# nodus inference

> Call hosted models: list them, send a chat completion and read a request's receipt

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

## nodus inference

Call hosted models: list them, send a chat completion and read a request’s receipt

### Synopsis

inference talks to the OpenAI-compatible data plane of the current context with its credential: the inference host of the API (inference. for api., else the API host itself), or –base-url.

### Options

```plaintext
      --base-url string   Inference origin (default: derived from the API URL)
  -h, --help              help for inference
```

### 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](https://nodus-platform-site.pages.dev/docs/reference/cli/nodus/) - Run compute Jobs on Nodus
* [nodus inference chat](https://nodus-platform-site.pages.dev/docs/reference/cli/nodus_inference_chat/) - Send one chat completion and print the answer; the request id and charge go to stderr
* [nodus inference models](https://nodus-platform-site.pages.dev/docs/reference/cli/nodus_inference_models/) - List the models you can call now
* [nodus inference receipt](https://nodus-platform-site.pages.dev/docs/reference/cli/nodus_inference_receipt/) - Show what one inference request was charged (receipts are kept 30 days)