Documentation
Quickstart
Make your first API call to a Canadian-hosted Singulus model in under 60 seconds.
curl https://api.singulus.ai/v1/chat/completions \
-H "Authorization: Bearer $SINGULUS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "singulus-1-pro",
"messages": [{"role": "user", "content": "Explain sovereign AI in one sentence."}]
}'- 1
Get an API key
Sign up and create a key in the Singulus console. Keys are scoped, rotatable, and tied to your Canadian-region project.
- 2
Install the SDK
Use our official Python, TypeScript, or Go client — or call the REST API directly. Everything is OpenAI-spec compatible for easy migration.
- 3
Make a request
Point your request at api.singulus.ai/v1 and you'll be served from Canadian infrastructure with zero data retention.
POST/v1/chat/completions
Generate a chat completion from one of our instruction-tuned models. OpenAI-compatible request and response shape.
Request parameters
| Name | Type | Required | Description |
|---|---|---|---|
| model | string | Yes | Model ID, e.g. singulus-1-pro. |
| messages | array | Yes | Conversation history as an array of role/content objects. |
| temperature | number | No | Sampling temperature. Default 0.7. |
| max_tokens | integer | No | Maximum tokens to generate. Defaults to model limit. |
| stream | boolean | No | If true, returns server-sent events. |
| tools | array | No | Function/tool schemas for tool-calling. |