DaoXEDaoXE is OpenAI-compatible with a single base URL (https://daoxe.com/v1) and native Anthropic Messages for Claude Code, so most tools need only a base-URL-and-key change. This hub links every integration guide, every model-family guide, and the honest gateway comparisons. Not sure where to start? Use the decision table — and always detect model swapping so a cheaper endpoint can't quietly downgrade you.
Editors & CLI agents#
One page per tool — real, tool-specific setup and caveats, not a copy-paste template:
- Cursor — Cursor via Override OpenAI Base URL + custom models.
- Cline — Cline via the OpenAI Compatible provider.
- Roo Code — Roo Code via OpenAI Compatible, per-mode models.
- Continue — Continue via config.yaml apiBase.
- Aider — Aider via OPENAI_API_BASE + openai/ prefix.
- Zed — Zed via language_models.openai_compatible.
- opencode — opencode via a custom provider in opencode.json.
- Cherry Studio — Cherry Studio via an OpenAI-type provider.
- Open WebUI — Open WebUI via an OpenAI API connection.
- goose — goose via the OpenAI provider's custom host.
- Kilo Code — Kilo Code via the OpenAI Compatible provider.
- n8n — n8n via the OpenAI credential's Base URL.
- LobeChat — LobeChat via a custom OpenAI-compatible endpoint.
- Chatbox — Chatbox via Custom Provider (API host + key).
- NextChat — NextChat via endpoint override or OPENAI_BASE_URL.
- Obsidian Copilot — Obsidian Copilot via BYOK custom provider.
- Raycast AI — Raycast AI via Custom Providers (providers.yaml).
- Text Generator — Text Generator via custom OpenAI-compatible endpoint.
- AnythingLLM — AnythingLLM via the OpenAI (Generic) provider.
- SillyTavern — SillyTavern via the Custom (OpenAI-compatible) source.
- Dify — Dify via the OpenAI-API-compatible provider.
- LibreChat — LibreChat via endpoints.custom in librechat.yaml.
- gptel — gptel via gptel-make-openai (:host + :endpoint).
- Jan — Jan via Add Provider (OpenAI-compatible).
- Msty — Msty via Remote Model Providers (Open AI Compatible).
- BoltAI — BoltAI via Settings → Models (OpenAI-compatible Server).
- TypingMind — TypingMind via Add Custom Model (OpenAI API type).
- Crush — Crush via provider add (openai-compat).
- gptme — gptme via a [[providers]] block (base_url + api_key_env).
- OpenHands — OpenHands via Settings → LLM → Advanced (openai/ prefix).
- OpenClaw — OpenClaw via models.providers in openclaw.json.
By model family#
Reach a specific model family through your one key — with the real per-model quirks:
- Claude — Claude via OpenAI chat + native Anthropic Messages.
- GPT — GPT via chat + Responses; drop-in OpenAI SDK.
- Gemini — Gemini via /v1/chat/completions; no Google key needed.
- DeepSeek — DeepSeek via /v1/chat/completions; mind reasoning_content.
- Kimi (Moonshot) — Kimi via /v1/chat/completions; a per-generation reasoning contract.
- Qwen — Qwen via /v1/chat/completions; mind enable_thinking.
- Doubao — Doubao via /v1/chat/completions; catalog ID, no ep- setup.
- GLM — GLM via OpenAI-compatible chat; no separate Zhipu account.
- MiniMax — MiniMax via OpenAI-compatible chat; no separate console.
- Grok — Grok via OpenAI-compatible chat; no xAI console needed.
- Mistral — Mistral via OpenAI-compatible chat; reasoning_effort, shape-shifting content.
- MiMo — MiMo via OpenAI-compatible chat; thinking defaults ON, locked sampling.
Compare & decide#
Honest, verifiable head-to-heads and cost guides:
- DaoXE vs OpenRouter — OpenRouter — broad hosted multi-provider router.
- DaoXE vs LiteLLM — LiteLLM — self-hosted OpenAI-compatible proxy.
- DaoXE vs One API / New API — One API / New API — self-hosted relay & key-management panels.
