Which has the larger context window, Pro/deepseek-ai/DeepSeek-V3.2 or deepseek-ai/DeepSeek-V3?

Both models offer a similar context window.

Pro/deepseek-ai/DeepSeek-V3.2 vs deepseek-ai/DeepSeek-V3

Q: Is Pro/deepseek-ai/DeepSeek-V3.2 or deepseek-ai/DeepSeek-V3 cheaper?

Pro/deepseek-ai/DeepSeek-V3.2 is cheaper on output tokens ($0.42 vs $1.00 per 1M).

Pro/deepseek-ai/DeepSeek-V3.2 is cheaper on output tokens. Choose Pro/deepseek-ai/DeepSeek-V3.2 or deepseek-ai/DeepSeek-V3 based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Pro/deepseek-ai/DeepSeek-V3.2	deepseek-ai/DeepSeek-V3
Provider	SiliconFlow (China)	SiliconFlow (China)
Input / 1M tokens	$0.27	$0.25
Output / 1M tokens	$0.42	$1.00
Context window	164K	164K
Parameters	—	671B
Open weights	No	No
Released	Dec 2025	Dec 2024

Pro/deepseek-ai/DeepSeek-V3.2 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.