All your models. One API.

A full model catalog behind one integration

Use GPT, Claude and Gemini alongside Kimi K3, GLM-5.3, DeepSeek, MiMo and other supported models. Your application connects to TextCortex instead of maintaining a separate integration for every model family.

Change the model identifier for a request to compare answers, power a different feature or introduce a new model into your product. Your account catalog is available through GET /models.

Route requests around your application

A support response, a code review and a classification step can use different models. Define the selection in your application and send each request through the same API. Measure quality, latency and token usage against the task.

Start with explicit model choices so behavior is predictable. If you need automatic selection or failover, use only the routing controls documented for your configuration.

EU-hosted endpoints for European workloads

Use the deployment that matches your processing requirements. The EU model pages cover European hosting; other models in the wider catalog can have different processing arrangements.

• Kimi K3 EU-hosted API
• GLM-5.3 EU-hosted API
• DeepSeek EU-hosted API
• MiMo EU-hosted API

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)

From a first request to production

Use the OpenAI-compatible API guide to connect your application. Then define the model choices, request limits and error handling your product needs.

Compare costs with the API cost calculator and use the routing guide to organize a multi-model integration.