Your first deployment

The full Creating deployments guide covers every provider, custom models, and every operation type. This page is the minimal path for your very first one: a known model from a first-class adapter, verified before you save it.

1. Pick a catalog model

Known models need no catalogEntry — their capabilities, limits, and pricing already live in the adapter's catalog. Browse src/adapters/<provider>/catalog.json in the repo, or just pick a model id you already know exists at the provider (e.g. gpt-5.5 for OpenAI).

2. Dry-run it

POST /admin/deployments/resolve validates and resolves the exact same body a real POST /admin/deployments would use, without saving anything or touching credentials encryption — safe to run repeatedly while you get the shape right:

curl -X POST "$GATEWAY/admin/deployments/resolve" \
  -H "Authorization: Bearer $MASTER_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "publicModel": "general",
    "adapterKey": "openai",
    "upstreamModel": "gpt-5.5",
    "credentials": { "apiKey": "sk-..." }
  }'

The response shows source: "catalog" (confirming it recognized the model — no catalogEntry needed), plus the resolved operations and transports. If source comes back "custom" instead, the model isn't in the catalog and you'll need to follow the custom-model path in Creating deployments instead.

3. Create it for real

Same body, real endpoint:

curl -X POST "$GATEWAY/admin/deployments" \
  -H "Authorization: Bearer $MASTER_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "publicModel": "general",
    "adapterKey": "openai",
    "upstreamModel": "gpt-5.5",
    "credentials": { "apiKey": "sk-..." }
  }'

4. Test it

With a virtual key (see Virtual keys) or the master key:

curl -X POST "$GATEWAY/v1/chat/completions" \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "model": "general", "messages": [{ "role": "user", "content": "Say hi" }] }'

What to read next

• Creating deployments — every provider, custom models, images/embeddings/audio.
• Routing — what happens once general has more than one deployment.
• Virtual keys — scoped, rate-limited client keys instead of the master key.