## Run inference with free-form payload

`inference.create(InferenceCreateParams**kwargs)  -> InferenceCreateResponse`

**post** `/v5/inference`

Runs a model using a free-form, vendor-native request payload rather than a fixed OpenAI schema.

Use this endpoint when the target model does not fit the OpenAI chat, responses, or
text-completion contracts: the `args` field is an arbitrary dict passed straight through to the
selected vendor gateway, and the reply is returned inside `response` as arbitrary JSON (object,
array, string, number, or boolean). Prefer /v5/chat/completions, /v5/responses, or /v5/completions
when your request matches one of those OpenAI-standard shapes, since those return typed OpenAI
response objects. The model is chosen from the `model` field formatted as `vendor/name`, which
selects the per-vendor inference gateway. When the request enables streaming, the response is sent
as server-sent events with each chunk wrapped as a `generic_inference.chunk` object; otherwise a
single `generic_inference` object is returned.

### Parameters

- `model: str`

  model specified as `vendor/name` (ex. openai/gpt-5)

- `args: Optional[Dict[str, object]]`

  Arguments passed into model

- `inference_configuration: Optional[LaunchInferenceConfigurationParam]`

  Vendor specific configuration

  - `num_retries: Optional[int]`

  - `timeout_seconds: Optional[int]`

### Returns

- `InferenceCreateResponse`

  - `class InferenceResponse: …`

    - `response: Union[Dict[str, object], List[object], str, 3 more]`

      - `Dict[str, object]`

      - `List[object]`

      - `str`

      - `float`

      - `bool`

    - `object: Optional[Literal["generic_inference"]]`

      - `"generic_inference"`

  - `class InferenceResponseChunk: …`

    - `response: Union[Dict[str, object], List[object], str, 3 more]`

      - `Dict[str, object]`

      - `List[object]`

      - `str`

      - `float`

      - `bool`

    - `object: Optional[Literal["generic_inference.chunk"]]`

      - `"generic_inference.chunk"`

### Example

```python
import os
from scale_gp_beta import SGPClient

client = SGPClient(
    api_key=os.environ.get("SGP_API_KEY"),  # This is the default and can be omitted
)
inference = client.inference.create(
    model="model",
)
print(inference)
```

#### Response

```json
{
  "response": {
    "foo": "bar"
  },
  "object": "generic_inference"
}
```