Your first API call

One endpoint. Your choice of model. Get started with Avenrix’s OpenAI-compatible gateway.

Integration example. Confirm your model access and API key with Avenrix before making production requests.

1. Confirm developer access

Contact Avenrix developer support to confirm the API endpoint, available model routes and access credentials. Keep keys on your server and out of client bundles and source control.

2. Send a request

curl https://avenrix.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_AVENRIX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-3-5-sonnet",
    "messages": [{"role":"user","content":"Hello from Avenrix"}]
  }'

The model ID above is the requested integration example; current availability must be confirmed with Avenrix.

3. Bring your SDK

All OpenAI-compatible SDKs work by simply changing base_url to https://avenrix.ai/v1.

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AVENRIX_API_KEY"],
    base_url="https://avenrix.ai/v1",
)

Use the SDK version and features supported by your selected model route. Provider-specific features may differ.

Architecture

Single Gateway → Model Routing → Compute Pool → Agent Engine

flowchart LR
    A[Single Gateway] --> B[Model Routing]
    B --> C[Compute Pool]
    C --> D[Agent Engine]

Authentication →