Qwen: Qwen3 Next 80B A3B Thinking

Text input Text output
Author's Description

Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic planning, and reports strong results across knowledge, reasoning, coding, alignment, and multilingual evaluations. Compared with prior Qwen3 variants, it emphasizes stability under long chains of thought and efficient scaling during inference, and it is tuned to follow complex instructions while reducing repetitive or off-task behavior. The model is suitable for agent frameworks and tool use (function calling), retrieval-heavy workflows, and standardized benchmarking where step-by-step solutions are required. It supports long, detailed completions and leverages throughput-oriented techniques (e.g., multi-token prediction) for faster generation. Note that it operates in thinking-only mode.

Key Specifications
Cost
$$$$$
Context
131K
Parameters
80B
Released
Sep 11, 2025
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Temperature Response Format Include Reasoning Seed Tool Choice Reasoning Max Tokens Top P Presence Penalty Tools
Features

This model supports the following features:

Tools Response Format Reasoning
Performance Summary

Qwen3-Next-80B-A3B-Thinking is a reasoning-focused chat model designed for complex multi-step problems. Its speed performance tends to be slower, ranking in the 15th percentile across benchmarks, indicating longer response times. In terms of cost, it is positioned at premium pricing levels, falling into the 5th percentile. However, the model demonstrates exceptional reliability with a 99% success rate, consistently providing usable responses. Across benchmarks, the model exhibits strong performance in Coding (94.9% accuracy, 90th percentile), Reasoning (96.0% accuracy, 81st percentile), and Ethics (100% accuracy, achieving perfect scores and being the most accurate at its price point and speed). General Knowledge and Email Classification also show high accuracy at 99.5% and 99.0% respectively. A notable strength is its low hallucination rate (98.0% accuracy). The primary weakness lies in Instruction Following, where it achieved only 14.7% accuracy, placing it in the 21st percentile. Mathematics performance is moderate at 88.9% accuracy. Its "thinking-only" mode is a key feature for structured problem-solving.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.0975
Completion $0.78

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Alibaba
Alibaba | qwen/qwen3-next-80b-a3b-thinking-2509 131K $0.0975 / 1M tokens $0.78 / 1M tokens
Novita
Novita | qwen/qwen3-next-80b-a3b-thinking-2509 131K $0.0975 / 1M tokens $0.78 / 1M tokens
Chutes
Chutes | qwen/qwen3-next-80b-a3b-thinking-2509 262K $0.0975 / 1M tokens $0.78 / 1M tokens
DeepInfra
DeepInfra | qwen/qwen3-next-80b-a3b-thinking-2509 262K $0.0975 / 1M tokens $0.78 / 1M tokens
Hyperbolic
Hyperbolic | qwen/qwen3-next-80b-a3b-thinking-2509 262K $0.0975 / 1M tokens $0.78 / 1M tokens
GMICloud
GMICloud | qwen/qwen3-next-80b-a3b-thinking-2509 262K $0.0975 / 1M tokens $0.78 / 1M tokens
AtlasCloud
AtlasCloud | qwen/qwen3-next-80b-a3b-thinking-2509 262K $0.15 / 1M tokens $1.5 / 1M tokens
NCompass
NCompass | qwen/qwen3-next-80b-a3b-thinking-2509 262K $0.0975 / 1M tokens $0.78 / 1M tokens
Together
Together | qwen/qwen3-next-80b-a3b-thinking-2509 262K $0.0975 / 1M tokens $0.78 / 1M tokens
Parasail
Parasail | qwen/qwen3-next-80b-a3b-thinking-2509 262K $0.0975 / 1M tokens $0.78 / 1M tokens
Google
Google | qwen/qwen3-next-80b-a3b-thinking-2509 262K $0.15 / 1M tokens $1.2 / 1M tokens
Parasail
Parasail | qwen/qwen3-next-80b-a3b-thinking-2509 262K $0.0975 / 1M tokens $0.78 / 1M tokens
Chutes
Chutes | qwen/qwen3-next-80b-a3b-thinking-2509 262K $0.0975 / 1M tokens $0.78 / 1M tokens
Novita
Novita | qwen/qwen3-next-80b-a3b-thinking-2509 131K $0.15 / 1M tokens $1.5 / 1M tokens
Nebius
Nebius | qwen/qwen3-next-80b-a3b-thinking-2509 128K $0.15 / 1M tokens $1.2 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by qwen