Deepseek

--- title: "DeepSeek Provider" description: "Configure DeepSeek V4 in Aurora and understand how reasoning effort is mapped to DeepSeek's reasoning_effort field." icon: "brain" ---

Aurora routes to DeepSeek through DeepSeek's chat completions API. DeepSeek does not expose a native Responses API, so Aurora translates /v1/responses requests to /chat/completions automatically.

1. Configure DeepSeek

Env-only is enough:

export DEEPSEEK_API_KEY="..."

Or in config.yaml (not recommended):

providers:
  deepseek:
    type: deepseek
    base_url: "https://api.deepseek.com"
    api_key: "${DEEPSEEK_API_KEY}"

2. Reasoning effort mapping

DeepSeek V4 reasoning models accept reasoning_effort as a top-level string with two levels: high and max. Aurora accepts the standard OpenAI-style levels and remaps them:

low and medium are mapped up to high because DeepSeek's reasoning models do not accept lower levels. If you want to avoid reasoning entirely, omit the reasoning field instead of passing low.

Aurora rewrites the request body so DeepSeek sees a top-level reasoning_effort: "..." instead of OpenAI's nested "reasoning": {"effort": "..."} shape. No client change is required.

Current support

Integrated:

• chat completions and streaming
• Responses API and streaming (translated to chat completions)
• model listing through /models

Not supported by DeepSeek:

• embeddings (returns an invalid_request_error)