DeepSeek V4 Pro

deepseek/deepseek-v4-pro

DeepSeek V4 Pro reasoning model.

InputText
OutputText
Input / Outputclub$0.4611 / $0.9222per 1M tokens · USD
Context window200Ktoken
Maximum output65.5Ktoken

Pricing

Current model usage rates. Choose your plan to see its published prices.

Pricing
UsagePricing
InputUS$0.4611/ 1M token
Cache readUS$0.0038425/ 1M token
Cache writeUS$0.4611/ 1M token
Cache write · 1 hUS$0.4611/ 1M token
OutputUS$0.9222/ 1M token

Membership and model usage are billed separately. Compare plans

Capabilities

Input
Text
Output
Text
Context window
200,000 token
Maximum output
65,535 token

Providers

Model supply available through Vecbase.

deepseek

Access is subject to your account’s permissions and model availability.

Frequently asked questions

What is DeepSeek V4 Pro, and who develops it?

DeepSeek V4 Pro is a model from DeepSeek. Its model ID on Vecbase is deepseek/deepseek-v4-pro. DeepSeek V4 Pro reasoning model.

How much does DeepSeek V4 Pro cost on Vecbase?

For DeepSeek V4 Pro, the Club plan lists USD 0.4611 per 1 million input tokens and USD 0.9222 per 1 million output tokens, as of 9/15/2026, 4:36:00 AM UTC. See the pricing table for cache rates, input-length tiers and other usage types. Membership fees are separate.

How many tokens fit in DeepSeek V4 Pro’s context window?

DeepSeek V4 Pro has a context window of 200,000 tokens. Input and output must fit within the limits of the API you use.

What is the maximum output length for DeepSeek V4 Pro?

DeepSeek V4 Pro can generate up to 65,535 tokens per response. Your API or request settings may set a lower limit.

Can DeepSeek V4 Pro call tools in an agent workflow?

Yes. DeepSeek V4 Pro supports tool calling. Your application provides the tool definitions and runs the tools the model requests.

Which input and output formats does DeepSeek V4 Pro support?

DeepSeek V4 Pro accepts Text and produces Text.

Which providers make DeepSeek V4 Pro available through Vecbase?

Vecbase offers DeepSeek V4 Pro through deepseek. Availability may vary by provider.

Which model ID should an agent use to request DeepSeek V4 Pro?

Use deepseek/deepseek-v4-pro as the model identifier for DeepSeek V4 Pro. See Vecbase’s API documentation for authentication, required inputs and supported request formats.

What does an agent need to access DeepSeek V4 Pro through Vecbase?

To use DeepSeek V4 Pro, you need an authenticated account with the required permissions, sufficient balance and the relevant capability enabled. See the documentation for setup.

Is a release date available for DeepSeek V4 Pro?

We do not yet have a confirmed release date for DeepSeek V4 Pro.

Which models can I compare with DeepSeek V4 Pro on Vecbase?

You can compare DeepSeek V4 Pro with DeepSeek V4 Flash (deepseek/deepseek-v4-flash), Vecbase 1.0 Lite (vecbase-1.0-lite), and Vecbase 1.0 (vecbase-1.0). Check their capabilities and prices to find the best fit for your task.