Delete an inference endpoint Generally available; Added in 8.11.0

DELETE /_inference/{task_type}/{inference_id}
Api key auth Basic auth Bearer auth

All methods and paths for this operation:

DELETE /_inference/{inference_id}

DELETE /_inference/{task_type}/{inference_id}

This API requires the manage_inference cluster privilege (the built-in inference_admin role grants this privilege).

Path parameters

  • task_type string Required

    The task type

    Values are sparse_embedding, text_embedding, rerank, completion, or chat_completion.

  • inference_id string Required

    The inference identifier.

Query parameters

  • dry_run boolean

    When true, checks the semantic_text fields and inference processors that reference the endpoint and returns them in a list, but does not delete the endpoint.

  • force boolean

    When true, the inference endpoint is forcefully deleted even if it is still being used by ingest processors or semantic text fields.

Responses

  • 200 application/json
    Hide response attributes Show response attributes object

    Acknowledged response. For dry_run, contains the list of pipelines which reference the inference endpoint

    • acknowledged boolean Required

      For a successful response, this value is always true. On failure, an exception is returned instead.

    • pipelines array[string] Required
DELETE /_inference/{task_type}/{inference_id} 
DELETE /_inference/sparse_embedding/my-elser-model 
resp = client.inference.delete( task_type="sparse_embedding", inference_id="my-elser-model", )
const response = await client.inference.delete({ task_type: "sparse_embedding", inference_id: "my-elser-model", });
response = client.inference.delete( task_type: "sparse_embedding", inference_id: "my-elser-model" )
$resp = $client->inference()->delete([ "task_type" => "sparse_embedding", "inference_id" => "my-elser-model", ]);
curl -X DELETE -H "Authorization: ApiKey $ELASTIC_API_KEY" "$ELASTICSEARCH_URL/_inference/sparse_embedding/my-elser-model"
client.inference().delete(d -> d .inferenceId("my-elser-model") .taskType(TaskType.SparseEmbedding) );