Developer Documentation

Augure API

OpenAI-compatible chat completions API on sovereign Canadian infrastructure. No US exposure. No CLOUD Act.

Base URL: https://api.augureai.ca

🍁

Data Routing & Residency

All API requests enter through our gateway on OVHcloud infrastructure in Beauharnois, Quebec. Inference runs on sovereign infrastructure with no US parent company in the stack — no data touches US infrastructure at any point. Ossington 4 runs on Canadian GPU infrastructure (Denvr, Calgary). Prompts are encrypted in transit (TLS 1.2+), never logged by Augure, and never used for model training.

Canadian gatewaySovereign inferenceNo US exposureNo prompt logging

Authentication

All API endpoints require a Bearer token. Include your API key in the Authorization header of every request.

Example

curl https://api.augureai.ca/v1/models \
  -H "Authorization: Bearer YOUR_API_KEY"

Getting a key: API keys are issued through our gated application process. Apply for access to get started.

Models

Three models are available, optimized for different workloads.

ossington-4

Large model, highest capability

Complex reasoning, legal analysis, document review

tofino-2.5

Fast, efficient small model

Chat, summaries, quick tasks

augure-nano

Compact 8B model

Classification, extraction, simple tasks

OpenAI compatibility: The aliases gpt-4, gpt-4o, gpt-4o-mini, and gpt-3.5-turbo are supported for drop-in compatibility with OpenAI client libraries. They map to ossington-4 and tofino-2.5 respectively.

Endpoints

POST/v1/chat/completions

Create a chat completion. Accepts the same request format as the OpenAI chat completions endpoint.

Parameters

Field	Type	Required	Description
model	string	Yes	Model ID (see Models above)
messages	array	Yes	Array of message objects
stream	boolean	No	Stream response via SSE. Default: false
temperature	number	No	Sampling temperature (0.0–2.0)
max_tokens	number	No	Max tokens to generate (up to 32,768)
top_p	number	No	Nucleus sampling threshold
stop	string \| array	No	Stop sequence(s)

Each message in the messages array has a role ("system", "user", or "assistant") and a content string.

Example Request

curl

curl -X POST https://api.augureai.ca/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "ossington-4",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "What is the Civil Code of Quebec?"}
    ]
  }'

Example Response

Response

{
  "id": "chatcmpl-a9adf17e-5ff3-4804-b01e-f7cbd30ae996",
  "object": "chat.completion",
  "created": 1771286577,
  "model": "ossington-4",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The Civil Code of Quebec (Code civil du Québec) is..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 24,
    "completion_tokens": 150,
    "total_tokens": 174
  },
  "_augure": {
    "gateway_region": "ca-montreal-1",
    "inference_region": "augure-cloud",
    "request_id": "a9adf17e-5ff3-4804-b01e-f7cbd30ae996"
  }
}

Streaming

Set "stream": true to receive Server-Sent Events. Each event is a JSON chunk with a delta object containing incremental content. The stream ends with data: [DONE].

Streaming request

curl -N -X POST https://api.augureai.ca/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tofino-2.5",
    "messages": [{"role": "user", "content": "Hello"}],
    "stream": true
  }'

GET/v1/models

Returns a list of all available models.

curl

curl https://api.augureai.ca/v1/models \
  -H "Authorization: Bearer YOUR_API_KEY"

Response

{
  "object": "list",
  "data": [
    { "id": "ossington-4",  "object": "model", "owned_by": "augure" },
    { "id": "tofino-2.5",   "object": "model", "owned_by": "augure" },
    { "id": "augure-nano",  "object": "model", "owned_by": "augure" }
  ]
}

Client Libraries

Use any OpenAI-compatible SDK. Just point it to https://api.augureai.ca/v1 as the base URL.

Python

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.augureai.ca/v1"
)

response = client.chat.completions.create(
    model="ossington-4",
    messages=[
        {"role": "user", "content": "Explain Quebec privacy law"}
    ]
)
print(response.choices[0].message.content)

JavaScript / TypeScript

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "YOUR_API_KEY",
  baseURL: "https://api.augureai.ca/v1",
});

const response = await client.chat.completions.create({
  model: "tofino-2.5",
  messages: [{ role: "user", content: "Summarize PIPEDA" }],
});
console.log(response.choices[0].message.content);

Limits

Request body

2 MB max

Messages per request

256 max

Max output tokens

32,768

Request timeout

300 seconds

Token quotas are applied per API key. Contact us if you need higher throughput for production workloads.

Errors

All errors return a JSON object with an error field, matching the OpenAI error format.

Error response

{
  "error": {
    "message": "Invalid API key provided",
    "type": "invalid_request_error",
    "param": null,
    "code": "invalid_api_key"
  }
}

Status	Meaning
401	Missing or invalid API key
400	Malformed request or missing required fields
404	Unknown model or endpoint
413	Request body exceeds 2 MB
429	Token quota exceeded for this API key
502	Upstream processing error — retry shortly

Ready to integrate?

Get your API key and start building with Augure.

Apply for API Access