> ## Documentation Index
> Fetch the complete documentation index at: https://vendo-mintlify-24213046.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Model credentials

> How the Vendo Cloud model gateway fills every model seat, which model names it serves, how to pin one, and what a keyless turn does.

Your Cloud key is the model credential. Leave the `models` slot unset and every
turn rides the console's gateway.

## How the gateway is wired

Managed inference is not a bespoke client. It is the stock `@ai-sdk/anthropic`
provider, pointed at the console instead of at Anthropic.

<Frame caption="One provider, one base URL swap. VENDO_API_KEY is the bearer token.">
  <svg viewBox="0 0 720 132" width="100%" role="img" aria-label="createVendo calls the stock Anthropic provider, which calls the console gateway at /api/v1">
    <g fill="none" stroke="currentColor" strokeOpacity="0.28" strokeWidth="1.25">
      <rect x="1" y="34" width="196" height="64" rx="12" />

      <rect x="262" y="34" width="196" height="64" rx="12" />

      <rect x="523" y="34" width="196" height="64" rx="12" />
    </g>

    <g fill="currentColor" fontFamily="ui-monospace, monospace" fontSize="12.5">
      <text x="20" y="62">createVendo()</text>
      <text x="281" y="62">@ai-sdk/anthropic</text>
      <text x="542" y="62">console.vendo.run</text>
    </g>

    <g fill="currentColor" fillOpacity="0.6" fontSize="11.5">
      <text x="20" y="82">your composition</text>
      <text x="281" y="82">stock provider, no fork</text>
      <text x="542" y="82">/api/v1 · Messages wire</text>
    </g>

    <g stroke="currentColor" strokeOpacity="0.45" strokeWidth="1.25" fill="none">
      <path d="M205 66 h48" />

      <path d="M243 61 l10 5 l-10 5" />

      <path d="M466 66 h48" />

      <path d="M504 61 l10 5 l-10 5" />
    </g>

    <g fill="currentColor" fillOpacity="0.6" fontSize="10.5" fontFamily="ui-monospace, monospace" textAnchor="middle">
      <text x="229" y="28">baseURL</text>
      <text x="490" y="28">VENDO\_API\_KEY</text>
    </g>
  </svg>
</Frame>

The console speaks the Anthropic Messages wire, which is the whole reason the
stock provider serves it.

<Note>
  Gateway traffic does not carry Vendo's deployment-identity headers, so
  inference never appears in the console's deployment inventory. Usage still
  meters.
</Note>

***

## Which model you get

The gateway serves the `vendo` family as literal model ids. The console maps
each name to a concrete model server-side, so a Cloud-keyed app can be retuned
without a client release.

| Name            | Seat it serves                                            |
| --------------- | --------------------------------------------------------- |
| `vendo`         | The `default` seat, and the default when no name is given |
| `vendo-apps`    | The `apps` seat, which writes the generated apps          |
| `vendo-review`  | The `review` seat, which grades the finished ones         |
| `vendo-judge`   | The `judge` seat, the guard's run/ask/block               |
| `vendo-extract` | Tool extraction, in the CLI                               |

Leave a seat unset and it takes its own family id above, so an empty `models`
block still puts each job on the name tuned for it.

Names pass through verbatim — nothing is translated on the client. That is also
how the `default` seat's three billed tiers work: `vendo-fast`, `vendo`, and
`vendo-strong`, at the rates on the
[Vendo Cloud](/production/vendo-cloud#pricing) page.

***

## Pinning a model

Two ways, and an explicit model object beats both.

```ts app/api/vendo/[...vendo]/route.ts highlight={2} theme={null}
const vendo = createVendo({
  models: { default: "vendo-strong" },
  auth: authJs(),
});
```

```bash .env.local highlight={1} theme={null}
VENDO_MODEL=vendo-strong
```

Precedence runs top to bottom: an explicit model object, then the environment
pin, then the configured string, then that seat's own family name.

Every other seat has a pin of its own — `VENDO_MODEL_APPS`,
`VENDO_MODEL_REVIEW`, `VENDO_MODEL_JUDGE`, and `VENDO_MODEL_EXTRACT`.

Passing your own AI SDK model object into `models` also works and always wins,
so Vendo runs without a Cloud key.

***

## If a seat has no model

Seats resolve lazily, on the first call that needs one. A missing credential
therefore surfaces on the first turn, not at boot, as
[`E-MODEL-001`](/production/troubleshooting/e-model-001).

A provider key sitting in your shell is a credential, not a selection — Vendo
never picks a provider for you. And if your product already runs its own agent
loop, Vendo's internal turns still need models of their own and will not borrow
yours; leaving the seats unset is what hands them the gateway.

***

## Verifying the model

`vendo doctor` names the credential the runtime will resolve. It reads your
environment and makes no model call.

```bash Terminal highlight={1} theme={null}
$ npx vendo doctor

ok: model credential: VENDO_API_KEY (Vendo Cloud)
```

A key that is set but malformed reports
[`E-CLOUD-001`](/production/troubleshooting/e-cloud-001).