Response from raw inference. Returns the inference results along with metadata about the request.
| Name | Type | Description | Notes |
|---|---|---|---|
| data | object | ||
| provider | str | Provider that was used | |
| model | str | Model that was used | |
| tokens_used | Dict[str, int] | Token usage statistics (if available) | [optional] |
| latency_ms | float | Total inference latency in milliseconds | |
| cached | bool | Whether the response was served from semantic cache (vCache) | [optional] [default to False] |
from mixpeek.models.raw_inference_response import RawInferenceResponse
# TODO update the JSON string below
json = "{}"
# create an instance of RawInferenceResponse from a JSON string
raw_inference_response_instance = RawInferenceResponse.from_json(json)
# print the JSON string representation of the object
print(RawInferenceResponse.to_json())
# convert the object into a dict
raw_inference_response_dict = raw_inference_response_instance.to_dict()
# create an instance of RawInferenceResponse from a dict
raw_inference_response_from_dict = RawInferenceResponse.from_dict(raw_inference_response_dict)