Kimi K2.6. EU-hosted. OpenAI-compatible.

Use Kimi K2.6 through a familiar API

For an existing Kimi K2.6 workload, keep the model mapping explicit while evaluating Kimi K3. This page remains the version-specific reference; the Kimi K3 page covers the newer EU-hosted option.

Keep your model client pointed at https://api.textcortex.com/v1. Select the model identifier returned for your account, with the EU-hosted deployment required by your application.

European hosting, selected deliberately

Choose the EU-hosted Kimi route for requests that need European model processing. Keep that requirement attached to the route when changing versions or adding fallback behavior.

Your application may also use other models from the catalog. Their hosting arrangements can differ, so keep an explicit list of the deployments permitted for each workload.

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)

One model today. More choices when you need them.

Use the same TextCortex connection to compare Kimi K2.6 with GPT, Claude, Gemini and other open-weight models. Assign models to different tasks using your application’s routing configuration.

Review capabilities for the chosen version before enabling tools, structured output, streaming or reasoning settings. The model selection guide helps you build a repeatable evaluation.

Explore related EU-hosted endpoints

Keep one API integration while expanding the models available to your product.

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