Solutions / BYOC

Bring your own compute back to your API
BYOC (Bring Your Own Compute)

Run the model on equipment you control while your application keeps one BazaarLink API entry point. The node serves its owner’s account; this is not a shared compute marketplace.

Manage BYOC nodes

From GitHub install to connected node

@bazaarlink/byoc-agent v0.1.0 is MIT licensed. Install the CLI globally from the public GitHub repository; the npm registry version is coming later. The --models value (for example qwen3.5:2b) is the local backend model ID; it is not the canonical ID used by the API. Authenticated only confirms the gateway connection. Then open /keys/byok?tab=byoc, create byoc/qwen3.5-2b -> qwen3.5:2b, and call byoc/qwen3.5-2b through the API.

Install the CLI globally

Install the MIT-licensed CLI directly from the public GitHub repository.

1
npm install -g github:Bazaarlinkorg/bazaarlink-byoc-agent

Get a BYOC key

If you already have one, continue; otherwise use register with your email, models, and concurrency.

1
2
3
4
bazaarlink-byoc register \
  --email you@example.com \
  --models qwen3.5:2b \
  --max-concurrent 4

Log in to the gateway

1
2
3
4
5
6
bazaarlink-byoc login \
  --key "byoc_..." \
  --gateway "https://byoc-gateway.bazaarlink.ai" \
  --models "qwen3.5:2b" \
  --input-price 0 \
  --output-price 0

Start and connect

Authenticated only confirms the gateway connection. Then open /keys/byok?tab=byoc, create byoc/qwen3.5-2b -> qwen3.5:2b, and call byoc/qwen3.5-2b through the API.

1
2
3
bazaarlink-byoc start
# Authenticated only confirms the gateway connection.
# Create byoc/qwen3.5-2b -> qwen3.5:2b in /keys/byok?tab=byoc

Customer machine → BYOC Agent → BazaarLink gateway → Customer app

The model and inference environment stay on your equipment. The Agent opens the gateway connection, the gateway routes your account’s work to your node, and the app keeps one API entry point.

Your GPU capacity

Model and inference stay on your hardware

BazaarLink models

Take over when your node is full or offline

BazaarLink BYOC

No BazaarLink price on your own node's traffic

One API key

Same endpoint, no client changes

Your application

Local backends supported today

Choose the local backend that runs your model, then pass its connection settings to the Agent.

Ollama

Default backend; the default URL is http://localhost:11434.

LM Studio / vLLM

Use --backend openai and --url with the model ID your local server accepts.

llama.cpp server

Uses the same OpenAI-compatible streaming path without model-name translation.

Why connect compute to your own account

Models run on your equipment

You control the model files, inference process, hardware, and local runtime.

Zero BazaarLink pricing for this traffic

Traffic executed through your BYOC node has zero BazaarLink pricing; you still own the equipment, power, and operations.

One API for the application

The local model connects through the gateway, so product code does not need a transport layer per backend.

The node serves its owner

Jobs stay bound to the owning account. The node is not placed in a shared pool or compute marketplace.

Technical details

These fields mirror the current CLI and package metadata. Install from the public GitHub repository until the npm registry version arrives.

npm package: @bazaarlink/byoc-agent v0.1.0 · MIT · install from GitHub, npm registry version coming later
Source: github.com/Bazaarlinkorg/bazaarlink-byoc-agent
CLI: bazaarlink-byoc
Runtime: Node.js 18+
Connection: Agent opens gateway /ws outbound; no inbound port is required
Local config: ~/.bazaarlink/config.json (Windows: %USERPROFILE%\.bazaarlink\config.json)
login pricing flags: --input-price and --output-price are currently required; 0 is a compatibility value, not a BYOC charge

Install the CLI from GitHub

1
npm install -g github:Bazaarlinkorg/bazaarlink-byoc-agent

The CLI is installed globally from the public GitHub repository; the npm registry version is coming later.

Ollama: log in and start

1
2
3
4
bazaarlink-byoc login   --key "byoc_REPLACE_WITH_YOUR_KEY"   --gateway "https://byoc-gateway.bazaarlink.ai"   --models "qwen3.5:2b"   --input-price 0   --output-price 0
bazaarlink-byoc start
# Authenticated only confirms the gateway connection.
# Create byoc/qwen3.5-2b -> qwen3.5:2b in /keys/byok?tab=byoc

--backend ollama is the default. Add --ollama-url when Ollama runs elsewhere.

OpenAI-compatible: log in and start

1
2
3
4
bazaarlink-byoc login   --key "byoc_REPLACE_WITH_YOUR_KEY"   --gateway "https://byoc-gateway.bazaarlink.ai"   --backend openai   --url "http://localhost:1234/v1"   --models "your-model-id"   --input-price 0   --output-price 0
bazaarlink-byoc start
# Authenticated only confirms the gateway connection.
# Create byoc/qwen3.5-2b -> your-model-id in /keys/byok?tab=byoc

LM Studio, vLLM, and llama.cpp use --backend openai; --url is required and --models must match the local model ID.

Who this is for

You have a GPU host and local model, and want the model files and inference environment to stay on equipment you control while your product keeps a familiar API entry point.

You do not want to rent out idle compute or place requests into a shared node pool. BYOC connects your equipment, your account, and one gateway path.

Validate with one machine you own