Proprietary and open-weight models
Access GPT, Claude, Gemini, Kimi, GLM, DeepSeek, MiMo and more through TextCortex. Choose models from the catalog available to your account.
TextCortex API · Models and routing
Choose where your model requests run.
Use TextCortex’s EU-hosted model options through an OpenAI-compatible API. Keep model selection and processing requirements in the same routing decision.
One API. Every model family.
GPTOpenAI
ClaudeAnthropic
GeminiGoogle
GLM5.3
DeepSeek
KimiK3
MiMo
TextCortex
Why TextCortex
EU inference starts with the selected route.
TextCortex provides EU-hosted model access alongside a wider proprietary and open-weight catalog. Choose the deployment that matches your application’s regional requirements.
One OpenAI-compatible API
Use a familiar client, one TextCortex API key and a common base URL. Change the model identifier to switch between supported models.
EU-hosted model options
Use EU-hosted routes for European inference requirements. Hosting depends on the selected model and route; the wider catalog also includes other deployments.
A European endpoint is a deployment choice
Kimi K3, GLM-5.3, DeepSeek and MiMo are the focus of this EU-hosted collection. Use the EU deployment enabled for your account and record the model and processing arrangement for that workload.
The broader API also gives you access to GPT, Claude, Gemini and other models. Do not infer the processing region of these routes from the location of the TextCortex application.
Keep model inference and application data together in your review
Your application may retrieve documents, log prompts or call external tools around a model request. Review those systems as well as the selected inference route.
The privacy policy describes processing recipients and conditions. Model access, logging, storage and connected tools should be assessed against the requirements of the actual application.
Use a regional model allowlist
Record which identifiers and deployments your application can use before enabling model switching.
- Select the permitted EU-hosted deployments.
- Keep the allowed model identifiers in server-side configuration.
- Apply the same regional requirement to any fallback path.
- Recheck the route when adding a model or changing a deployment.
Explore EU-hosted API access
Start with Kimi K3, GLM-5.3, DeepSeek or MiMo. Each uses the same TextCortex API integration.
Create your account to get started and select the model route for your application.
Questions
Your next questions, answered.
Are all models in the catalog EU-hosted?
TextCortex offers EU-hosted model routes and a broader multi-provider catalog. Select the EU-hosted deployment required by your application; catalog membership alone does not establish where a particular request is processed.
Can I use an OpenAI-compatible client?
Yes. Configure the client with the TextCortex base URL and API key. Use a TextCortex model identifier and the parameters supported by that model. Model discovery, chat completions and responses are documented in the API reference.
Is TextCortex limited to open-source models?
No. The API provides access to proprietary model families such as GPT, Claude and Gemini alongside open-weight families such as Kimi, GLM, DeepSeek and MiMo. Use GET /models to list the identifiers available to your account.
How do I start using the API?
Sign up for TextCortex, create an API key in your account settings, and use https://api.textcortex.com/v1 as the base URL. Retrieve the model catalog, select a model identifier and send a chat-completion request.
TextCortex AI
One integration. Your choice of models.
Sign up for TextCortex, create an API key and start building with the models your application needs.
Sources and documentation
Product documentation and provider references used for this guide. Reviewed on 5 October 2026.