Is DeepSeek V4 Flash or deepseek-ai/DeepSeek-V3 cheaper?

DeepSeek V4 Flash is cheaper on output tokens ($0.28 vs $1.00 per 1M).

Which has the larger context window, DeepSeek V4 Flash or deepseek-ai/DeepSeek-V3?

DeepSeek V4 Flash has the larger context window (1M tokens).

DeepSeek V4 Flash vs deepseek-ai/DeepSeek-V3

DeepSeek V4 Flash is cheaper on output tokens, while DeepSeek V4 Flash offers a larger context window. Choose DeepSeek V4 Flash or deepseek-ai/DeepSeek-V3 based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	DeepSeek V4 Flash	deepseek-ai/DeepSeek-V3
Provider	SiliconFlow (China)	SiliconFlow (China)
Input / 1M tokens	$0.14	$0.25
Output / 1M tokens	$0.28	$1.00
Context window	1M	164K
Parameters	284B	671B
Open weights	Yes	No
Released	Apr 2026	Dec 2024

DeepSeek V4 Flash details →deepseek-ai/DeepSeek-V3 details →

FAQ

Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.