InferPrice

All models

DeepSeek V4 Flash (0731) API pricing

DeepSeek V4 Flash (0731) by DeepSeek is cheapest at DeepInfra: $0.06 input and $0.18 output per 1M tokens. Compared across 2 providers.

ProviderInput $/1MOutput $/1MBlended 3:1Notes
DeepInfra$0.06$0.18$0.09source
Baseten$0.13$0.26$0.16source

Providers may serve different quantizations or speed tiers of the same model, so check the notes. Last checked 2026-10-12.