The DeepSeek Provider supports querying DeepSeek language models for prompt-based interactions.

​
Inputs

The DeepSeek Provider supports the following functions:

  • prompt: Interact with DeepSeek’s models by sending prompts and receiving responses
  • model: The model to be used, defaults to deepseek-reasoner
  • max_tokens: Limit amount of tokens returned by the model, default 1024
  • system_prompt: Optional system prompt to guide the model’s behavior
  • structured_output_format: Optional JSON format for the structured output (check examples at the GitHub)

​
Outputs

Currently, the DeepSeek Provider outputs the response from the model based on the prompt provided.

​
Authentication Parameters

To use the DeepSeek Provider, you’ll need an API Key from DeepSeek. The required parameters for authentication are:

  • api_key (required): Your DeepSeek API Key.

​
Connecting with the Provider

To connect to DeepSeek, you’ll need to obtain an API Key:

  1. Sign up for an account at DeepSeek
  2. Navigate to your account settings
  3. Generate an API key for Keep

Use the generated API key in the authentication section of your DeepSeek Provider configuration.

Datadog ProviderDiscord Provider