vast-ai/vast-cli/vastai

# Linux/macOS (recommended, no Python required)
curl -fsSL https://vast.ai/install.sh | bash
 
# or via PyPI (Windows, or if you'd rather use pip)
pip install vastai

vastai set api-key <YOUR_API_KEY>                   # Authenticate (one-time); Create API Key in account at https://console.vast.ai/manage-keys/
vastai show user                                    # Verify auth + check balance
vastai create ssh-key ~/.ssh/id_ed25519.pub         # Register SSH key (do BEFORE create)
vastai search offers 'gpu_name=RTX_4090 num_gpus=1 verified=true direct_port_count>=1 rentable=true' -o 'dlperf_usd-'
# Note the offer ID from the output
vastai create instance <OFFER_ID> --image pytorch/pytorch:@vastai-automatic-tag --disk 20 --ssh --direct
# Automatically grab appropriate image tag; Response:  {"success": true, "new_contract": <INSTANCE_ID>}
vastai show instance <INSTANCE_ID>                  # Poll until actual_status == "running" (see Instance status values below)
vastai ssh-url <INSTANCE_ID>                        # Get SSH connection string
vastai copy local:./data/ <INSTANCE_ID>:/workspace/ # Upload files
vastai destroy instance <INSTANCE_ID> -y             # Clean up (stops all billing; -y skips confirmation)

--api-key KEY    Override stored API key
--raw            Output machine-readable JSON (agents should always use this)
--full           Print full results (don't page with less)
--explain        Show underlying API calls (useful for debugging)
--curl           Show equivalent curl command
--no-color       Disable colored output
--url URL        Override server REST API URL
--retry RETRY    Set retry limit for API calls
--version        Show CLI version

# Examples
'gpu_name=RTX_4090 num_gpus=1'           # Exact match + numeric
'gpu_ram>=48 reliability>0.95'           # Greater-than filters
'geolocation=EU dph_total<=2.0'          # Region + price cap

vastai show instances                                    # List all your instances (fetches every page, no prompts)
vastai show instances --status running loading           # Filter by status
vastai show instances --gpu-name 'RTX 4090'              # Filter by GPU
vastai show instances --label training                   # Filter by label
vastai show instances --order-by start_date desc         # Sort by column
vastai show instances --cols id,status,gpu,dph           # Custom columns
vastai show instances --raw                              # Flat JSON list of all instances (scripting)
vastai show instance <id>                                # Poll single instance (use for status checks)
vastai create instance <offer-id> --image pytorch/pytorch:2.4.0-cuda12.4-cudnn9-runtime --disk 20 --ssh --direct
# Response includes "new_contract": <id> — that is your instance ID
vastai launch instance --gpu-name RTX_4090 --num-gpus 1 --image pytorch/pytorch
vastai start instance <id>                               # Start stopped instance
vastai stop instance <id>                                # Stop (preserves disk, no GPU charges)
vastai reboot instance <id>                              # Stop + start
vastai destroy instance <id> -y                          # Delete permanently (irreversible; -y required for non-interactive use)
vastai destroy instances <id1> <id2> -y                  # Batch delete (-y skips confirmation prompt)
vastai label instance <id> --label "training-run-1"      # Tag instance
vastai update instance <id>                              # Recreate from updated template
vastai prepay instance <id>                              # Deposit credits into reserved instance
vastai recycle instance <id>                             # Destroy + recreate

vastai/base-image:@vastai-automatic-tag          # Minimal Ubuntu base
vastai/pytorch:@vastai-automatic-tag             # PyTorch + CUDA
vastai/linux-desktop:@vastai-automatic-tag       # Linux desktop (VNC/RDP)
 
# vLLM — set model via env vars with huggingface model example
vastai create instance <id> --image vastai/vllm:@vastai-automatic-tag --disk 40 --ssh --direct \
  --env '-e MODEL_NAME=Qwen/Qwen2.5-3B-Instruct -e HF_TOKEN=hf_xxx'
 
# ComfyUI — set model checkpoint via env vars with huggingface model example
vastai create instance <id> --image vastai/comfy:@vastai-automatic-tag --disk 40 --ssh --direct \
  --env '-e CHECKPOINT_MODEL=black-forest-labs/FLUX.1-schnell -e HF_TOKEN=hf_xxx'

vastai search offers                                     # Default: verified, on-demand, sorted by score
vastai search offers 'gpu_name=RTX_4090 num_gpus=1 verified=true direct_port_count>=1' -o 'dlperf_usd-'
vastai search offers 'num_gpus>=4 reliability>0.99' -o 'num_gpus-'
vastai search offers --type bid                          # Interruptible (spot) pricing
vastai search offers --type reserved                     # Reserved pricing
vastai search offers -n 'gpu_name=H100_SXM'             # No default filters
vastai search volumes                                    # Search volume offers
vastai search templates "pytorch"                        # Search templates
vastai search benchmarks                                 # Search benchmarks
vastai search invoices                                   # Search invoice history

vastai ssh-url <id>                                      # Get ssh:// connection URL
vastai scp-url <id>                                      # Get scp:// URL
vastai attach ssh <id> "ssh-ed25519 AAAA..."             # Attach SSH key to instance
vastai detach ssh <id> <ssh_key_id>                      # Remove SSH key (ssh_key_id from show ssh-keys)
vastai show ssh-keys                                     # List account SSH keys
vastai create ssh-key ~/.ssh/id_ed25519.pub              # Add SSH key from file (do BEFORE create instance)
vastai create ssh-key                                    # Generate new key if you don't have one
vastai create ssh-key "ssh-ed25519 AAAA..."              # Add SSH key inline
vastai delete ssh-key <id>                               # Remove SSH key from account
vastai update ssh-key <id> "ssh-ed25519 AAAA..."         # Update SSH key value

vastai copy <src> <dst>                                  # Copy between instance and local
vastai copy local:./data/ <id>:/workspace/data/          # Local → instance (preferred format)
vastai copy <id>:/workspace/results/ local:./results/    # Instance → local
vastai copy <id-a>:/workspace/ <id-b>:/workspace/        # Instance → instance
vastai copy s3.101:/data/ C.<id>:/workspace/             # Cloud service → instance (s3.<connection-id>)
vastai copy V.1234:/file C.<id>:/workspace/              # Volume → instance
vastai copy V.1234:/file s3.101:/workspace/              # Volume → cloud service
# Legacy format also works: vastai copy 12345:./data ./local-data
vastai cloud copy --src ./data --dst s3://bucket/path \
  --instance 12345 --connection <conn-id> \
  --transfer "Instance To Cloud"                         # To cloud storage (add connection in UI on settings page)
vastai cancel copy <dst-id>                              # Cancel in-progress copy

vastai logs <id>                                         # Container logs (last 1000 lines)
vastai logs <id> --tail 100                              # Last 100 lines
vastai logs <id> --filter "error"                        # Grep filter
vastai execute <id> "nvidia-smi"                         # Run command on instance
vastai execute <id> "ls /workspace" --schedule DAILY     # Scheduled execution