Divulgación: This article was written with AI assistance and reviewed by EmpirioLabs AI.
DeepSeek V4 Pro 0813 is available on EmpirioLabs. This is the official DeepSeek V4 Pro release. It keeps the Pro architecture and focuses the update on stronger agent capabilities, especially in production coding and tool-use work.
What changed in the 0813 release
The headline is the agent upgrade. DeepSeek reports major gains across coding, repository work, tool use, automation, and full-stack tasks compared with the V4 Pro preview. The model retains a 1M token context window and hybrid thinking, so applications can enable deeper reasoning for difficult work or disable thinking for lower-latency responses.
Optional Linkup web search can add recent web context through the web_search_linkup request control. Function calling is available on the same OpenAI-compatible chat surface as the rest of the catalog.
How to call DeepSeek V4 Pro 0813
Use the OpenAI-compatible chat completions endpoint and set model to deepseek-v4-pro-0813:
curl https://api.empiriolabs.ai/v1/chat/completions \
-H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"model": "deepseek-v4-pro-0813",
"enable_thinking": true,
"thinking_budget": 32768,
"messages": [
{
"role": "user",
"content": "Review this service design and return a prioritized migration plan."
}
]
}'Streaming responses include final usage data, and reasoning tokens are billed as output tokens.
Precios
Token usage is billed at one published input rate and one published output rate. Cached input receives no separate discount. See the live model page and pricing page for current rates.
Start building
Try DeepSeek V4 Pro 0813 in the Playground, read the API documentation, or compare it with other models in the model catalog.
