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

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

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

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

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

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

Spec	deepseek-ai/DeepSeek-V4-Pro	deepseek-ai/DeepSeek-V3
Provider	SiliconFlow (China)	SiliconFlow (China)
Input / 1M tokens	$1.74	$0.25
Output / 1M tokens	$3.48	$1.00
Context window	1M	164K
Parameters	1.6T	671B
Open weights	Yes	No
Released	Apr 2026	Dec 2024

deepseek-ai/DeepSeek-V4-Pro 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.