Your OpenAI client. A wider model catalog.

Three parts of the connection

Keep these settings on your server. The base URL already includes /v1; SDK clients append the endpoint themselves.

• Base URL: https://api.textcortex.com/v1
• Authentication: Authorization: Bearer <api_key>
• Model: an identifier returned by GET /models

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)

Use the endpoint your application needs

GET /models lists the catalog. POST /chat/completions accepts chat requests, and POST /responses provides the documented Responses interface. Review each endpoint separately when moving an existing application.

Start with a minimal request, then add streaming, tool use or structured output where the chosen model supports it. A shared request format simplifies integration while each model retains its own capabilities.

Switch models without another provider integration

Keep the client and authentication configuration in one place. Change TEXTCORTEX_MODEL to another available identifier when evaluating GPT, Claude, Gemini, Kimi, GLM, DeepSeek or MiMo.

Use the model catalog guide for model families and the inference router guide for application-level selection. EU-hosted routes are available for workloads with European inference requirements.