Documentation | Inference › create

API Reference

Evaluation Items

Generic Inference

Inference

InferenceResource

Methods

client.inference.create() ->

InferenceCreateResponse

post/v5/inference

Generic Inference

Parameters

model: str

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

args: Optional[Dict[str,

]]

Arguments passed into model

inference_configuration: Optional[

InferenceConfiguration

]

Vendor specific configuration

num_retries: Optional[int]

timeout_seconds: Optional[int]

Returns

InferenceCreateResponse =

InferenceCreateResponse

InferenceResponse

InferenceResponseChunk

Request example

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)

200Example

{
  "response": {},
  "object": "generic_inference"
}

Domain types

class InferenceResponse: ...

class InferenceResponseChunk: ...