Inference Providers

DaoXE

DaoXE is a multi-model, multi-protocol AI API gateway. It exposes an OpenAI-compatible endpoint at https://daoxe.com/v1, giving you access to models from multiple providers (GPT, Claude, Grok, GLM, and others) through a single API key.

Capabilities with PrivateGPT

CapabilityStatus
Model discovery (/v1/models)✅
Tokenizer endpoint (/tokenize)❌
Embeddings✅ provider-dependent
Tool / function calling✅ model-dependent
Structured output✅ model-dependent
Streaming✅
Vision / image input✅ model-dependent

Setup

1

Get a DaoXE API key

  1. Sign up at daoxe.com.
  2. Go to your dashboard and create an API key.
  3. Note the available model IDs in your account — these are the models you can use.
2

Run PrivateGPT

OPENAI_API_BASE=https://daoxe.com/v1 \
  OPENAI_API_KEY=your-daoxe-api-key \
  private-gpt serve

Store the API key in an .env file or use OPENAI_API_KEY as an environment variable to avoid exposing it in shell history.

Advanced profile example

# settings-model.yaml
llm:
  default_model: gpt-4o
models:
  - name: gpt-4o
    type: llm
    mode: openai
    context_window: 128000
    support_tools: true
    support_reasoning: false
    sampling_params:
      temperature: 0.7
  - name: claude-sonnet-4-20250514
    type: llm
    mode: openai
    context_window: 200000
    support_tools: true
    support_reasoning: true
    sampling_params:
      temperature: 0.7
  - name: grok-3
    type: llm
    mode: openai
    context_window: 131072
    support_tools: true
    support_reasoning: false
    sampling_params:
      temperature: 0.7

Run with a profile:

OPENAI_API_BASE=https://daoxe.com/v1 \
  OPENAI_API_KEY=your-daoxe-api-key \
  PGPT_PROFILES=model \
  uv run python -m private_gpt

settings.yaml override

You can also set the endpoint directly in settings.yaml instead of environment variables:

openai:
  api_base: https://daoxe.com/v1
  api_key: ${DAOXE_API_KEY:}

Notes

  • Model IDs depend on your DaoXE account plan. Check your dashboard for available models.
  • Not available in mainland China. The service is accessible from other regions worldwide.
  • DaoXE supports the OpenAI, Anthropic Messages, and other protocols — PrivateGPT uses the OpenAI-compatible endpoint.
  • Because DaoXE does not expose /tokenize, set context_window explicitly in your model profiles for accurate token management.