Qwen3-Next 80B-A3B (Thinking) API Pricing and Cost Calculator
Efficient Qwen thinking model for local reasoning, math, and coding agents
- Input / 1M tokens
- $0.500
- Cached input / 1M tokens
- —
- Output / 1M tokens
- $6.00
- Context window
- 131K
Efficient Qwen thinking model for local reasoning, math, and coding agents