DeepSeek V4 Pro 0813 (batch)

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

ChatDeepSeek1M tokens$1.4389 / $4.3166 · 1M

deepseek/deepseek-v4-pro-0813:batch

Context
1M tokens
Completion cap
943,718
Tools
Yes
JSON
Yes
Released
2026-08-12

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v4-pro-0813:batch",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is DeepSeek V4 Pro 0813 (batch)?
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro. DeepSeek V4 Pro 0813 (batch) runs on the Geek Hub API (OpenAI-compatible). Model id: deepseek/deepseek-v4-pro-0813:batch.
Is DeepSeek V4 Pro 0813 (batch) free?
No. Input is $1.4389 per 1M tokens and output is $4.3166 per 1M tokens on Geek Hub (markup included).
What is the context length of DeepSeek V4 Pro 0813 (batch)?
DeepSeek V4 Pro 0813 (batch) has a 1M tokens context window. It supports up to 943,718 completion tokens.
Does DeepSeek V4 Pro 0813 (batch) support tool calling and structured outputs?
DeepSeek V4 Pro 0813 (batch) accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
When was DeepSeek V4 Pro 0813 (batch) released?
DeepSeek V4 Pro 0813 (batch) was released on 2026-08-12.

More models from DeepSeek