computegpu

Rent cloud GPUs from your terminal, or let your AI agent do it.

npm i -g computegpu
computegpu signup [email protected] my-agent
computegpu deploy --gpu "RTX 4090"

Install

npm i -g computegpu

Requires Node.js 18+.

Quick Start

# Create account (the owner's email gets a $0 card check: no charge)
computegpu signup [email protected] my-project

# Where am I? verified, balance, next step
computegpu me

# Link expired? (it lasts 5 minutes) send a fresh one
computegpu verify

# Browse GPUs
computegpu types

# Deploy
computegpu deploy --gpu "RTX 4090" --models llama3.3

# Check status
computegpu pods
computegpu status POD_ID

# Stop
computegpu stop POD_ID

Commands

| Command | Description | |---------|-------------| | signup <email> <tenantId> | Create account + get API key | | login --key <KEY> | Save existing API key | | logout | Clear saved key | | me | Account: verified, balance, next step | | verify | Email the owner a fresh $0 card-check link | | types | Live GPU catalogue with pricing | | cheapest --vram <GB> | Find cheapest GPU for VRAM | | deploy --gpu "RTX 4090" | Deploy on-demand instance | | pods | List active instances | | status <podId> | Instance status + billing | | stop <podId> | Pause (billing stops) | | resume <podId> | Resume paused instance | | destroy <podId> | Permanent destroy | | balance | Wallet balance and next step | | topup <amount> | Email the owner a top-up request ($1 minimum) | | mcp-serve | MCP server for Claude Code / Cursor (stdio) |

Deploy Options

computegpu deploy --gpu "RTX 4090"           # on-demand
computegpu deploy --gpu "RTX 4090" --spot    # 50% off (preemptible)
computegpu deploy --gpu "H100" --count 4     # multi-GPU
computegpu deploy --gpu "RTX 4090" --models llama3.3,gemma4  # pre-load models
computegpu deploy --gpu "RTX 4090" --type docker  # Docker + SSH
computegpu deploy --gpu "RTX 4090" --volume 100   # persistent storage

Config

API key is saved to ~/.computegpu/config.json (global) or ./.computegpu/config.json (local).

Priority: --key flag > COMPUTEGPU_API_KEY env > local config > global config.

computegpu login --key gpu_your_key          # save globally
computegpu login --key gpu_your_key --local  # save per-project
computegpu config                             # show active config

Pricing

Per-second billing, $1 minimum top-up. Prices change with the market, so this file quotes none: computegpu types is the live catalogue.

If a deploy returns 402

• verification_required: the owner has not added a card yet ($0, no charge). Run computegpu verify.
• insufficient_credits: run computegpu topup <amount>, then retry.

Links

• Website: computegpu.com
• Docs: computegpu.com/docs
• API: computegpu.com/.well-known/openapi.json

License

Proprietary. Copyright (c) 2026 Tyga.Cloud Ltd. See LICENSE.