- cost vs official APIs
- OpenRouter alternative
- cheapest APIs guide
- gateway benchmark guide
- detect model swapping
Which path should I take?#
Pick the shortest path to what you actually want to do:
| You want… | Best DaoXE path | Guide |
|---|---|---|
| An autonomous coding agent in VS Code | Cline, Roo Code or Kilo Code via OpenAI Compatible | Open guide |
| Cursor running your own models | Override OpenAI Base URL + custom model IDs | Open guide |
| Native Claude Code | Anthropic Messages via the host-root base URL | Open guide |
| Terminal pair-programming | Aider with OPENAI_API_BASE + an openai/ model | Open guide |
| A single config-file IDE assistant | Continue via config.yaml roles | Open guide |
| A local multi-provider desktop chat | Cherry Studio as an OpenAI provider | Open guide |
| A self-hosted team chat UI | Open WebUI via an OpenAI connection | Open guide |
| A local-first agent that runs on your machine | goose via the OpenAI provider's custom host | Open guide |
| LLM calls inside n8n automations | One OpenAI credential's Base URL, per-node models | Open guide |
| A desktop chat app (no server) | Chatbox or NextChat via a custom endpoint | Open guide |
| AI inside your notes vault | Obsidian Copilot's BYOK custom provider | Open guide |
| AI in a macOS launcher, everywhere | Raycast Custom Providers via providers.yaml | Open guide |
| Template-driven AI over notes | Obsidian Text Generator, full endpoint path | Open guide |
| Chat over your own documents | AnythingLLM via OpenAI (Generic) | Open guide |
| Roleplay & character-chat workflows | SillyTavern via Custom (OpenAI-compatible) | Open guide |
| Build LLM apps, workflows & agents | Dify via the OpenAI-API-compatible provider | Open guide |
| A self-hosted multi-model chat UI by config file | LibreChat via endpoints.custom | Open guide |
| An LLM client inside Emacs | gptel via gptel-make-openai | Open guide |
| Local models and cloud APIs in one desktop app | Jan via Add Provider (OpenAI-compatible) | Open guide |
| Local models and cloud APIs on a Mac, plus Msty workspaces | Msty via Remote Model Providers (Open AI Compatible) | Open guide |
| AI across all of macOS — inline, commands and chat | BoltAI via the OpenAI-compatible Server provider | Open guide |
| A BYOK chat UI that lives entirely in the browser | TypingMind via Add Custom Model (OpenAI type) | Open guide |
| A terminal coding agent on your own models | Crush via provider add (openai-compat) | Open guide |
| An open-source agent loop in your terminal | gptme via a [[providers]] block | Open guide |
| An autonomous engineer that opens its own PRs | OpenHands via Settings → LLM → Advanced | Open guide |
| A personal AI assistant across your chat channels | OpenClaw via models.providers in openclaw.json | Open guide |
| The cheapest access to a given model | Start from the model-family guide | Open guide |
| To compare gateways honestly | DaoXE vs OpenRouter / LiteLLM / One-API | Open guide |
Verify us — don't trust us
Point the open benchmark at DaoXE and at the official API and compare at temperature 0. Then learn to detect model swapping so a cheaper endpoint can't quietly swap you to a smaller model.
Frequently asked questions#
What's the fastest way to start?
Find your tool in the editors list or the decision table, set the base URL to https://daoxe.com/v1 and paste your key. Most tools need nothing more.
Which tools support native Claude Code?
Claude Code uses native Anthropic Messages — see the Claude model guide and the Cursor & Claude Code guide. Point ANTHROPIC_BASE_URL at the host root.
How do I make sure I get the real model?
Benchmark the same prompt against the official API at temperature 0, and learn to detect model swapping. A cheaper endpoint is only a saving if it serves the real model.
Can one key drive several tools at once?
Yes — the same DaoXE key works across every integration here, on one balance. Top-up is a flat 1 RMB = $1 of credit on every payment method.
Do reasoning models expose their thinking the same way?
No — and that's worth checking before you build. GLM spends the same max_tokens on thinking and answer, DeepSeek returns a separate reasoning_content field, MiniMax needs an explicit reasoning_split flag. Each model page in this cluster documents its exact mechanism.
Try DaoXE — and benchmark it yourself
One key for GPT, Claude, Gemini, DeepSeek and more. Point the open benchmark at us and compare — don't take our word for it.