Same open weights, served by 1 provider. Weights: Qwen/Qwen3.5-27B.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra | Qwen/Qwen3.5-27B | flexFP80.8× standard | $0.208 | $2.08 | — | $0.676 | Verified 4h ago · Changed 7h ago | |
DeepInfra | Qwen/Qwen3.5-27B | standardFP8 | $0.26 | $2.6 | — | $0.845 | Verified 4h ago · Changed 7h ago | |
DeepInfra | Qwen/Qwen3.5-27B | priorityFP81.5× standard | $0.39 | $3.9 | — | $1.27 | Verified 4h ago · Changed 7h 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 fp8 | $78/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.