# nodus create inferenceendpoint

> Create a inferenceendpoint

Source: https://nodus-platform-site.pages.dev/docs/reference/cli/nodus_create_inferenceendpoint/
Build revision: 211ad9f836655b1c3a2668c4693e442471f28614

## nodus create inferenceendpoint

Create a inferenceendpoint

```plaintext
nodus create inferenceendpoint NAME [flags]
```

### Examples

```plaintext
  nodus create inferenceendpoint support-bot --model nodus/gpt-oss-120b --rpm 120 --max-cost 5
```

### Options

```plaintext
      --allowed-key stringArray     API key name allowed to call it (repeatable)
      --dry-run string[="server"]   server returns the estimate without creating; client prints the manifest (default "none")
  -h, --help                        help for inferenceendpoint
      --max-concurrent int          Open requests
      --max-cost string             Spend limit in USD
      --model string                Catalog model, as 'nodus inference models' lists them
  -o, --output string               Output format: name, json, yaml, or estimate (with --dry-run=server)
      --rpm int                     Requests per minute
      --tpm int                     Tokens per minute
```

### Options inherited from parent commands

```plaintext
      --context string   Context from the config file to use
      --org string       Organization (selects the context for that org)
  -p, --project string   Project to work in
  -v, --verbose          Log each API request (never credentials)
```

### SEE ALSO

* [nodus create](https://nodus-platform-site.pages.dev/docs/reference/cli/nodus_create/) - Create resources from manifests or with a typed generator