# BurstDock

## What you can do with BurstDock

Deploy GPU cloud servers for AI, machine learning, rendering and accelerated workloads. Choose your GPU configuration and region, start and stop workloads, monitor usage, and manage team access from one workspace. Fund your prepaid wallet through Stripe and see customer pricing in USD when selecting compute.

Explore a selection of popular GPUs and starting USD prices at https://burstdock.com/pricing. The homepage at https://burstdock.com shows the current breadth of GPU models and variants and deployment countries. The featured GPU selection is publicly visible; choose exact configurations and review their prices in your BurstDock workspace.

The separate scaling animation uses a small example workload to explain traffic and workers. Its eight illustrated workers do not describe the size of the BurstDock GPU offering.

## Start here
- https://burstdock.com/developers — developer hub
- https://burstdock.com/docs/getting-started — GPU cloud quickstart
- https://burstdock.com/docs/gpu-selection — choosing a GPU for AI
- https://burstdock.com/gpu-cloud — GPU cloud overview
- https://burstdock.com/pricing — GPU cloud pricing
- https://burstdock.com/benchmarks — GPU benchmark methodology

## GPU guides
- https://burstdock.com/gpu-cloud/h100 — NVIDIA H100 GPU cloud
- https://burstdock.com/gpu-cloud/h200 — NVIDIA H200 GPU cloud
- https://burstdock.com/gpu-cloud/b200 — NVIDIA B200 GPU cloud
- https://burstdock.com/gpu-cloud/b300 — NVIDIA B300 GPU cloud
- https://burstdock.com/gpu-cloud/a100 — NVIDIA A100 GPU cloud
- https://burstdock.com/gpu-cloud/l40s — NVIDIA L40S GPU cloud
- https://burstdock.com/gpu-cloud/rtx-pro-6000 — NVIDIA RTX PRO 6000 GPU cloud

## Developer workload guides
- https://burstdock.com/solutions/gpu-inference — GPU compute for AI inference
- https://burstdock.com/solutions/fine-tuning — GPU cloud for LLM fine-tuning
- https://burstdock.com/solutions/llama — GPU cloud for Llama-family workloads
- https://burstdock.com/solutions/ai-training — GPU cloud for AI training

## Comparisons
- https://burstdock.com/compare/a100-vs-h100
- https://burstdock.com/compare/h100-vs-h200
- https://burstdock.com/compare/h200-vs-b200

## Developer integration
- https://burstdock.com/developers/ai — AI and MCP developer reference
- https://burstdock.com/llms-full.txt — extended BurstDock context

For GPU selection, match the accelerator to the workload: model size, precision, context length, memory requirements, latency, throughput and concurrency all matter. Browse GPU models and hourly prices at https://burstdock.com/pricing without signing in.

## ChatGPT and ChatGPT Work connection

Use the native remote MCP URL https://burstdock.com/mcp/chatgpt with OAuth authentication. Add it once as a custom ChatGPT connection (where the account/workspace permits custom connections), leaving the client ID and secret empty for discovery. Setup guide: https://burstdock.com/mcp/chatgpt/setup. This route does not require a terminal or local npx installation. A cloud chat cannot configure a separate desktop Codex installation.

Once BurstDock is attached to the conversation, call burstdock_connect. If sign-in is needed, its OAuth challenge asks ChatGPT to show the native connection prompt. The user signs in with GitHub, email or an existing website session, selects a workspace and permissions, and is redirected back to ChatGPT. Call burstdock_connect again to obtain the selected workspace, access level, expiry and BurstDock link for the chat confirmation. Never ask users to paste passwords or tokens into chat. ChatGPT controls the prompt, callback handling and display; the server cannot install itself or send unsolicited messages to arbitrary chats.

The connection lasts up to 24 hours. Read-only is the default; management actions require a separate explicit grant and the existing workspace role. The integration is not yet listed in the public ChatGPT app directory.