by QwenReleased 23 October 2025
The dense 32B Qwen3-VL Instruct, aimed at precise understanding and reasoning across text, images and video, from spatial layout and document or scene analysis to long videos, with OCR in 32 languages
Reads about 130 pages · writes up to 32 pages
Standard OpenAI fields, grouped by what they control. Anything not listed is accepted and ignored.
Shaping the reply
How long, how varied, where to stop.
max_tokenstemperaturetop_ptop_kstopseedfrequency_penaltypresence_penaltylogprobstop_logprobsStructured output
Get JSON you can parse instead of prose.
response_formatstructured_outputsTools
Let the model call your functions.
toolstool_choiceNo. Qwen has retired it. Other Qwen models are on sale.
The dense 32B Qwen3-VL Instruct, aimed at precise understanding and reasoning across text, images and video, from spatial layout and document or scene analysis to long videos, with OCR in 32 languages.
Qwen states that its text reading (OCR) covers 32 languages, without listing them in the card. Arabic, French and Darja are not named.
It reads text and images. Up to 131K tokens in one request, about 130 pages. It writes up to 25 000 words at once.
Yes, its weights are public. Open weights on Hugging Face
Qwen. Released 23 October 2025.
The 8B Qwen3 Embedding, carrying Qwen3's multilingual reach and long-text understanding into vectors for text and code retrieval, classification, clustering and bitext mining; the 4B is its smaller sibling
Qwen3 Reranker 8B reads a search question together with each candidate text and gives each pair a relevance score, so the best matches rise to the top. It covers over 100 languages and programming languages, and you can tell it what counts as relevant for your task. Use it as the second pass after a search step such as Qwen3's text-meaning models has fetched candidates, to put your answers in order. It does not write text itself.
Qwen3 Embedding 4B turns text into a fingerprint of its meaning, so search finds text that means the same even in other words or another language. It covers over 100 languages, code included, and reads about 32 pages at once, which suits searching documents or code, grouping similar texts and matching translations.
Qwen-Audio-3.0-TTS Plus reads text and speaks it aloud, and Alibaba's docs say it takes plain-language directions for speech rate, emotion and speaking style. It is the higher-quality tier of the two Qwen-Audio-3.0 speech models, made by Alibaba. Pick it for narration, voiceover or any line where voice quality matters more than speed.
From what its maker and two benchmark sites publish, and where it stands on OpenDunes. Read 9 Oct 2026.
Thinks first No.
Works through the problem before it answers.
Uses your tools
Can call functions your code provides.
Fills your JSON
Answers in the JSON shape you give it.
Searches the web No.
Can look things up online while it answers.
Cheaper on repeats No.
A prompt it saw a moment ago costs less the second time.
Open weights
The model's weights are public.
Read a scanned invoice and return its fields as JSON
Images · Fills your JSON
Pull a table out of a chart image
Images
Describe a product photo for a listing
Images