Developer Docs

API Keys

Two types of API keys:

Generate an account key from Settings → API Keys or via the API:

POST /auth/api-key
Content-Type: application/json
Cookie: (session)

{"label": "My CLI Key"}

CLI Tool

npm install -g computegpu

Setup

computegpu login gpu_your_api_key_here

Commands

Search flags

computegpu search \
  --gpu RTX4090 \
  --max-price 1.00 \
  --vram 24 \
  --model llama3 \
  --sort price

REST API

Base URL: https://computegpu.com/api/v1/marketplace

Public (no auth)

Authenticated (Authorization: Bearer gpu_...)

Example: Search + Rent

# Search
curl https://computegpu.com/api/v1/marketplace/search?gpu=RTX4090

# Rent
curl -X POST https://computegpu.com/api/v1/marketplace/rent/LISTING_ID \
  -H "Authorization: Bearer gpu_your_key"

# Use the GPU
curl https://computegpu.com/api/v1/ollama/RENTAL_ID/api/chat \
  -H "Authorization: Bearer RENTAL_API_KEY" \
  -d '{"model":"llama3","messages":[{"role":"user","content":"Hello"}]}'

# Stop
curl -X POST https://computegpu.com/api/v1/marketplace/rentals/RENTAL_ID/stop \
  -H "Authorization: Bearer gpu_your_key"

GPU Cloud API

Deploy, manage, and destroy cloud GPU instances programmatically. Supports single-GPU and multi-GPU (up to 8x) configurations.

Base URL: https://computegpu.com/api/v1/gpu

Public (no auth)

Authenticated (Authorization: Bearer gpu_...)

Example: Deploy + Use + Destroy

# Browse GPU types
curl https://computegpu.com/api/v1/gpu/types

# Deploy an RTX 4090 with Ollama
curl -X POST https://computegpu.com/api/v1/gpu/deploy \
  -H "Authorization: Bearer gpu_your_key" \
  -H "Content-Type: application/json" \
  -d '{"gpuType":"RTX 4090","models":["llama3.3","gemma4:e4b"]}'

# Check instance status
curl https://computegpu.com/api/v1/gpu/pods/POD_ID \
  -H "Authorization: Bearer gpu_your_key"

# Pause billing (keep volume)
curl -X PUT https://computegpu.com/api/v1/gpu/pods/POD_ID/stop \
  -H "Authorization: Bearer gpu_your_key"

# Resume
curl -X PUT https://computegpu.com/api/v1/gpu/pods/POD_ID/resume \
  -H "Authorization: Bearer gpu_your_key"

# Destroy (permanent, final billing)
curl -X DELETE https://computegpu.com/api/v1/gpu/pods/POD_ID \
  -H "Authorization: Bearer gpu_your_key"

Deploy response

{
  "instance": {
    "id": "68abc123def456",
    "gpuType": "RTX 4090",
    "vramGb": 24,
    "pricePerHour": 0.51,
    "instanceType": "ollama",
    "status": "deploying",
    "pricingTier": "on-demand",
    "startedAt": "2026-04-30T15:00:00.000Z"
  }
}

Access types

Set instanceType in the deploy body:

Serverless GPU API

Deploy inference endpoints that auto-scale to zero. Pay per second of compute, not per hour of uptime.

Base URL: https://computegpu.com/api/v1/serverless

Public (no auth)

Authenticated (Authorization: Bearer gpu_...)

Example: Deploy + Inference

# Create an Ollama serverless endpoint
curl -X POST https://computegpu.com/api/v1/serverless/endpoints \
  -H "Authorization: Bearer gpu_your_key" \
  -H "Content-Type: application/json" \
  -d '{"name":"llama3-api","templateId":"tpl_ollama","gpuType":"AMPERE_24","workersMax":3}'

# Run sync inference
curl -X POST https://computegpu.com/api/v1/serverless/endpoints/ENDPOINT_ID/run \
  -H "Authorization: Bearer gpu_your_key" \
  -H "Content-Type: application/json" \
  -d '{"input":{"prompt":"What is the capital of France?","max_tokens":100}}'

