Same model, served by 1 provider. Weights: Qwen/Qwen4-Max.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra | Qwen/Qwen4-Max | standardQuantization not disclosed | $1.41 | $4.24 | $0.071 | $2.12 | Verified 3h ago ยท Changed 6d ago |
Same weights don't always mean identical outputs: quantization, context limits and serving stacks can change quality, especially for tool calling. Prices are USD per 1M tokens; hyperscaler prices are for the reference region shown.
| DeepInfra | $226.1/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.