Status: private beta. The hosted LLM endpoint at
https://api.itdatex.support/api/chatis currently in a closed testing phase. New API keys are handed out on a case-by-case basis to WordPress sites that want to try the itdatex Cloud provider of the “itdatex Blog-Bot” plugin. There is no self-service signup and no public pricing yet.
If you install the plugin and just want to use it right away, pick Local Ollama in the settings — that is the default and works without any account, key, or contact with us. See the plugin’s readme for setup instructions.
What “itdatex Cloud” is
- A hosted endpoint (
https://api.itdatex.support/api/chat) that speaks the Ollama chat API and returns rewritten blog drafts to the plugin. - Operated by itdatex on servers in Germany.
- Opt-in — the plugin defaults to Local Ollama and will not talk to itdatex Cloud unless you explicitly pick the provider, tick the privacy-consent checkbox, and enter an API key.
Request an API key
If you want to try the beta, send an email to rainerneuenhausen@gmail.com with:
- The domain of the WordPress site that will use the key.
- A short line about what you plan to do with it (helps us gauge load).
- The email address you want us to send account notices to.
We aim to reply within a few business days. Beta keys are issued at our discretion; we may decline requests when the beta is at capacity.
What you get during the beta
- One key per approved site.
- No published rate limit — we monitor usage manually and will get in touch if a site consumes disproportionately.
- The service runs an open-weights model of our choice (currently Qwen2.5-7B-Instruct or an equivalent); this may change without notice during the beta.
- No SLA, no availability guarantee. The beta can go down for maintenance at any time. Do not build a workflow that assumes it is always up.
What you pay
Nothing during the beta. Once the service exits beta, we will publish pricing here at least 30 days before it takes effect, and existing beta users will get an email with the transition details.
Data handling
See the Privacy Policy for the full detail. Summary of what happens with a request:
- We receive: your API key, the plugin’s rewrite prompt, the RSS item title + URL, and up to ~3,500 characters of the item’s content.
- We run it through the LLM and return the rewritten JSON.
- We keep short-lived request logs (timestamp, key ID, IP, status, tokens) for up to 30 days for abuse prevention and capacity planning. Payloads themselves are not persisted.
- We do not train models on your content.
- We do not share your content with third parties for advertising or profiling.
Rotating or revoking a key
- Email
rainerneuenhausen@gmail.comfrom the address on your account. - We rotate or revoke immediately on request.
Terms
Use of the endpoint is governed by the Terms of Service. By requesting a key and using it, you accept those terms.
Not accepted into the beta?
That is fine — the plugin’s Local Ollama provider gives you the same functionality on your own hardware. Install Ollama (https://ollama.com/), pull a model (ollama pull qwen2.5:7b-instruct-q4_K_M), leave the plugin’s provider on the default, and you’re set. Nothing leaves your server.