Qwen

Qwen3 Next 80B A3B Instruct

by Qwentext->text5 endpoints
Neura Intelligence Index
45.7/ 100
Rank
#197
Confidence
low
Benchmarks
3(8% coverage)

Overview

Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...

Capabilities

Text generation
Tool use / Function calling
Structured output
Long context
Top-P sampling
Stop sequences
Deterministic seed
Log probabilities

Modalities

Input
Text
Output
Text

Technical Specifications

Context Window
262.1K tokens
Max Output
16.4K tokens
Knowledge Cutoff
2025-09-30
Tokenizer
Qwen3
Uptime (24h)
9999.1%
Parameters
80000000000B
License
apache_2_0Open Weights
Country
🇨🇳CN
Release Date
September 10, 20251y

Supported Parameters

frequency_penaltylogit_biaslogprobsmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Benchmark Performance

math

BenchmarkScoreSource
AIME 2025
69.5
verified

reasoning

BenchmarkScoreSource
GPQA Diamond
72.9
verified

agent

BenchmarkScoreSource
TAU-Bench Retail
60.9
verified

Performance Over Time

Pricing

Per 1M tokens
Input$0.09
Output$1.10
Added
September 11, 2025
Last synced 9/18/2026