, images, screenshots, and video. Its 8B-parameter encoder processes up to 32K input tokens and produces vectors of up to 4,096 dimensions. A dual-tower design independently embeds queries and content into a shared semantic space, enabling text-to-image search, video retrieval, visual document discovery, and multimodal retrieval-augmented generation (RAG). Matryoshka Representation Learning allows adjustable embedding dimensions, while task-specific instructions help adapt retrieval behavior. The model supports more than 30 languages and can encode mixed text-and-image or text-and-video inputs. It produces embeddings rather than generated answers; a separate Qwen3-VL-Reranker can refine retrieved results. Weights are released under Apache 2.0.

API

Model ID qwen3-vl-embedding-8b-tl5 OpenAI compatible

Base URL https://api.aki.io/v1

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_AKI_API_KEY",
    base_url="https://api.aki.io/v1",
)

response = client.embeddings.create(
    model="qwen3-vl-embedding-8b-tl5",
    input="Hello!",
)
print(response.data[0].embedding)
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "YOUR_AKI_API_KEY",
  baseURL: "https://api.aki.io/v1",
});

const response = await client.embeddings.create({
  model: "qwen3-vl-embedding-8b-tl5",
  input: "Hello!",
});
console.log(response.data[0].embedding);
curl https://api.aki.io/v1/embeddings \
  -H "Authorization: Bearer $AKI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3-vl-embedding-8b-tl5",
    "input": "Hello!"
  }'

Frequently Asked Questions

How much does Qwen3 VL Embedding 8B TL5 cost?
Input: 0.10 € per 1M tokens. Prices are exclusive of VAT. Output is not priced.
What is the context window of Qwen3 VL Embedding 8B TL5?
Qwen3 VL Embedding 8B TL5 supports up to 16K tokens.
Which trust levels are available for Qwen3 VL Embedding 8B TL5?
Qwen3 VL Embedding 8B TL5 is available at TL5 (Germany Sovereign, DE).
Is Qwen3 VL Embedding 8B TL5 open weights?
Yes. The model weights are available on Hugging Face under the linked license.
Is Qwen3 VL Embedding 8B TL5 available with zero data retention?
Yes. Qwen3 VL Embedding 8B TL5 is served at TL5 (Germany Sovereign) with zero data retention and no model training.
How do I use Qwen3 VL Embedding 8B TL5 with the OpenAI SDK?
Use the model ID qwen3-vl-embedding-8b-tl5 with the OpenAI-compatible endpoint at https://api.aki.io/v1.

Start Building with Qwen3 VL Embedding 8B TL5