Build model choice into your product.

Separate product logic from model access

Put the TextCortex client behind a server-side service in your application. Keep authentication, request construction and usage logging in that service so product features can share it.

The service can select a different model for each feature. A document parser, support assistant and code-review tool do not need to use the same model or generation settings.

Give customers choices you can support

Offer a curated model list rather than passing arbitrary identifiers through from the browser. Explain which models are available for each feature, and keep EU-hosted choices aligned with the customer’s requirements.

Store customer preferences in your application. Use your own authentication and authorization to decide which choices are allowed, and keep API credentials off public clients.

Measure usage at the product boundary

Associate requests with the feature and tenant that initiated them. Record the selected model, token usage and outcome without unnecessarily retaining sensitive prompts.

Use these measurements for application budgets and capacity planning. Confirm the API terms that apply to your use case before defining customer-facing pricing or service commitments.

Make your first API request

Create a TextCortex account and generate an API key in account settings. Install the OpenAI Python package on your server. Store the key in TEXTCORTEX_API_KEY and set TEXTCORTEX_MODEL to an identifier returned by GET /models.

This example keeps credentials in environment variables. The same client configuration works when you choose another supported model. Read the API reference for endpoint-specific parameters.

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["TEXTCORTEX_API_KEY"],
    base_url="https://api.textcortex.com/v1",
)

for model in client.models.list():
    print(model.id)

response = client.chat.completions.create(
    model=os.environ["TEXTCORTEX_MODEL"],
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)