Context Window
262,144
Input tokens
Full-context input ≈ $0.20
Model Cost Profile
Developer: qwen· Tokenizer: Qwen · Quantization: unknown
Canonical ID: qwen/qwen3-max-thinking-20260123
Pricing updated Apr 24, 2026
Live Pricing
Input: $0.7800
Output: $3.90
Last synced Apr 24, 2026 · MMLU score via public benchmark data
Qwen3 Max Thinking, developed by Qwen, offers an extensive context window of 262,144 tokens, making it ideal for applications requiring deep contextual understanding, such as legal document analysis or complex data summarization. With an input price of $1.20 per million tokens and an output price of $6.00 per million tokens, teams can effectively manage costs based on their specific usage patterns and project requirements. This model's high token capacity allows for more comprehensive interactions, which is beneficial for industries such as finance and research where detailed insights are crucial.
Context Window
262,144
Input tokens
Full-context input ≈ $0.20
Max Output
32,768
Completion tokens
Input Price / 1M
$0.7800
Prompt tokens
Output Price / 1M
$3.90
Completion tokens
Top Benchmark
82.4
MMLU score — highest of MMLU, GPQA, MATH, HumanEval
Evaluation scores for Qwen: Qwen3 Max Thinking. The “Top Benchmark” shown above is the highest score across MMLU, GPQA, MATH & HumanEval.
Price History
Current Input / 1M
$0.7800
Current Output / 1M
$3.90
Performance History
Current TPS
0.00
Current Latency
0ms
Uptime
100.0%
| Usage Type | Price / 1M Tokens |
|---|---|
| Input (Prompt) | $0.7800 |
| Output (Completion) | $3.90 |
Estimate monthly spend for Qwen: Qwen3 Max Thinking based on your workload.
Estimated Monthly Cost
$66
25M input + 12M output tokens
Quick links for cost-down decisions before production rollout.