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

1# settings-model.yaml
2llm:
3  default_model: gpt-4o
4
5models:
6  - name: gpt-4o
7    type: llm
8    mode: openai
9    context_window: 128000
10    support_tools: true
11    support_reasoning: false
12    sampling_params:
13      temperature: 0.7
14
15  - name: claude-sonnet-4-20250514
16    type: llm
17    mode: openai
18    context_window: 200000
19    support_tools: true
20    support_reasoning: true
21    sampling_params:
22      temperature: 0.7
23
24  - name: grok-3
25    type: llm
26    mode: openai
27    context_window: 131072
28    support_tools: true
29    support_reasoning: false
30    sampling_params:
31      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:

1openai:
2  api_base: https://daoxe.com/v1
3  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.