deepseek-v4-pro-0813 — API, Pricing & Context Window | Vivgrid

deepseek-v4-pro-0813 is the 0813 release of DeepSeek's flagship coding model. It keeps the line's standout 1M-token context window and unusually large 384K-token max output, and lands at a lower price than deepseek-v4-pro — $1.35 per 1M input tokens, $0.05 cached, and $3.00 output.

It is a separate model id, not an in-place upgrade: deepseek-v4-pro stays available and unchanged, so you can pin either one.

On Vivgrid, deepseek-v4-pro-0813 is available through the unified, OpenAI-compatible endpoint, so you can route DeepSeek alongside OpenAI, Anthropic, and Google models with a single API key.

Specifications

Pricing

Pricing in USD per 1M tokens, matching the provider's rates.

Quick start

Call deepseek-v4-pro-0813 through Vivgrid's unified, OpenAI-compatible endpoint. Get an API key from the Vivgrid Console.

curl https://api.vivgrid.com/v1/chat/completions \
  -H "Authorization: Bearer $VIVGRID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-pro-0813",
    "messages": [
      { "role": "user", "content": "Say hello in English, Chinese and Spanish." }
    ],
    "stream": true
  }'

Ideal use cases

• Cost-effective coding agents needing very long context
• Tasks that generate large outputs (up to 384K tokens)
• Whole-repository reasoning and refactoring
• High-volume engineering workloads on a budget

Related models

• deepseek-v4-pro — the prior flagship release
• deepseek-v4-flash (0731) — faster, cheaper V4 sibling
• deepseek-v4-flash-vision-exp — multimodal DeepSeek sibling