Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions docs.json
Original file line number Diff line number Diff line change
Expand Up @@ -166,6 +166,7 @@
"openhands/usage/llms/openhands-llms",
"openhands/usage/llms/aws-bedrock",
"openhands/usage/llms/azure-llms",
"openhands/usage/llms/daoxe",
"openhands/usage/llms/google-llms",
"openhands/usage/llms/groq",
"openhands/usage/llms/local-llms",
Expand Down
48 changes: 48 additions & 0 deletions openhands/usage/llms/daoxe.mdx
Original file line number Diff line number Diff line change
@@ -0,0 +1,48 @@
---
title: DaoXE
description: Use DaoXE as an OpenAI-compatible multi-model multi-protocol API gateway with OpenHands via LiteLLM.
---

## Overview

[DaoXE](https://daoxe.com) is a multi-model multi-protocol API gateway. OpenHands talks to LLMs through LiteLLM, so you can point OpenHands at DaoXE with an OpenAI-compatible base URL and your DaoXE API key.

DaoXE exposes OpenAI Chat Completions (and other protocols such as OpenAI Responses and Anthropic Messages for other clients). This page covers the OpenAI-compatible path that OpenHands uses.

DaoXE is not available in mainland China. Use an exact model ID from your DaoXE account catalog rather than a hard-coded public list.

## Configuration (UI)

When running OpenHands, set the following under **Settings → LLM**:

1. Enable **Advanced** options.
2. Set:
- **Custom Model** to `openai/<your-exact-daoxe-model-id>` (LiteLLM OpenAI-compatible form), for example `openai/YOUR_DAOXE_MODEL_ID`
- **Base URL** to `https://daoxe.com/v1`
- **API Key** to the key created in your [DaoXE dashboard](https://daoxe.com)

If a built-in provider dropdown entry for DaoXE is not present, the Advanced custom model + base URL path is the supported integration.

## Configuration (`config.toml`)

```toml
[llm]
# LiteLLM OpenAI-compatible model string; replace with an exact ID from your DaoXE account
model = "openai/YOUR_DAOXE_MODEL_ID"
api_key = "YOUR_DAOXE_API_KEY"
base_url = "https://daoxe.com/v1"
```

Discover model IDs with `GET https://daoxe.com/v1/models` (authorized with your key) or from the live catalog in your DaoXE account / [pricing page](https://daoxe.com/pricing) for discovery only.

## Notes

- Prefer tool-capable models from your account when you need agent tool use.
- Requests may be billed by DaoXE.
- Examples and client setup: [DaoXE-AI](https://github.com/seven7763/DaoXE-AI)

## See also

- [OpenAI / OpenAI-compatible endpoints](./openai-llms)
- [Custom LLM configurations](./custom-llm-configs)
- [LiteLLM OpenAI-compatible providers](https://docs.litellm.ai/docs/providers/openai_compatible)