Back to qwen
Alibaba /

Qwen3-Next 80B-A3B (Thinking)
Qwen3-Next 80B-A3B (Thinking)

Open WeightsChat & ReasoningtextUpdated September 1, 2025
Some details or benchmark scores on this page are self-reported by developers and unconfirmed.

Qwen3-Next 80B-A3B (Thinking)

📌 Model Overview

Efficient Qwen thinking model for local reasoning, math, and coding agents

Qwen3-Next 80B-A3B (Thinking) is a Open Weights model developed by Alibaba, released on 2025-09-01. It is designed primarily for Chat Reasoning workloads. Featuring a 131K tokens context window and 80B parameter count, it offers robust performance for enterprise integration, developers, and researchers.

✨ Key Features & Capabilities

Specification Table
FeatureDescription
Context Window131K tokens capacity for extended prompts and multi-turn workflows
Primary TaskOptimized for Chat Reasoning
Deploymentself-hostable, api-only
Modalitytext
Max OutputMax Output: 33K tokens
Native reasoning capabilityNative reasoning capability
Tool / function calling supportTool / function calling support

⚙️ Technical Specifications

Specification Table
SpecificationDetails
Developer / LabAlibaba
Release Date2025-09-01
Model TypeOpen Weights
Parameters80B
Context Window131K tokens
LicenseApache-2.0
Model Familyqwen

💰 Pricing

Specification Table
Tier / UnitRate (USD)
1M input tokens$0.15
1M output tokens$1.2

🔗 Resources & Links

Specification Table
ResourceLink
Hugging Facehttps://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Thinking

📜 License & Usage

This model is governed by the Apache-2.0 license. Please check official developer guidelines before commercial deployment.

Key Features

Max Output: 33K tokens

Feature 01✦

Native reasoning capability

Feature 02✦

Tool / function calling support

Feature 03✦

You might also want to compare

Kimi K3

Moonshot AI

Specs →

Claude Opus 5

Anthropic

Specs →

KAT-Coder-V2.5-Dev

Kwaipilot

Specs →

Verified Sources

Tags

reasoningtool-callingopen-weights

Model Specs

open-weights

Parameters

80B

Context Window

131K tokens

License

Apache-2.0

Deployment

self-hostableapi-only

Pricing

  • 1M input tokens$0.15
  • 1M output tokens$1.2

as of 2026-07-26

Resources & Links

Hugging Face

Lineage

Model Family

Part of the qwen family

Qwen3.8 Max PreviewQwen3.7 PlusQwen3.7 MaxQwen3.6 27BQwen3.6 Max PreviewQwen3.6 35B-A3BQwen3.6 PlusQwen3.5 122B-A10BQwen3.5 27BQwen3.5 35B-A3BQwen3.5 9BQwen3.5 PlusQwen3.5 397B-A17BQwen3 MaxQwen3-VL PlusQwen3-Next 80B-A3B InstructQwen FlashQwen3 Coder FlashQwen3 Coder PlusQwen3 235B-A22BQwen3 32BQwen3-Coder 30B-A3B InstructQwen3-Coder 480B-A35B InstructQwQ PlusQwen-Omni TurboQwen TurboQwen2.5-VL 72B InstructQwen-VL MaxQwen MaxQwen PlusQwen-VL Plus

Curator Notes

Skeleton entry imported from models.dev backfill (2026-07-26). Needs manual enrichment and primary-source verification.

Compare Specs

Compare parameters, context windows, modalities, and benchmark scores of this model side-by-side with others.

Compare Model