Simple, transparent pricing

From lightweight containers to dedicated GPU servers. Pick the right plan for your workload — no hidden fees, no long-term contracts.

Pods CPU GPU

Bufo Pod

POD

Large and powerful container for heavier workloads before going dedicated.

$20/month

CPU: 2 vCPU

RAM: 2 GB RAM

Disk: 20 GB Storage

BW: 3 TB Transfer

Everything in Poison Dart Pod
2 vCPU / 2 GB RAM
20 GB storage
2 workspaces
Priority email support

Pro

CPU

More compute for active development and heavier workloads.

$39/month

CPU: 2 vCPU

RAM: 4 GB RAM

Disk: 80 GB NVMe

BW: 4 TB Transfer

Everything in Lite
2 vCPU / 4 GB RAM
80 GB NVMe storage
2 workspaces
Automatic daily backups
Firewall management (15 rules)
Priority email support

GPU A16

GPU

Entry-level GPU for local inference and AI experimentation.

$449/month

CPU: 6 vCPU

RAM: 64 GB RAM

Disk: 500 GB NVMe

BW: 8 TB Transfer

GPU: A16 — 16 GB VRAM

Everything in Ultra
NVIDIA A16 — 16 GB GDDR6
Ollama pre-installed
Private on-device inference
Run 7B-13B parameter models
3 workspaces
Daily backups
Firewall management (50 rules)
SSH access

See all 3 Pods plans →See all 3 CPU plans →See all 3 GPU plans →

Compare featured plans

Feature	Bufo Pod	Pro	GPU A16
Price	$20/mo	$39/mo	$449/mo
Infrastructure	Docker Container	Dedicated VM	Dedicated GPU VM
vCPU	2	2	6
RAM	2 GB	4 GB	64 GB
Storage	20 GB	80 GB NVMe	500 GB NVMe
Bandwidth	3 TB Transfer	4 TB Transfer	8 TB Transfer
GPU			A16 — 16 GB VRAM
Workspaces	2	2	3
Backups
Firewall Rules		15 rules	50 rules
REST API
BYOK (any LLM)
Ollama Pre-installed
SSH Access
More options	All 3 plans	All 3 plans	All 3 plans

Bufo Pod

$20/month

Infrastructure	Docker Container
vCPU	2
RAM	2 GB
Storage	20 GB
Bandwidth	3 TB Transfer
GPU
Workspaces	2
Backups
Firewall Rules
REST API
BYOK (any LLM)
Ollama Pre-installed
SSH Access

See all 3 Pod plans

Pro

$39/month

Infrastructure	Dedicated VM
vCPU	2
RAM	4 GB
Storage	80 GB NVMe
Bandwidth	4 TB Transfer
GPU
Workspaces	2
Backups
Firewall Rules	15 rules
REST API
BYOK (any LLM)
Ollama Pre-installed
SSH Access

See all 3 CPU plans

GPU A16

$449/month

Infrastructure	Dedicated GPU VM
vCPU	6
RAM	64 GB
Storage	500 GB NVMe
Bandwidth	8 TB Transfer
GPU	A16 — 16 GB VRAM
Workspaces	3
Backups
Firewall Rules	50 rules
REST API
BYOK (any LLM)
Ollama Pre-installed
SSH Access

See all 3 GPU plans

Frequently Asked Questions

What is Coqui Bot?

Coqui Bot is a terminal-based AI agent powered by PHP 8.4+ that can execute shell commands, edit files, run code, and interact with any LLM provider. Think of it as Claude Code or Cursor, but self-hosted and extensible with PHP toolkits.

What's the difference between Pods and CPU plans?

Pods are lightweight Docker containers running on shared infrastructure — great for trying Coqui or running light automations at a lower cost. CPU plans give you a dedicated VM with guaranteed resources and NVMe storage, ideal for active development and production workloads.

Can I use my own API keys?

Yes. Coqui supports BYOK (Bring Your Own Keys) for OpenAI, Anthropic, Mistral, xAI, Google, and Ollama. Your keys are stored in your instance's .env and never leave your VM.

What does 'private inference' mean?

GPU plans come with Ollama pre-installed. You can download and run LLM models directly on your instance. Your prompts, data, and outputs never leave the VM — no third-party API calls needed.

Can I cancel anytime?

Yes. Subscriptions are month-to-month with no contracts. Cancel from your dashboard or Stripe portal. Your instance stays active until the end of the billing period.

What happens to my data if I cancel?

After cancellation, your instance data is preserved for 7 days. You can create a backup snapshot before canceling. After 7 days, the instance and all data are permanently deleted.