Same model, served by 1 provider. Weights: Qwen/Qwen3.8-Flash.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra | Qwen/Qwen3.8-Flash | standardQuantization not disclosed | $0.113 | $0.382 | $0.014 | $0.18 | Verified 6h ago · Changed 8h 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 | $18.94/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.