Qwen: Qwen3 Max Thinkingqwen
Qwen: Qwen3 Max Thinking: $0.78/1M input, $3.90/1M output, 262K context, CPS grade B. 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...
API Pricing (per 1M tokens)
| Input | $0.78 |
| Output | $3.90 |
| Cache Read | — |
| Cache Write | — |
| Blended (3:1) | $1.56 |
Specs & Performance
| Context Length | 262K |
| Max Output | 66K |
| Intelligence | 16 |
| Coding | 31 |
| Math | 82 |
| Speed | — |
| TTFT | — |
| CPS Grade | B |
| Input / Output Modalities | text → text |
More from qwen
Looking for cheaper alternatives?
Find the cheapest model by task, or compare two models head-to-head.
FAQ
How much does the Qwen: Qwen3 Max Thinking API cost?
Qwen: Qwen3 Max Thinking costs $0.78/1M input tokens and $3.90/1M output tokens. Blended cost at a 3:1 ratio is about $1.56/1M tokens.
What is the context window of Qwen: Qwen3 Max Thinking?
Qwen: Qwen3 Max Thinking supports a 262K token context window with up to 66K output tokens.
Is Qwen: Qwen3 Max Thinking worth it?
Qwen: Qwen3 Max Thinking has a CPS grade of B (score 64), intelligence index 16, coding index 31. Use the compare page to benchmark against rivals.