Skip to content

Inference

Run inference with free-form payload
inference.create(InferenceCreateParams**kwargs) -> InferenceCreateResponse
POST/v5/inference
ModelsExpand Collapse
class InferenceResponse: …
response: Union[Dict[str, object], List[object], str, 3 more]
One of the following:
Dict[str, object]
List[object]
str
float
bool
object: Optional[Literal["generic_inference"]]
class InferenceResponseChunk: …
response: Union[Dict[str, object], List[object], str, 3 more]
One of the following:
Dict[str, object]
List[object]
str
float
bool
object: Optional[Literal["generic_inference.chunk"]]
class LaunchInferenceConfiguration: …
num_retries: Optional[int]
timeout_seconds: Optional[int]
One of the following:
class InferenceResponse: …
response: Union[Dict[str, object], List[object], str, 3 more]
One of the following:
Dict[str, object]
List[object]
str
float
bool
object: Optional[Literal["generic_inference"]]
class InferenceResponseChunk: …
response: Union[Dict[str, object], List[object], str, 3 more]
One of the following:
Dict[str, object]
List[object]
str
float
bool
object: Optional[Literal["generic_inference.chunk"]]