DeepSeek V4 Pro 0813

deepseek/deepseek-v4-pro-0813

DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.

InputText
OutputText
Input / Outputclub$1.3992 / $4.1976per 1M tokens · USD
Context window1Mtoken
Maximum output384Ktoken

Pricing

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

Pricing
UsagePricing
InputUS$1.3992/ 1M token
Cache readUS$0.04664/ 1M token
OutputUS$4.1976/ 1M token

Membership and model usage are billed separately. Compare plans

Capabilities

Input
Text
Output
Text
Context window
1,048,576 token
Maximum output
384,000 token
Reasoning
max · high · low

Providers

Model supply available through Vecbase.

Via OpenRouter

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

Frequently asked questions

What is DeepSeek V4 Pro 0813, and who develops it?

DeepSeek V4 Pro 0813 is a model from DeepSeek. Its model ID on Vecbase is deepseek/deepseek-v4-pro-0813. DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.

How much does DeepSeek V4 Pro 0813 cost on Vecbase?

For DeepSeek V4 Pro 0813, the Club plan lists USD 1.3992 per 1 million input tokens and USD 4.1976 per 1 million output tokens, as of 10/22/2026, 9:28:00 PM 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 0813’s context window?

DeepSeek V4 Pro 0813 has a context window of 1,048,576 tokens. Input and output must fit within the limits of the API you use.

What is the maximum output length for DeepSeek V4 Pro 0813?

DeepSeek V4 Pro 0813 can generate up to 384,000 tokens per response. Your API or request settings may set a lower limit.

Can DeepSeek V4 Pro 0813 call tools in an agent workflow?

Yes. DeepSeek V4 Pro 0813 supports tool calling. Your application provides the tool definitions and runs the tools the model requests.

Does DeepSeek V4 Pro 0813 support structured outputs?

Yes. DeepSeek V4 Pro 0813 supports structured output. Set the required format in your API request and check the returned data before using it.

Which input and output formats does DeepSeek V4 Pro 0813 support?

DeepSeek V4 Pro 0813 accepts Text and produces Text.

Which providers make DeepSeek V4 Pro 0813 available through Vecbase?

Vecbase offers DeepSeek V4 Pro 0813 through OpenRouter. Availability may vary by provider.

Which model ID should an agent use to request DeepSeek V4 Pro 0813?

Use deepseek/deepseek-v4-pro-0813 as the model identifier for DeepSeek V4 Pro 0813. See Vecbase’s API documentation for authentication, required inputs and supported request formats.

Which reasoning settings are listed for DeepSeek V4 Pro 0813?

DeepSeek V4 Pro 0813 supports these reasoning levels: max, high, and low. Available options depend on your API.

What does an agent need to access DeepSeek V4 Pro 0813 through Vecbase?

To use DeepSeek V4 Pro 0813, 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 0813?

We do not yet have a confirmed release date for DeepSeek V4 Pro 0813.

Which models can I compare with DeepSeek V4 Pro 0813 on Vecbase?

You can compare DeepSeek V4 Pro 0813 with DeepSeek V4 Flash (deepseek/deepseek-v4-flash), DeepSeek V4 Pro (deepseek/deepseek-v4-pro), and DeepSeek V4 Flash 0731 (deepseek/deepseek-v4-flash-0731). Check their capabilities and prices to find the best fit for your task.