DeepSeek V4 Pro
DeepSeek's 1.6T-parameter open-weights MoE model with a 1M-token context window.
Price
What the gateway charges per million tokens: what you send in, and what the model writes back.
Source: Vercel AI Gateway, checked 2026-09-25.
- Input
- $0.66per 1M tokens
- Output
- $1.98per 1M tokensOutput costs 3x the input.
Specs
How much it reads at once, how much it writes back, and how recent its knowledge is.
Sources: Vercel AI Gateway, checked 2026-09-25; Hugging Face, checked 2026-09-25.
- Context window
- 1M tokens1,000,000
- Max output
- 384K tokens384,000
- Knowledge cutoff
- May 2025
- Released
- Type
- Language
- Modalities
- Takes text. Returns text.
- License
- mit
- Gateway ID
deepseek/deepseek-v4-pro
Capabilities
What the gateway says this model supports.
Source: Vercel AI Gateway, checked 2026-09-25.
- Implicit caching
- Reasoning
- Tool use
- Structured output
Data handling
What happens to your prompts, and what you have to switch on.
Source: Vercel AI Gateway, checked 2026-09-25.
ZDRSome providers
Zero data retention
Available on a paid Vercel plan through the AI Gateway, from some providers on it (you turn it on).
NTSome providers
No training on prompts
Offered by some providers on the Vercel AI Gateway, when you turn it on.
Usage
How much people actually run it, as counted where it is served.
- downloads
- 514.4K514,445 downloads
Counted on Hugging Face over the 30 days to 2026-09-25.
- requests
- 238.2M238,217,775 requests
- tokens
- 6.8T6,845,254,864,912 tokens
Counted on OpenRouter over the 31 days to 2026-09-25.
Also by DeepSeek
Friday
The brief, by email
Five to seven links an issue, each with what to do about it.
Unsubscribe from any issue.