Qwen

Qwen: Qwen3 Max Thinking

Verified from OpenRouter · Text & embedding rates at 2026-10-04T03:25:53.257Z.

RatePriceBilling unitCondition
InputUSD 0.78per 1M input tokens—
OutputUSD 3.9per 1M output tokens—
InputUSD 1.56per 1M input tokenswhen prompt exceeds 32,000 tokens
OutputUSD 7.8per 1M output tokenswhen prompt exceeds 32,000 tokens
InputUSD 1.95per 1M input tokenswhen prompt exceeds 128,000 tokens
OutputUSD 9.75per 1M output tokenswhen prompt exceeds 128,000 tokens