ZeroTwo home

DeepSeek V4 Pro

Default
DeepSeek's generally available V4 Pro build (0813) with 1M token context and hybrid attention for coding and agentic tasks. Served via the official DeepSeek API.
DeepSeek's generally available V4 Pro build (0813) with 1M token context and hybrid attention for coding and agentic tasks. Served via the official DeepSeek API.

DeepSeek V4 Pro is an AI model from DeepSeek, available on ZeroTwo. It costs $0.66 per million input tokens and $1.98 per million output tokens, has a 1,000,000-token context window, can return up to 384,000 output tokens.

Price
$0.66 • $1.98
Input • Output

DeepSeek's generally available V4 Pro build (0813) with 1M token context and hybrid attention for coding and agentic tasks. Served via the official DeepSeek API.

1,000,000 context window
384,000 max output tokens
Reasoning token support
Pricing
Pricing is based on the number of tokens used. For tool-specific models, like search and computer use, there's a fee per tool call. See details in the pricing page.

Listed rates are off-peak; peak hours are 2× per DeepSeek pricing.

Text tokens
Per 1M tokens
∙
Batch API price
Input
$0.66
Cached input
Output
$1.98
Quick comparison
Input
Cached input
Output
DeepSeek V4 Pro
$0.66

Questions

How much does DeepSeek V4 Pro cost?

DeepSeek V4 Pro is priced at $0.66 per million input tokens and $1.98 per million output tokens. On ZeroTwo it is included in your plan's credits rather than billed per token.

What is DeepSeek V4 Pro's context window?

DeepSeek V4 Pro accepts up to 1,000,000 tokens of context and can return up to 384,000 output tokens.

Can I use DeepSeek V4 Pro for free?

You can try DeepSeek V4 Pro on ZeroTwo's free plan, which includes a monthly credit allowance across every model in the catalogue. Heavier use moves to a paid plan rather than a per-token bill.