DeepSeek V4 Pro

by DeepSeek

DeepSeek V4 Pro 0813 is a 1.7T-parameter open-weight model for complex coding work. A common setup is to use Pro for the main agent and V4 Flash 0731 for sub-agents. This keeps the whole coding workflow on open-weight models and can cost less than using closed frontier models.

Best for: A main coding agent paired with DeepSeek V4 Flash sub-agents.

1M context

Text
Reasoning
Tool use

Model weights

Try it in the playground

Pricing

USD per 1M tokens.

Window	Input	Cached input	Output
asap	$1.04	$0.04	$2.08

What one request costs

Prompt94Ktokens

Cached prefix66Ktokens

Reply2Ktokens

$0.0348

per request to DeepSeek V4 Pro

Prompt: 84.4%
Cached: 6.7%
Reply: 9%

The same request, across other models