Augure API

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

Parameters

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

Images and documents

content can also be an array of parts. Alongside text parts, a user message may carry image_url parts (PNG, JPEG, WebP or GIF as a base64 data URL) and file parts (a PDF as a base64 data URL). PDFs are read on the gateway: the text layer is extracted directly, and scanned documents are OCR’d automatically. Send the PDF itself rather than rendering it to an image; you keep the exact text, and it works with every model.

curl -X POST https://api.augureai.ca/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "ossington-5",
    "messages": [{
      "role": "user",
      "content": [
        {"type": "text", "text": "Extract the invoice number, date, vendor and total as JSON."},
        {"type": "file", "file": {
          "filename": "invoice-2041.pdf",
          "file_data": "data:application/pdf;base64,JVBERi0xLjQK..."
        }}
      ]
    }]
  }'

import base64
from openai import OpenAI

client = OpenAI(api_key="YOUR_API_KEY", base_url="https://api.augureai.ca/v1")
pdf = base64.b64encode(open("invoice-2041.pdf", "rb").read()).decode()

response = client.chat.completions.create(
    model="ossington-5",
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "Extract the invoice number, date, vendor and total as JSON."},
            {"type": "file", "file": {
                "filename": "invoice-2041.pdf",
                "file_data": f"data:application/pdf;base64,{pdf}",
            }},
        ],
    }],
)
print(response.choices[0].message.content)

Each PDF may be up to 25 MB and 200 pages, within the 35 MB request body. A file part also accepts spreadsheets (.xlsx or .csv data URLs, first 100 rows of each sheet). Images are read by our vision engine and handed to the model as text; add "augure_ocr": true to an image_url part for a verbatim OCR transcription with no description. The gateway keeps no copy of a file once the request completes.

Example Request

curl -X POST https://api.augureai.ca/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "ossington-5",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "What is the Civil Code of Quebec?"}
    ]
  }'

Example Response

{
  "id": "chatcmpl-a9adf17e-5ff3-4804-b01e-f7cbd30ae996",
  "object": "chat.completion",
  "created": 1771286577,
  "model": "ossington-5",
  "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]. Add "stream_options": {"include_usage": true} to receive a final chunk carrying the usage object (with empty choices) just before it.

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-3",
    "messages": [{"role": "user", "content": "Hello"}],
    "stream": true
  }'

Usage and cost

Every response carries a usage object with prompt_tokens, completion_tokens and total_tokens; multiply by the per-model rates above to price a call. Your developer dashboard shows the same numbers per model, per day and per key, with the cost in CAD at the published rates. Text extracted from an attached PDF counts toward prompt tokens like any other input.