Qwen3.7 Max API Pricing & Cost Calculator

How this is calculated

Qwen3.7 Max is priced at $1.475 per million input tokens and $4.425 per million output tokens, with an 80% prompt caching discount ($0.295 per million cached reads). That puts it slightly costlier than GLM-5.2 ($1.40/$4.40) but cheaper than Gemini 3.6 Flash on output.

Verdict

Qwen3.7 Max sits at $1.475/M input and $4.425/M output, with an 80% cache discount dropping cached input to $0.295/M. The pricing overlaps GLM-5.2's $1.40/$4.40 nearly exactly, and falls below Gemini 3.6 Flash's $7.50/M on the output row. The 1M context window is the differentiator that makes the cost math work for document-heavy workloads: large persistent contexts fit in a single call without chunking, and the 80% cache discount cuts the stable-prompt portion of the bill by a factor of five. For Qwen-lineage buyers the call is straightforward: the per-token cost is competitive and the context size eliminates the chunking tax.