diff --git a/docs/docs.json b/docs/docs.json index 2e7b990055..90f3890e6b 100644 --- a/docs/docs.json +++ b/docs/docs.json @@ -192,6 +192,7 @@ "getting-started/integration-method/hyperbolic", "getting-started/integration-method/mistral", "getting-started/integration-method/nebius", + "getting-started/integration-method/daoxe", "getting-started/integration-method/novita", { "group": "Nvidia", diff --git a/docs/getting-started/integration-method/daoxe.mdx b/docs/getting-started/integration-method/daoxe.mdx new file mode 100644 index 0000000000..f203052e53 --- /dev/null +++ b/docs/getting-started/integration-method/daoxe.mdx @@ -0,0 +1,93 @@ +--- +title: "DaoXE Integration" +sidebarTitle: "DaoXE" +description: "Connect Helicone with DaoXE, a multi-model multi-protocol AI gateway. Monitor Chat Completions traffic through Helicone Gateway with Helicone-Target-Url." +"twitter:title": "DaoXE Integration - Helicone OSS LLM Observability" +--- + +import LegacyWarning from "/snippets/legacy-provider-warning.mdx"; + + + +[DaoXE](https://daoxe.com) is a multi-model multi-protocol API gateway with an OpenAI-compatible Chat Completions endpoint at `https://daoxe.com/v1`. Use an exact model ID from your DaoXE account catalog (`GET /v1/models`). DaoXE is not available in mainland China. + +# Gateway Integration + +Use Helicone Gateway and point the target URL at DaoXE. This does **not** require a dedicated Helicone subdomain. + + + + Log into [helicone](https://www.helicone.ai) or create an account. Once you have an account, you + can generate an [API key](https://helicone.ai/developer). + + + Log into [daoxe.com](https://daoxe.com) or create an account. Generate an API key from the + [dashboard](https://daoxe.com/dashboard). + + +```bash +HELICONE_API_KEY= +DAOXE_API_KEY= +DAOXE_MODEL= +``` + + + +Point the OpenAI client at Helicone Gateway and set `Helicone-Target-Url` to DaoXE: + +``` +base_url: https://gateway.helicone.ai/v1 +Helicone-Auth: Bearer $HELICONE_API_KEY +Helicone-Target-Url: https://daoxe.com +Authorization: Bearer $DAOXE_API_KEY +``` + + + + +## Example (Python) + +```python +from openai import OpenAI +import os + +client = OpenAI( + api_key=os.environ["DAOXE_API_KEY"], + base_url="https://gateway.helicone.ai/v1", + default_headers={ + "Helicone-Auth": f"Bearer {os.environ['HELICONE_API_KEY']}", + "Helicone-Target-Url": "https://daoxe.com", + "Helicone-Target-Provider": "DaoXE", + }, +) + +resp = client.chat.completions.create( + model=os.environ["DAOXE_MODEL"], + messages=[{"role": "user", "content": "Say hello in one short sentence."}], +) +print(resp.choices[0].message.content) +``` + +## Example (cURL) + +```bash +curl https://gateway.helicone.ai/v1/chat/completions \ + -H "Authorization: Bearer $DAOXE_API_KEY" \ + -H "Helicone-Auth: Bearer $HELICONE_API_KEY" \ + -H "Helicone-Target-Url: https://daoxe.com" \ + -H "Helicone-Target-Provider: DaoXE" \ + -H "Content-Type: application/json" \ + -d '{ + "model": "'"$DAOXE_MODEL"'", + "messages": [{"role": "user", "content": "Say hello in one short sentence."}] + }' +``` + +## Notes + +- Prefer exact account model IDs from DaoXE `GET /v1/models` — do not hardcode a public model price list. +- DaoXE also exposes OpenAI Responses and Anthropic Messages for other clients; this page covers the Chat Completions path used with the OpenAI SDK. +- For domain approval / dedicated subdomain requests, contact Helicone engineering (see [Gateway approved domains](/getting-started/integration-method/gateway#approved-domains)). + +For more headers, see [Helicone Headers](/helicone-headers/header-directory). +DaoXE examples: [github.com/seven7763/DaoXE-AI](https://github.com/seven7763/DaoXE-AI)