Same open weights, served by 2 providers. Weights: Qwen/Qwen3.5-9B.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra | Qwen/Qwen3.5-9B | flexFull precision0.8× standard | $0.08 | $0.12 | — | $0.09 | Verified 6h ago · Changed 8h ago | |
DeepInfra | Qwen/Qwen3.5-9B | standardFull precision | $0.10 | $0.15 | — | $0.113 | Verified 6h ago · Changed 8h ago | |
DeepInfra | Qwen/Qwen3.5-9B | priorityFull precision1.5× standard | $0.15 | $0.225 | — | $0.169 | 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 bfloat16 | $13/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.