When was Qwen3-Next-80B-A3B-Thinking released?

Qwen3-Next-80B-A3B-Thinking was released on September 10, 2025 by Qwen. This is the official Qwen3-Next-80B-A3B-Thinking release date tracked on LLM Stats.

How big is Qwen3-Next-80B-A3B-Thinking?

Qwen3-Next-80B-A3B-Thinking has 80 billion parameters. It was trained on 15.0 trillion tokens. It ships as an open-weight model, so you can download and run it on your own hardware.

Who created Qwen3-Next-80B-A3B-Thinking?

Qwen3-Next-80B-A3B-Thinking was created by Qwen.

What is the license for Qwen3-Next-80B-A3B-Thinking?

Qwen3-Next-80B-A3B-Thinking is released under the Apache 2.0 license. This is an open-source / open-weight license that permits self-hosting.

Where can I use Qwen3-Next-80B-A3B-Thinking?

Qwen3-Next-80B-A3B-Thinking is available through 1 provider including Novita.

Where is the Qwen3-Next-80B-A3B-Thinking paper or technical report?

Qwen3-Next-80B-A3B-Thinking has a paper or technical report available at https://qwenlm.github.io/blog/qwen3-next/. Use that source for architecture, training, release and evaluation details.

What models should I compare Qwen3-Next-80B-A3B-Thinking against?

Common Qwen3-Next-80B-A3B-Thinking comparisons include Qwen3-Next-80B-A3B-Thinking vs GPT-5 Medium, Qwen3-Next-80B-A3B-Thinking vs LongCat-Flash-Thinking, Qwen3-Next-80B-A3B-Thinking vs Llama 3.1 Nemotron Ultra 253B v1. Compare them side by side for benchmark scores, pricing, context window, latency and provider availability.

Qwen3-Next-80B-A3B-Thinking Benchmarks, Pricing & Context Window

Name: Qwen3-Next-80B-A3B-Thinking
Author: Qwen

Qwen3-Next-80B-A3B-Thinking: Benchmarks, Pricing & Context Window

Qwen3-Next-80B-A3B-Thinking is a language model from Qwen, released in September 2025.

Qwen3-Next-80B-A3B-Thinking is the thinking variant of the Qwen3-Next series, featuring the same groundbreaking architecture as the instruct model. Leveraging GSPO, it addresses stability and efficiency challenges of hybrid attention +

Input

Text

Output

Text

Qwen3-Next-80B-A3B-Thinking benchmarks

Capability tiers

Standing within each category, adjusted for leaderboard depth.

Real tasks performance

High-confidence performance for Qwen3-Next-80B-A3B-Thinking across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.

Performance by conversation depth

How Qwen3-Next-80B-A3B-Thinking holds up as conversations get longer.

Quality Tracker

Qwen3-Next-80B-A3B-Thinking Performance Across Datasets

Scores sourced from the model's scorecard, paper, or official blog posts

llm-stats.com - Sun Sep 13 2026

Notice missing or incorrect data?

Qwen3-Next-80B-A3B-Thinking pricing

Providers

Qwen3-Next-80B-A3B-Thinking starts at $0.150 per million input tokens and $1.50 per million output tokens via Novita.

Provider	Input $/M	Cached input $/M	Output $/M	Context in / out	TTFT p95 s	Output p5 c/s	Modalities in / out
Novita	$0.150	—	$1.50	65.5K/65.5K	—	—	/

Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.

Qwen3-Next-80B-A3B-Thinking model size

Qwen3-Next-80B-A3B-Thinking has 80 billion parameters and was trained on 15 trillion tokens. See how it compares to other models in the same parameter range.

ParametersTraining tokens

80BMoE

15Ttokens

188× tokens-to-params ratio

Very large (80–200B)

80B

1B7B70B405B

Qwen3-Next-80B-A3B-Thinking context window

Input and output token limits for Qwen3-Next-80B-A3B-Thinking, plus how it ranks on long-context understanding.

InputOutput

66Ktokens

≈ 99 pages of text

66K

8K128K1M

Try now

huggle

Qwen3-Next-80B-A3B-Thinkingin Huggle

Make it with
Qwen3-Next-80B-A3B-Thinking.

Qwen3-Next-80B-A3B-Thinking latency

Qwen3-Next-80B-A3B-Thinking time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.

Qwen3-Next-80B-A3B-Thinking examples

Recent arena outputs from Qwen3-Next-80B-A3B-Thinking, picked from the highest-ranked matchups.

Qwen3-Next-80B-A3B-Thinking license

Qwen3-Next-80B-A3B-Thinking is released under the Apache 2.0 license, which permits commercial use, has 80.0B parameters.

License: Apache 2.0; Commercial use allowed
Parameters: 80.0B

Apache License 2.0 - allows commercial use

Qwen3-Next-80B-A3B-Thinking resources

Official sources for Qwen3-Next-80B-A3B-Thinking: provider documentation, official playground, official launch post, source repository.

Qwen3-Next-80B-A3B-Thinking vs other models

The most-compared alternatives to Qwen3-Next-80B-A3B-Thinking are GPT-5 Medium, LongCat-Flash-Thinking, Llama 3.1 Nemotron Ultra 253B v1. Open any pair side-by-side for benchmarks, pricing, context, and latency.