Skip to content

Getting Started

LootVM is a hosted enterprise AI API gateway. You authenticate with a LootVM-issued API key from the Console—not an upstream provider key in your client—and call models your workspace enables over one base URL.

LootVM speaks both:

  • OpenAI-compatible Chat Completions — POST /v1/chat/completions
  • Anthropic-compatible Messages (Claude) — POST /v1/messages

Sign in at lootvm.com and open the Console.

In the Console, create an API key for your user. Restrict it to the groups and models your workspace policy allows.

Store the secret once it is shown. LootVM does not re-display the full key later.

Point clients at:

https://api.lootvm.com/v1

Use HTTPS only. Do not put the API key in the URL.

Terminal window
export LOOTVM_KEY='your-lootvm-api-key'
curl --fail-with-body https://api.lootvm.com/v1/models \
-H "Authorization: Bearer ${LOOTVM_KEY}"

Anthropic-style clients may send the same key as x-api-key on /v1/models and /v1/messages instead of Authorization.

Replace your-enabled-model with a model id from /v1/models that your key can use.

Terminal window
curl --fail-with-body https://api.lootvm.com/v1/chat/completions \
-H "Authorization: Bearer ${LOOTVM_KEY}" \
-H "Content-Type: application/json" \
-d '{
"model": "your-enabled-model",
"messages": [
{"role": "user", "content": "Hello from LootVM"}
]
}'
Terminal window
curl --fail-with-body https://api.lootvm.com/v1/messages \
-H "Authorization: Bearer ${LOOTVM_KEY}" \
-H "anthropic-version: 2023-06-01" \
-H "Content-Type: application/json" \
-d '{
"model": "your-enabled-model",
"max_tokens": 256,
"messages": [
{"role": "user", "content": "Hello from LootVM"}
]
}'

You can also send x-api-key: ${LOOTVM_KEY} instead of the Bearer header on this path. See Authentication.