All Models
Qwen/Qwen3-Next-80B-A3B-Thinking
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...
Available Providers (3)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 Kilo Gateway | qwen/qwen3-next-80b-a3b-thinking | $0.10/MTok | $0.78/MTok | 131.1K | 32.8K | |
 SiliconFlow (China) | Qwen/Qwen3-Next-80B-A3B-Thinking | $0.14/MTok | $0.57/MTok | 262K | 262K | |
 SiliconFlow | Qwen/Qwen3-Next-80B-A3B-Thinking | $0.14/MTok | $0.57/MTok | 262K | 262K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output