Deepseek v4 Pro-0813 API Pricing Calculator

DeepSeek V4 Pro 0813 is a flagship open-weight reasoning model built for advanced coding, autonomous agents, mathematics, scientific research, and complex problem-solving.

Deepseek v4 Pro-0813 is a reasoning model from DeepSeek, released 12 August 2026. It pairs a 1,048,576-token context window with up to 384,000 tokens of output, accepting text and returning text. Step-by-step reasoning is supported. It costs $1.32 per million input tokens through Perplexity.

Last updated Oct 18, 2026

Never miss an AI pricing or launch update

Get notified about new model launches, pricing changes, provider updates, deprecations, and cost-saving insights.

🔒 We respect your privacy. Unsubscribe anytime.

Model Details

Released
Aug 12, 2026
Context Length
1,048,576
Max Output
384,000
Modalities
Text → Text
Capabilities
Tool use Structured outputs Prompt caching Code execution Open weights
Hugging Face
deepseek-ai/DeepSeek-V4-Pro-0813 on Hugging Face (opens in a new tab)

Where is Deepseek v4 Pro-0813 a perfect fit?

DeepSeek V4 Pro 0813 combines a trillion-parameter mixture-of-experts architecture, one-million-token context, flexible reasoning effort, and speculative decoding to improve agentic coding, research, and production workflows. It is a perfect fit for:
- Autonomous coding agents and complex software engineering
- Large-codebase analysis and refactoring
- Mathematical and scientific reasoning
- Multi-step research and investigation
- Long-context document analysis
- Enterprise agent workflows
- Tool-using applications and automation
- Self-hosted frontier-model deployments

Quick Model Estimate

(USD 1.3200 per 1M tokens)
(USD 3.9600 per 1M tokens)

Your Deepseek v4 Pro-0813 Cost Estimate

💰 Total Cost

—

for 1000 input + 1000 output tokens

📥 Input (1000 × $1.320000) —
📤 Output (1000 × $3.960000) —

Cost Breakdown

📥 Input 📤 Output

Prices are watched for changes and checked against the provider's own page.

Pricing

Provider ↕
Modality ↕
Service Tier ↕
Input Price
(per 1M tokens) ↕
Output Price
(per 1M tokens) ↕
Cached Input
(per 1M tokens) ↕
Context Size ↕
View
Perplexity LogoPerplexityTextStandard$1.3200$3.9600$0.04401,048,576 tokens→

Other Models in the DeepSeek v4 Family

DeepSeek v4 Flash-0731

Active

Reasoning · 1,048,576 context

FAQs about Deepseek v4 Pro-0813

How much does Deepseek v4 Pro-0813 cost per 1M tokens?

Deepseek v4 Pro-0813 costs $1.32 per million input tokens, and $3.96 per million output tokens.

What does a typical workload cost with Deepseek v4 Pro-0813?

1,000 requests of 2,000 input and 500 output tokens each — 2,000,000 input and 500,000 output tokens in total — costs $4.62 with Deepseek v4 Pro-0813 at its lowest rates. Use the calculator on this page for your own volumes.

Where can I use Deepseek v4 Pro-0813?

Deepseek v4 Pro-0813 is available through Perplexity, from $1.32 per million input tokens.

What is Deepseek v4 Pro-0813's context window?

Deepseek v4 Pro-0813 has a context window of 1,048,576 tokens, and returns up to 384,000 tokens in a single response.

What input types does Deepseek v4 Pro-0813 support?

Deepseek v4 Pro-0813 accepts text input, and returns text.