Qwen: Qwen3 Max is an API-access large language model from Qwen priced at $0.78/1M input tokens and $3.90/1M output tokens with a 262k context window. Context caching reduces input costs to $0.39/1M for cache reads.
Economics (OpenRouter)
Input / 1M
$0.78
Output / 1M
$3.90
Est. Monthly Cost
$58.73
Based on current usage settings
Cache Read$0.39
Cache Write$0.98
Capabilities (models.dev)
ReasoningNo
Tool CallNo
Audio InNo
Audio OutNo
Modalitytext
Context Window262k
Benchmarks (AA)
Intelligence Index
General reasoning and knowledge
—
Coding Index
Code generation & debugging
—
Math Index
Mathematical reasoning
—
Performance
—tokens/sec
* Median output throughput
Model ID: qwen/qwen3-max • Data Sources: OpenRouter, Artificial Analysis, models.dev