Same open weights, served by 3 providers. Weights: deepseek-ai/DeepSeek-V4-Flash-0731.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra | deepseek-ai/DeepSeek-V4-Flash-0731 | flexFP80.8× standard | $0.048 | $0.144 | $0.012 | $0.072 | Verified 4h ago · Changed 7h ago | |
DeepInfra | deepseek-ai/DeepSeek-V4-Flash-0731 | standardFP8 | $0.06 | $0.18 | $0.015 | $0.09 | Verified 4h ago · Changed 7h ago | |
DeepInfra | deepseek-ai/DeepSeek-V4-Flash-0731 | priorityFP81.5× standard | $0.09 | $0.27 | $0.022 | $0.135 | Verified 4h ago · Changed 7h ago | |
Together AI | deepseek-ai/DeepSeek-V4-Flash-0731 | standardQuantization not disclosed | $0.14 | $0.28 | $0.03 | $0.175 | Verified 6h ago · Changed 6h ago | |
Azure AI Foundry | deepseek-v4-flash-0731 | standardglobal endpointQuantization not disclosed | $0.44 | $1.32 | $0.014 | $0.66 | Verified 4h ago · Changed 7h ago | |
Azure AI Foundry | deepseek-v4-flash-0731 | standarddata zone (US)Quantization not disclosed | $0.484 | $1.45 | $0.015 | $0.726 | 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 | $9.6/mo |
| Together AI | $19.6/mo |
| Azure AI Foundry global endpoint | $70.4/mo |
| Azure AI Foundry data zone (US) | $77.44/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.