Same open weights, served by 3 providers. Weights: deepseek-ai/DeepSeek-V4-Pro-0813.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepSeek Original creator | deepseek-v4-pro | standardQuantization not disclosed | $0.66 | $1.98 | $0.022 | $0.99 | Verified 7h ago · Changed 7h ago More prices
| |
DeepInfra | deepseek-ai/DeepSeek-V4-Pro-0813 | flexFP80.8× standard | $1.04 | $2.08 | $0.08 | $1.3 | Verified 5h ago · Changed 7h ago | |
DeepInfra | deepseek-ai/DeepSeek-V4-Pro-0813 | standardFP8 | $1.3 | $2.6 | $0.10 | $1.63 | Verified 5h ago · Changed 7h ago | |
Together AI | deepseek-ai/DeepSeek-V4-Pro-0813 | standardQuantization not disclosed | $1.32 | $3.96 | $0.13 | $1.98 | Verified 7h ago · Changed 7h ago | |
DeepInfra | deepseek-ai/DeepSeek-V4-Pro-0813 | priorityFP81.5× standard | $1.95 | $3.9 | $0.15 | $2.44 | 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.
| DeepSeek | $105.6/mo |
| DeepInfra fp8 | $182/mo |
| Together AI | $211.2/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.