# Run async + poll
JOB_ID=$(curl -s -X POST .../endpoints/ENDPOINT_ID/run-async \
  -H "Authorization: Bearer gpu_your_key" \
  -d '{"input":{"prompt":"Explain quantum computing"}}' | jq -r '.jobId')

curl .../jobs/$JOB_ID?endpointId=ENDPOINT_ID \
  -H "Authorization: Bearer gpu_your_key"

Templates

Billing

• Billed per second of compute time (not wall clock)
• Zero cost when scaled to zero (no idle charges)
• Wallet prepaid — deducted per job completion
• Minimum $0.10 wallet balance to run jobs
• Rate limit: 60 jobs/minute per user

GPU Clusters

Multi-node GPU clusters with InfiniBand interconnect. 2–32 instances per cluster, up to 8 GPUs per node.

Manage via the dashboard or programmatically. Cluster API coming soon — currently available via dashboard UI.

Configuration

Learn more about clusters →

Network Storage

Persistent network volumes that survive instance restarts. Store models, datasets, and checkpoints. Attach to any instance or cluster.

Manage via the dashboard or programmatically. Storage API coming soon — currently available via dashboard UI.

Features

• Persistent across instance restarts and redeployments
• Shared across multiple instances in a cluster
• Resize anytime without data loss
• Available in multiple regions

Wallet API

Prepaid credits for GPU rentals. Add funds via inline Stripe Elements (cards, Apple Pay, Google Pay).

Base URL: https://computegpu.com/wallet (session auth required)

Billing rules

• Minimum top-up: $5
• Must have ≥1 hour's GPU cost to start a rental
• Pods: billed per second of uptime. Auto-stops at $0.
• Serverless: billed per second of compute. $0 when idle.

Agent Signup

Programmatic provisioning for AI agents. Provide an email — we send the account owner a signup link. They create an account, add credits, and get an API key.

Base URL: https://computegpu.com/api/signup

Example

# Request agent account (emails the human a signup link)
curl -X POST https://computegpu.com/api/signup \
  -H "Content-Type: application/json" \
  -d '{"email":"dev@company.com","tenantId":"my-agent","agent":"claude-code"}'

# Human clicks link → creates account → tops up wallet → gets API key
# Use the key for all GPU Cloud + Serverless operations

How it works

• Agent calls POST /api/signup with an email + tenant ID
• Account owner receives email with a signup link
• Owner creates account, adds credits via credit card (minimum $5 top-up)
• API key available on dashboard — share with your agent
• Per-second billing. No free credit. Pay only for what you use.

τAI Chat API

AI-powered support chat. 14 domain experts for GPUs, billing, deployments, and more.

Base URL: https://computegpu.com/api/support

Example

curl -X POST https://computegpu.com/api/support/message \
  -H "Content-Type: application/json" \
  -d '{"message":"How much is an RTX 4090?","sessionId":"my-session"}'

# Returns: {"answer":"...","experts":["marketplace"],"fastPath":true}

Instance Types

Billing

Per-second billing

Everything is billed per second. Prices displayed as $/hr for readability. Stop after 47 seconds? Pay for 47 seconds.

Product billing

Pricing tiers

Wallet

• Prepaid credits — add via inline Stripe (cards, Apple Pay, Google Pay)
• Minimum top-up: $5. Presets: $5, $10, $25, $50, $100
• Instance auto-stops when balance hits $0
• Serverless requires $0.10 minimum to run jobs

Templates

970+ pre-built templates for pods and serverless endpoints. Browse the Template Hub.

• Serverless templates — Ollama, vLLM, SDXL, Whisper, ComfyUI, SGLang, Faster Whisper, and more
• Instance templates — PyTorch, TensorFlow, JupyterLab, Ubuntu, and 940+ community templates

Each template specifies a Docker image, minimum VRAM, and access type (Jupyter/SSH). Pick one, choose a GPU, deploy.

Browse Template Hub

Open Source

ComputeGpu is built on open-source infrastructure and contributes back to the ecosystem.

Tyga.Cloud ecosystem

Projects we use and thank