Every model family. One place to connect.

Proprietary model families

Bring leading proprietary models into the same integration as your open-weight choices. Select the version and capabilities exposed to your account.

• GPT models from OpenAI.
• Claude models from Anthropic.
• Gemini models from Google.

EU-hosted model pages

Explore the European deployments requested for this model collection. Hosting is attached to the selected route, not to every model in the wider catalog.

• Kimi K3
• GLM-5.3
• DeepSeek
• MiMo

Read identifiers from the API

Call GET /models with your TextCortex key. Use the returned identifier in your request rather than constructing one from a display name. Model versions can change independently of the application using them.

Keep a versioned list of approved models in your application configuration. Evaluate new entries before moving production traffic, and remove retired identifiers from your task mapping.

Choose by the result you need

For coding, run the output against your project checks. For extraction, score field accuracy and output validity. For a user-facing assistant, measure helpfulness and response time on representative conversations.

Use the model selection guide to compare candidates and the API pricing guide to estimate usage.

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)