Processing machines on your site; control layer at TTNC.
- API keys per team or application
- Usage tracked per key and team
- OpenAI-compatible API for your developers
Your organisation
GPU server 32 GBTTNC · Bangkok DC
Data centre in Bangkok- Modules: Your organisation
- Platform Gateway: TTNC · Bangkok DC
- Token Factory: Your organisation
- What leaves your organisation
- Permission checks and usage records, via the control layer at TTNC
- GPU
- Yes — processing on site
- Best for
- Dev teams that want their own API keys and GPUs
GPU servers on your site
Runs on standard GPU servers · our software is not tied to a single vendor. Installed in your server room and looked after from day one.
Move to another package later without changing your apps
Nothing to buy piece by piece
Every package comes with what an organisation needs before staff start using AI.
Audit log
A usage record is kept for later review — who used it, when, and through which model
Installed for you
The TTNC team installs and configures it on site
First-year service
Support and updates for the first year
Sign-in & permissions
Who sees what, set by role
Personal-data masking (opt-in)
Masking personal data before it reaches the model — can be switched on per organisation; not on by default
Open-source models
Pick the model for the job and change it without touching your apps
The only difference is where each layer runs
All three packages run the same platform. Start with any one and move later without rewriting your applications.
★ Private AI (Full)
Every layer on site; no need to send data out for processing
Token Factory
Processing machines on your site; control layer at TTNC; developers get their own API keys
Platform Gateway
No GPUs to buy; processed on GPU servers in TTNC's data centre in Thailand
Find the package that fits your organisation's data
45 minutes with the team, with a demo on your own sample data
Watch one request travel through all 3 layers → Modules → Platform Gateway → Token Factory