Qwen3-Next 80B-A3B (Thinking) Official Specifications, Pricing & Benchmarks
Qwen3-Next 80B-A3B (Thinking) (qwen3-next-80b-a3b-thinking) by Alibaba Qwen, released 2025-09, featuring 131,072 context window, 32,768 max output tokens, and Text input.
📋 Qwen3-Next 80B-A3B (Thinking) Official API & System Card Specifications
Verified against official Alibaba Qwen developer documentation & pricing
1. Identity & Capabilities
API Spec- API Model ID
- qwen3-next-80b-a3b-thinking
- Release Date
- 2025-09
- Weight License
- Open-Weight (API Spec)
- Native Reasoning
- ✅ Supported
- Function Calling & JSON Schema
- ✅ 原生支持
- Batch API 异步批处理
- ✅ Supported (50% off)
2. Context, Output & Modalities
Limits- Max Context Window
- 131,000 tokens (131K)
- Max Output Tokens
- 32,768 tokens
- Input Modalities
- Text
- Output Modalities
- Text
- Direct China Access
- ✅ Direct CN + RMB
- Deployment Mode
- Open-Weight + Cloud API
3. Official Pricing & Cache
USD / 1M- Input / 1M Tokens
- $ 0.5
- Cached Input / 1M
- $ 0.1 -80%
- Output / 1M Tokens
- $ 6
🎛️ Official Sampling & Reasoning Parameters
Recommended generation settings & API parameter constraints
📊 Qwen3-Next 80B-A3B (Thinking) Full Benchmark Scorecard
22 public benchmarks · ranks among 154 models · synced 2026-11-20
🤖 Agents & Tools 6 items
Berkeley Function Calling Leaderboard v3 (BFCL-v3) is an advanced benchmark that evaluates large language models' function calling capabilities through multi-turn and multi-step interactions.
A benchmark for evaluating tool-agent-user interaction in retail environments. Tests language agents' ability to handle dynamic conversations with users while using domain-specific API tools and following policy guidelines.
τ²-bench retail domain evaluates conversational AI agents in customer service scenarios within a dual-control environment where both agent and user can interact with tools.
TAU2 airline domain benchmark for evaluating conversational agents in dual-control environments where both AI agents and users interact with tools in airline customer service scenarios.
Part of τ-bench (TAU-bench), a benchmark for Tool-Agent-User interaction in real-world domains. The airline domain evaluates language agents' ability to interact with users through dynamic conversations while following domain-specific rules and using API tools.
τ²-Bench telecom domain evaluates conversational agents in a dual-control environment modeled as a Dec-POMDP, where both agent and user use tools in shared telecommunications troubleshooting scenarios that test coordination and communication capabilities.
📐 Math 8 items
An improved version of the MMLU benchmark featuring manually re-annotated questions to identify and correct errors in the original dataset. Provides more reliable evaluation metrics for language models by addressing dataset quality issues found in the original MMLU.
All 30 problems from the 2025 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999.
A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks.
Extended version of MMLU-Pro providing additional challenging multiple-choice questions for evaluating language models across diverse academic and professional domains. Built on the foundation of the Massive Multitask Language Understanding benchmark framework.
LiveBench is a challenging, contamination-limited LLM benchmark that addresses test set contamination by releasing new questions monthly based on recently-released datasets, arXiv papers, news articles, and IMDb movie synopses.
Harvard-MIT Mathematics Tournament 2025 - A prestigious student-organized mathematics competition for high school students featuring two tournaments (November 2025 at MIT and February 2026 at Harvard) with individual tests, team rounds, and guts rounds.
SuperGPQA is a comprehensive benchmark that evaluates large language models across 285 graduate-level academic disciplines.
Polymath is a challenging multi-modal mathematical reasoning benchmark designed to evaluate the general cognitive reasoning abilities of Multi-modal Large Language Models (MLLMs).
🧠 Reasoning & Science 5 items
Multi-IF benchmarks LLMs on multi-turn and multilingual instruction following. It expands upon IFEval by incorporating multi-turn sequences and translating English prompts into 7 other languages, resulting in 4,501 multilingual conversations with three turns each.
A challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. Questions are Google-proof and extremely difficult, with PhD experts reaching 65% accuracy.
LiveCodeBench is a holistic and contamination-free evaluation benchmark for large language models for code.
Arena-Hard-Auto v2 is a challenging benchmark consisting of 500 carefully curated prompts sourced from Chatbot Arena and WildChat-1M, designed to evaluate large language models on real-world user queries.
OJBench is a competition-level code benchmark designed to assess the competitive-level code reasoning abilities of large language models. It comprises 232 programming competition problems from NOI and ICPC, categorized into Easy, Medium, and Hard difficulty levels.
📚 Knowledge & General 2 items
Instruction-Following Evaluation (IFEval) benchmark for large language models, focusing on verifiable instructions with 25 types of instructions and around 500 prompts containing one or more verifiable constraints.
INCLUDE is a multilingual language-understanding benchmark of 197,243 multiple-choice questions drawn from regional exams in 44 languages, built to measure regional and cultural knowledge rather than translated English content (Romanou et al., 2024).
Source: ZeroEval / llm-stats.com (✓ = third-party verified, others vendor-reported).
Closest Self-Hostable Open-Weight Alternatives to Qwen3-Next 80B-A3B (Thinking)
Open-weight models with full HuggingFace weights for private GPU / Mac deployment
Frequently Asked Questions
Is Qwen3-Next 80B-A3B (Thinking) open-source or proprietary?
Qwen3-Next 80B-A3B (Thinking) (qwen3-next-80b-a3b-thinking) is a proprietary commercial model by Alibaba Qwen. Weights and internal layer dimensions are undisclosed; it is accessed via cloud API.
What are the context limit and API pricing of Qwen3-Next 80B-A3B (Thinking)?
Qwen3-Next 80B-A3B (Thinking) supports 131K input context and 32,768 max output tokens, priced at $0.5/1M input ($0.1/1M cached) and $6/1M output.