Alibaba

Qwen3-VL Embedding 2B

About

Qwen3-VL Embedding 2B is a 2B open-weight model from Alibaba. Multimodal embedding model for text, image, and video inputs. It accepts text, images, and video. Context window is 8K. Released January 7, 2026.

Parameters
2B
Published parameter count.
Context window
8K
Tokens of context on a request.
License
Apache-2.0
License on the weights.

Pricing

Token rates are US dollars per 1M tokens. Image rates are per 1K images. Audio rates are per 1M audio seconds.

Rate	Price
Input / 1M	$0.013
Cached input / 1M	$0.013
Output / 1M	$0

Compare

Qwen3-VL Embedding 2B is the only embedding model in the catalog. The other rows take similar inputs and do a different job.

Model	What it does	Price	Parameters	Context
Qwen3-VL Embedding 2B	Multimodal embedding model for text, image, and video inputs.	$0.013 / 1M input	2B	8K
OCR Auto	Routes each method to its best OCR engine: ocr to PP-OCRv6, markdown to a fast CPU parser (dots.mocr on error), layout to dots.mocr.	$0 / 1M input	—	—
PP-OCRv6	PaddleOCR PP-OCRv6 medium text detection and recognition; scene OCR JSONL on image chat; text returns plain text; document_url fan-out via text.	$0.02 / 1M input	20M	—
Qwen3.5 0.8B	Multimodal chat model with up to 64 images or one video per request.	$0.08 / 1M input	0.8B	256K

Benchmarks

Published scores for Qwen3-VL Embedding 2B, from the Qwen3-VL-Embedding model card.

Evals

Reading	Example
Qualitative	Clear structure, grounded in the input
Quantitative	MMEB image: 75.
Cost and performance	Lower listed rate, mid-pack latency

Methods

Methods this model serves. Payload shapes are in the docs.

Method	Returns
embed	An embedding vector

Supported inputs

textYes
A string, an array of strings, or text content parts.
image_urlYes
As content parts in input, embedded into the same vector space as text.
video_urlYes
As content parts in input; frames are sampled and embedded.
document_urlNo
Rasterize the pages and send them as image_url parts.

Served over POST /v1/openai/embeddings. Only method: embed. Context window 8,192 tokens. dimensions truncates the output vector.
Weights: Qwen/Qwen3-VL-Embedding-2B.

Estimate cost

Estimate. An hour of video is 15 frames a minute at 256 tokens a frame, plus the audio in that request, and 500 output tokens a minute.

Hours of video

$4.49

Quick start

Call this model on the OpenAI-compatible gateway. The model id is already filled in.

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))