Quickstart

Create an account, generate a key, call a hosted model.

1. Create an account

Sign up at /signup. This also creates your personal organization, which owns your API keys, provider credentials, and usage.

2. Generate an API key

In the app, go to Settings → API keys → Create key. Copy the secret immediately -- it's only shown once, and only a hash is stored afterward.

3. Call a hosted model

No provider key needed for hosted models -- your LLM Studio key is enough.

curl

curl https://api.llmstudio.dev/v1/chat/completions \
  -H "Authorization: Bearer $LLM_STUDIO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "studio/qwen3-0.6b",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

4. Try a BYOK model (optional)

Connect a provider key under Settings → Providers, then call any of that provider's models the same way -- just change model.

Terminal

curl https://api.llmstudio.dev/v1/chat/completions \
  -H "Authorization: Bearer $LLM_STUDIO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-5.1-mini",
    "messages": [{"role": "user", "content": "Hello"}]
  }'