Qwen3 Next 80B A3B Thinking

qwen3-next-80b-a3b-thinking

Chat & Textby Qwen

Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. 262,144 token context window, maximum output of 32,768 tokens. Higher uptime with 3 providers. Includes independent benchmarks from Artificial Analysis.

chatstreamingtoolsjson mode

Try in Studio →

Details

Accepts: text
Context window: 131K tokens

Pricing

Input: 18.75 cr / 1M tokens
Output: 150 cr / 1M tokens

Prices in credits (1 credit = $0.01).

Data schema

approximate

Input

Field	Type	Description
promptrequired	string	The text prompt.

Output

Field	Type	Description
text	string	Generated text (choices[0].message.content).