Ready-to-use endpoint
OpenAI-compatible API with OCR, Whisper and voice installed and maintained by GeHost.
An OpenAI-compatible endpoint with OCR, Whisper and voice already installed. Access is controlled by token and IP addresses, with at most 2 tenants per GPU, no content recorded and service ready within 48 h.
Connect your integration using the URL and model shown in the customer portal. You do not have access to the machine.
We accept only requests that include a valid token and come from an allowed IP address.
Each tenant has their own concurrency slots and context limits. Performance may vary with the other tenant’s usage.
Request and response content is never stored. Only usage counts and technical metadata are kept.
It comes with OCR, Whisper (transcription) and voice through the same endpoint.
Monthly reference price in US$. Billed in your account currency.
We're preparing our own cards for the Shared GPU service, with OCR, Whisper and voice, plus 10 GB of storage per tenant. Leave your contact details and we'll notify you when the service opens, with no obligation. Pricing and the launch date are only confirmed once the card is listed.
An OpenAI-compatible endpoint with OCR, Whisper and voice already installed. Access is controlled by token and IP addresses, each GPU has at most 2 tenants, and no content is recorded. Ready within 48 h, with no server to manage.
OpenAI-compatible API with OCR, Whisper and voice installed and maintained by GeHost.
A monitor checks the health of the service on the GPU and restarts it automatically if it stops.
Access via token and registered IPs. We do not log any request or response content.
The listed price applies when you have the GPU to yourself. When a second tenant joins, the discount is automatically applied to both invoices.
If the GPU becomes unavailable, GeHost migrates the service to an equivalent one.
After payment, the endpoint, token and IP addresses are available in the client area.
| Build it yourself | GeHost | |
|---|---|---|
| Máy chủ | Rent the machine and install drivers, models and an inference server | Ready-to-use OpenAI-compatible endpoint with OCR, Whisper and voice |
| Bảo trì | You monitor, restart, update and replace the machine | GeHost monitors and restarts the service and replaces the GPU at no extra cost |
| Bảo mật | You configure the token, firewall and logging | Token and registered IPs. No content logging. |
| Cost | Pay for the whole GPU, even with low usage | Up to 2 tenants, with an automatic invoice discount when the second joins |
| Hỗ trợ | Knowledge base, forum or ticket in English | 24/7 AI with immediate responses in Portuguese, Japanese and English |
Read PDFs and images with private AI without sending data to public services.
Whisper and voice through the same endpoint for customer support, meetings and media.
Private AI for your clients’ projects, with no server to set up or monitor.
Support in Portuguese and Japanese and billing in Brazilian real or Japanese yen.
Tell us about your workload and timeline. We respond in Portuguese, English or Japanese.
Endpoint and model prepared by GeHost, with up to two tenants. Use AI without administering the server.
For those who need exclusivity and administrative access to the server.
Explore Dedicated GPUJoin the waitlist or contact GeHost to size your setup for your workload.
Join the waitlistTrò chuyện với GeHost