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

deepseek-ai/DeepSeek-V4-Pro has the larger context window (1M tokens).

Pro/deepseek-ai/DeepSeek-V3 vs deepseek-ai/DeepSeek-V4-Pro

Q: Is Pro/deepseek-ai/DeepSeek-V3 or deepseek-ai/DeepSeek-V4-Pro cheaper?

Pro/deepseek-ai/DeepSeek-V3 is cheaper on output tokens ($1.00 vs $3.48 per 1M).

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

Spec	Pro/deepseek-ai/DeepSeek-V3	deepseek-ai/DeepSeek-V4-Pro
Provider	SiliconFlow (China)	SiliconFlow (China)
Input / 1M tokens	$0.25	$1.74
Output / 1M tokens	$1.00	$3.48
Context window	164K	1M
Parameters	—	1.6T
Open weights	No	Yes
Released	Dec 2024	Apr 2026

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

FAQ

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