modelgrep
Q

Qwen: Qwen3 Next 80B A3B Instruct

qwen/qwen3-next-80b-a3b-instruct

118th smartest of 180Cheaper than 85% of paidToolsJSON
Use via OpenRouter ↗
Intelligence
20.1
118th of 180
Design Elo
Speed
81
99th fastest
Latency
476ms
first token
Input price
$0.090
44th cheapest
Context
262K
16K max out

How it compares

Smarter than34%
of all ranked models
Faster than68%
of all ranked models
Cheaper than85%
of all ranked models

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...

Benchmarks

independent · via OpenRouter
Artificial Analysis33th percentile
Intelligence Index
20.1
Coding Index
15.3
Agentic Index
14.2
GPQA Diamond
74%
Humanity's Last Exam
7%
SciCode
31%
Tau²-Bench (agentic)
22%

Providers & pricing (6)

ProviderIn $/MOut $/MUptime
DeepInfrafp8$0.090$1.1080.5%
Alibaba$0.098$0.78097.9%
Parasailfp8$0.100$1.1098%
Google$0.150$1.2099.9%
AtlasCloudfp8$0.150$1.50100%
Novitabf16$0.150$1.50100%

Specifications

Context window262K
Max output16K
Knowledge cutoffSep 2025
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price
ModeratedNo

Qwen3 Next 80B A3B Instruct FAQ

How much does Qwen3 Next 80B A3B Instruct cost?

Qwen3 Next 80B A3B Instruct costs $0.090 per million input tokens and $1.10 per million output tokens via OpenRouter, making it 44th cheapest of 298 paid models.

How smart is Qwen3 Next 80B A3B Instruct?

Qwen3 Next 80B A3B Instruct scores 20.1 on the Artificial Analysis Intelligence Index, ranking 118th of 180 benchmarked models, with a GPQA Diamond score of 74%.

How fast is Qwen3 Next 80B A3B Instruct?

Qwen3 Next 80B A3B Instruct generates around 81 tokens per second with 476ms time-to-first-token (p50), the 99th fastest tracked model.

What is Qwen3 Next 80B A3B Instruct's context window?

Qwen3 Next 80B A3B Instruct supports a 262K-token context window and can output up to 16K tokens. It accepts text input.

Compare head-to-head