by QwenReleased 11 September 2025
Qwen3 Next 80B A3B Thinking reads text and writes back text, and it always thinks before it answers. Qwen aims it at hard multi-step problems: maths proofs, writing and debugging code, logic puzzles and planning the steps of a task. It keeps about 260 pages in mind at once, and Qwen reports roughly 10 times the speed of Qwen3 32B on long inputs.
Reads about 260 pages · writes up to 230 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_penaltyrepetition_penaltylogprobstop_logprobsReasoning
Let it think before answering — and see the thinking.
reasoninginclude_reasoningStructured 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.
Qwen3 Next 80B A3B Thinking reads text and writes back text, and it always thinks before it answers. Qwen aims it at hard multi-step problems: maths proofs, writing and debugging code, logic puzzles and planning the steps of a task. It keeps about 260 pages in mind at once, and Qwen reports roughly 10 times the speed of Qwen3 32B on long inputs.
Qwen names no languages for Qwen3 Next 80B A3B Thinking. Arabic, French and Darja: not stated.
It reads text. Up to 262K tokens in one request, about 260 pages. It writes up to 177 000 words at once.
Yes, its weights are public. Open weights on Hugging Face
Qwen. Released 11 September 2025. It knows the world up to 30 September 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 28 Oct 2026.
Thinks first
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.
Knows events up to 30 Sep 2025
What it learned stops at this date.
Work through a proof or a logic puzzle
Thinks first
Read a long codebase file and explain it
Call your tools to finish a task
Uses your tools