Quick Start
Make your first orientx API call in a few minutes
orientx puts many models behind a single OpenAI-compatible endpoint. If you already have code written against the OpenAI API, you can point it at orientx by changing two things: the base URL and the API key.
| Base URL | https://api.orientx.ai/v1 |
| Auth | Authorization: Bearer <ORIENTX_API_KEY> |
| Format | OpenAI Chat Completions |
Placeholders in this guide
<MODEL_ID> stands for a model you pick from listing models. Links
written as #TODO-... are not wired up yet.
Send your first request
Create an API key
Open the console and create a key. Copy it immediately — the full value is shown only once.
Store it as an environment variable
Keep the key out of your source tree so it never reaches version control.
export ORIENTX_API_KEY="sk-..."Call the API
curl https://api.orientx.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $ORIENTX_API_KEY" \
-d '{
"model": "<MODEL_ID>",
"messages": [
{ "role": "user", "content": "In one sentence, what is an API gateway?" }
]
}'A successful call returns the standard Chat Completions shape:
{
"id": "chatcmpl-...",
"object": "chat.completion",
"model": "<MODEL_ID>",
"choices": [
{
"index": 0,
"finish_reason": "stop",
"message": {
"role": "assistant",
"content": "An API gateway is a single entry point that routes and manages requests to backend services."
}
}
],
"usage": { "prompt_tokens": 18, "completion_tokens": 21, "total_tokens": 39 }
}Use the OpenAI SDKs
Because the API follows the OpenAI schema, the official SDKs work unchanged. Set base_url and
api_key, and the rest of your code stays the same. Step-by-step: OpenAI SDK.
pip install openaiThe same two fields unlock IDEs and apps — Codex, Cursor, Continue, Aider, Open WebUI, CrewAI, and others:
Stream responses
Set stream: true to receive tokens as they are generated instead of waiting for the full
response. The stream is delivered as server-sent events and terminates with data: [DONE].
stream = client.chat.completions.create(
model="<MODEL_ID>",
messages=[{"role": "user", "content": "Write a haiku about latency."}],
stream=True,
)
for chunk in stream:
delta = chunk.choices[0].delta.content
if delta:
print(delta, end="", flush=True)List available models
GET /v1/models returns every model your key can reach. Use the id field as the model value in
your requests.
curl https://api.orientx.ai/v1/models \
-H "Authorization: Bearer $ORIENTX_API_KEY"