Same open weights, served by 2 providers.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra | Qwen/Qwen3.5-397B-A17B | flexFP80.8× standard | $0.36 | $2.4 | $0.176 | $0.87 | Verified 5h ago · Changed 7h ago | |
DeepInfra | Qwen/Qwen3.5-397B-A17B | standardFP8 | $0.45 | $3.0 | $0.22 | $1.09 | Verified 5h ago · Changed 7h ago | |
Together AI Deprecated | Qwen/Qwen3.5-397B-A17B | standardQuantization not disclosed | $0.60 | $3.6 | $0.35 | $1.35 | Verified 7h ago · Changed 7h ago | |
DeepInfra | Qwen/Qwen3.5-397B-A17B | priorityFP81.5× standard | $0.675 | $4.5 | $0.33 | $1.63 | Verified 5h 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 | $105/mo |
| Together AI | $132/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.