deepseek-v4-flash

A DeepSeek model. Every figure below was read off DeepSeek's own pricing page and stamped with the date it was read — last pass 2026-08-04. Nothing here is estimated.

Input / 1M tokens$0.14
Output / 1M tokens$0.28
Context window1000000
Max output384000

supports Responses API

Price is only one decision input. Runtime performance requires reproducible measurement; the benchmark protocol explains what is measured and clearly marks results that are still pending. See every DeepSeek model on its provider page.