DeepSeek V4 Pro 0813 API
DeepSeek V4 Pro 0813 is the capacity-first model in the DeepSeek V4 line, and remains a separate option from V4.1 Flash. DeepSeek's release notes highlight stronger Agent performance, native OpenAI Responses API support with Codex integration, and low/high/max thinking levels for matching effort to task complexity.
Official source: model page · verified 2026-10-22
Pricing
Prices can change with upstream providers; the rate at settlement is authoritative.
Call the API
Use the OpenAI-compatible endpoint; no model-specific SDK setup is required.
curl https://api.kimiseek.app/v1/chat/completions \
-H "Authorization: Bearer $KIMISEEK_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4-pro-0813",
"messages": [{"role": "user", "content": "Hello from KimiSeek"}]
}'Where it fits
Best for
- Long-running agent workflows with a large output budget
- Codex and OpenAI Responses API integrations
- Multi-step analysis and long-form technical deliverables
Tradeoffs
- Peak and off-peak token rates are higher than the V4.1 Flash tier
- More capacity than short chat, routing or bulk classification usually needs
Model details
FAQ
Is DeepSeek V4 Pro 0813 still available?
Yes. As of the latest official verification it remains a separate model in this deployment; V4.1 Flash is a different option. Check the live catalog before depending on availability for a new production workflow.
What API capabilities does V4 Pro add?
DeepSeek's release notes list native OpenAI Responses API support, Codex integration, and low/high/max thinking levels.
How do I call this model?
Use KimiSeek's OpenAI-compatible API and set the model field to deepseek-v4-pro-0813 with your KimiSeek API key.