Skip to main content

DeepSeek

proxium calls DeepSeek with your own DeepSeek key. Your applications send their requests to proxium with a proxium virtual key. They never hold the DeepSeek key.

SettingValue
Preset iddeepseek
Base URLhttps://api.deepseek.com/v1
How proxium sends the keyan Authorization: Bearer header
Request formatthe OpenAI Chat Completions format
Request typechat

Add DeepSeek to a project​

  1. Get a key from DeepSeek at platform.deepseek.com/api_keys.
  2. In the console, open Providers and select Add a vendor.
  3. In What are you adding, select DeepSeek. proxium fills in the base URL and the models.
  4. Paste the key into API key, and select Add DeepSeek.

proxium stores the key encrypted with AES-256-GCM. The console does not show the key again.

Models​

A new DeepSeek vendor starts with these models. You can change the list on the Providers screen.

  • deepseek-chat
  • deepseek-reasoner

Call a model​

A vendor that you add has the provider id t.<project>.deepseek, where <project> is the project slug. Send GET /v1/models to get the exact ids that your key can use.

curl https://proxium.tech/v1/chat/completions \
  -H "Authorization: Bearer $PROXIUM_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "t.<project>.deepseek/deepseek-chat", "messages": [{"role": "user", "content": "Hello"}]}'

You can also send a tier name, such as trial, in model. proxium then picks the model from the routing policy of the project. Refer to Routing.