Qwen: Qwen3 Next 80B A3B Thinking Pricing & Specs

Released: Unknown
OpenRouter Model IDqwen/qwen3-next-80b-a3b-thinking

Qwen: Qwen3 Next 80B A3B Thinking is an API-access large language model from Qwen priced at $0.10/1M input tokens and $0.78/1M output tokens with a 131k context window. Context caching reduces input costs to $0.05/1M for cache reads.

Economics (OpenRouter)

Input / 1M
$0.10
Output / 1M
$0.78
Est. Monthly Cost
$10.85
Based on current usage settings
Cache Read$0.05
Cache Write$0.12

Capabilities (models.dev)

ReasoningNo
Tool CallNo
Audio InNo
Audio OutNo
Modalitytext
Context Window131k

Benchmarks (AA)

Intelligence Index
General reasoning and knowledge
Coding Index
Code generation & debugging
Math Index
Mathematical reasoning
Performance
tokens/sec

* Median output throughput

Model ID: qwen/qwen3-next-80b-a3b-thinking • Data Sources: OpenRouter, Artificial Analysis, models.dev