Same open weights, served by 1 provider. Weights: deepseek-ai/DeepSeek-V4-Pro.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra | deepseek-ai/DeepSeek-V4-Pro | standardFP8 | $1.3 | $2.6 | $0.10 | $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 | $182/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.