Create an Anthropic inference endpoint

PUT /_inference/{task_type}/{anthropic_inference_id}

Copy endpoint

Create an inference endpoint to perform an inference task with the anthropic service.

Required authorization

Cluster privileges: manage_inference

Parameters

path Path Parameters

Name	Type
`task_type` required The task type. The only valid task type for the model to perform is `completion`.	type InferenceTypesAnthropicTaskType = "completion"
`anthropic_inference_id` required The unique identifier of the inference endpoint.	type TypesId = string

query Query Parameters

Name	Type
`timeout` Specifies the amount of time to wait for the inference endpoint to be created.	type TypesDuration = string \| "-1" \| "0"

Request Body

application/json required

{ service:

InferenceTypesAnthropicServiceType

type InferenceTypesAnthropicServiceType = "anthropic"

;service_settings:

InferenceTypesAnthropicServiceSettings

interface InferenceTypesAnthropicServiceSettings {
api_key: string;
model_id: string;
rate_limit?: InferenceTypesRateLimitSetting;
}

;task_settings?:

InferenceTypesAnthropicTaskSettings

interface InferenceTypesAnthropicTaskSettings {
max_tokens: number;
temperature?: number;
top_k?: number;
top_p?: number;
}

; }

Responses

200 application/json

type InferenceTypesInferenceEndpointInfoAnthropic = interface InferenceTypesInferenceEndpoint {
chunking_settings?:

InferenceTypesInferenceChunkingSettings

Chunking configuration object

interface InferenceTypesInferenceChunkingSettings {
max_chunk_size?: number;
overlap?: number;
sentence_overlap?: number;
separator_group?: string;
separators?: string[];
strategy?: string;
}

;
service: string;
service_settings:

InferenceTypesServiceSettings

interface InferenceTypesServiceSettings {}

;
task_settings?:

InferenceTypesTaskSettings

interface InferenceTypesTaskSettings {}

;
} & { inference_id: string;task_type:

InferenceTypesTaskTypeAnthropic

type InferenceTypesTaskTypeAnthropic = "completion"

; }