DeepInfra GPU Instances give you dedicated access to NVIDIA B200 hardware — the most powerful GPUs available. You get a container with SSH access and full control over your environment, billed by the hour.
Available GPUs
Key features
- Dedicated access — no sharing with other users
- SSH access — connect directly to your container
- Full environment control — bring your own Docker image or use ours
- Pay-per-use — billed by the hour, only while running
- Quick setup — running in minutes
Use cases
- LLM training and fine-tuning
- Large-scale batch inference
- Research and experimentation
- Development environments with GPU access
Web UI
Start a new container
- Go to Dashboard → GPU Instances
- Click New Container
- Select GPU configuration — choose from available B200/B300 configs. Each shows:
- GPU type, quantity, and memory (e.g.,
1xB200-180GB, 8xB200-180GB)
- Hourly pricing
- Availability status
- Enter container details:
- Container Name — a descriptive name
- SSH Key — paste your public SSH key (format:
ssh-rsa AAAAB3NzaC1yc2E...)
- Accept the NVIDIA license agreements and cryptocurrency mining policy
- Click I agree to the above
Connect to a running container
- Wait for container status to show
running
- Click on the SSH login field to copy the command
- Run
ssh ubuntu@<ip-address> in your terminal
Stop a container
- Click on the container in the instances list
- Click Terminate
- Type
confirm and click Terminate
All container data is permanently lost when terminated. Save your work before stopping.
HTTP API
Create a container
Get container details
Once running, connect via SSH:
List containers
Terminate a container
Container lifecycle