Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.auriko.ai/llms.txt

Use this file to discover all available pages before exploring further.

The Auriko API is OpenAI-compatible. You can use the OpenAI SDK with a base URL change.

​
Base URL

https://api.auriko.ai/v1

​
Make a request

Send a chat completion request: 
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AURIKO_API_KEY"],
    base_url="https://api.auriko.ai/v1"
)

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "What is the capital of France?"}]
)

print(response.choices[0].message.content)
To stream the response, set stream to true: 
stream = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Explain quantum computing in one paragraph."}],
    stream=True
)

for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)
To optimize for cost, add routing options: 
response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Summarize the benefits of cloud computing."}],
    extra_body={"gateway": {"routing": {"optimize": "cost"}}}
)

print(response.choices[0].message.content)

​
Endpoints

EndpointMethodDescription
/v1/chat/completionsPOSTCreate a chat completion
/v1/responsesPOSTCreate a response (Response API)
/v1/modelsGETList available models
/v1/models/{model_id}GETRetrieve a model
/v1/meGETGet API key identity
/v1/registry/providersGETList available providers
/v1/registry/modelsGETList canonical models
/v1/directory/modelsGETFull model directory with pricing
/v1/workspaces/{workspace_id}/billing/balanceGETCredit balance

​
OpenAI compatibility

Auriko supports the same request/response format as OpenAI. Switch to Auriko by changing two values:
  1. Base URL: https://api.openai.com/v1 → https://api.auriko.ai/v1
  2. API Key: Use your Auriko API key (starts with ak_)

​
Auriko extensions

Auriko responses carry additional fields beyond the OpenAI format.

​
Response extensions

Every chat completion response includes a routing_metadata object with routing and cost details: 
{
  "routing_metadata": {
    "provider": "openai",
    "provider_model_id": "gpt-4o-2024-08-06",
    "model_canonical": "gpt-4o",
    "routing_strategy": "balanced",
    "ttft_ms": 312,
    "cost": {
      "usd": 0.00015
    },
    "warnings": []
  }
}
When the gateway had to modify or ignore part of the request, warnings carries one or more structured entries: 
{
  "routing_metadata": {
    "provider": "openai",
    "provider_model_id": "gpt-4o-2024-08-06",
    "model_canonical": "gpt-4o",
    "routing_strategy": "balanced",
    "warnings": [
      {
        "type": "unsupported_parameter",
        "code": "seed",
        "message": "Parameter 'seed' is not supported by the selected provider."
      }
    ]
  }
}
See Response metadata for the full field reference.

​
Request extensions

Pass routing options to optimize your requests via the gateway field: 
{
  "model": "gpt-4o",
  "messages": [{"role": "user", "content": "Hello!"}],
  "gateway": {
    "routing": {
      "optimize": "cost",
      "max_ttft_ms": 1000
    }
  }
}

​
Request metadata

Attach custom metadata to requests for tracking and observability via gateway.metadata. Auriko strips this metadata before forwarding to the provider. 
{
  "model": "gpt-4o",
  "messages": [{"role": "user", "content": "Hello!"}],
  "gateway": {
    "metadata": {
      "tags": ["production", "chatbot"],
      "user_id": "user_abc123",
      "trace_id": "trace_xyz789",
      "custom_fields": {
        "environment": "production",
        "feature": "customer-support"
      }
    }
  }
}
FieldTypeLimits
tagsstring[]Max 100 tags, each max 50 chars
user_idstringMax 255 chars
trace_idstringMax 255 chars
custom_fieldsRecord<string, string>Max 10 fields, keys max 50 chars, values max 200 chars

​
Response headers

Every response carries custom headers. See Response headers for the full reference.

Authentication

Learn how to authenticate your requests