Qwen · live price
Qwen3 Max Thinking API pricing
Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling model capacity and reinforcement learning compute, it...
- Input
- $0.78
- per 1M tokens
- Output
- $3.90
- per 1M tokens
- Cached input
- –
- per 1M tokens
- Context
- 262K
- 66K max output
List price from OpenRouter, which passes Qwen's price through without markup. Refreshed hourly. Released February 9, 2026. Model id qwen/qwen3-max-thinking.
What Qwen3 Max Thinking costs in practice
1,000 chat messages
$2.73
1,000 input + 500 output tokens each
1,000 RAG questions
$8.19
8,000 input + 500 output tokens each
100 coding-agent steps
$3.12
30,000 input + 2,000 output tokens each, no caching
Qwen3 Max Thinking price history
Qwen3 Max Thinking price by host
- Alibaba$0.78 in · $3.90 out · 262K ctx · 99.6% uptime 24h
Where to buy Qwen credits for less
Disclosure: this site is run by the team behind smaaart, one of the options compared. Tables are ranked by price only, from live quotes and published fees, including when smaaart isn't first. How we compare
Qwen3 Max Thinking cost calculator
Cheaper alternatives to Qwen3 Max Thinking
| Model | Input / 1M | Output / 1M |
|---|---|---|
| OpenAI: GPT-6 Luna Pro | $0.1 | $0.5 |
| OpenAI: GPT-6 Luna | $0.1 | $0.5 |
| Z.ai: GLM 5.3 FlashX | $0.37 | $1.25 |
| DeepSeek: DeepSeek V4.1 Flash | $0.03 | $0.5 |
| Google: Gemini 3.8 Flash | $0.75 | $3.75 |
| Z.ai: GLM 5.3 Flash | $0.15 | $0.5 |
Other Qwen models
| Model | Input / 1M | Output / 1M |
|---|---|---|
| Qwen3 Coder Next | $0.12 | $0.8 |
| Qwen3.5 397B A17B | $0.55 | $3.50 |
| Qwen3.5 Plus 2026-02-15 | $0.26 | $1.56 |
| Qwen3.5-Flash | $0.065 | $0.26 |
| Qwen3.5-122B-A10B | $0.26 | $2.08 |
| Qwen3.5-27B | $0.195 | $1.56 |