DeepSeek V4 Flash

General purpose, coding, long context. Runs on Confidential Inference: an OpenAI-compatible endpoint inside TEEs, with an attestation on every response.

StatusInput (per 1M tokens)Input Cached (per 1M tokens)Output (per 1M tokens)
Live$0.20$0.018$0.40

Get access

Full pricing: pricing. Docs: get started.