--- type: api title: Create an Anthropic inference endpoint description: Create an inference endpoint to perform an inference task with the `anthropic` service. url: https://www.elastic.co/elastic/docs-builder/docs/4493/api/doc/elasticsearch/v8/operation/operation-inference-put-anthropic resource: https://www.elastic.co/elastic/docs-builder/docs/4493/api/doc/elasticsearch/v8/operation/operation-inference-put-anthropic products: - Elasticsearch --- # Create an Anthropic inference endpoint Availability: Generally available since 8.16 ## Paths - `PUT` `/_inference/{task_type}/{anthropic_inference_id}` #### Path parameters - `task_type` (enum) — required The task type. The only valid task type for the model to perform is `completion`. Values: `completion` - `anthropic_inference_id` (string) — required The unique identifier of the inference endpoint. ## Description Create an inference endpoint to perform an inference task with the `anthropic` service. ## Required authorization - Cluster privileges: `manage_inference` ## Authentication - Api key: `Authorization: ` Elasticsearch APIs support key-based authentication. You must create an API key and use the encoded value in the request header. For example: ``` curl -X GET "${ES_URL}/_cat/indices?v=true" \ -H "Authorization: ApiKey ${API_KEY}" ``` To get API keys, use the `/_security/api_key` APIs. - Basic: `Authorization: Basic ` - Bearer: `Authorization: Bearer ` Elasticsearch APIs support the use of bearer tokens in the `Authorization` HTTP header to authenticate with the API. For examples, refer to [Token-based authentication services](https://www.elastic.co/guide/en/elasticsearch/reference/current/token-authentication-services.html) ## Query string parameters - `timeout` (string · default: 30s) — optional Specifies the amount of time to wait for the inference endpoint to be created. ## Request body `application/json` - `chunking_settings` (object) — optional The chunking configuration object. - `max_chunk_size` (number · default: 250) — optional The maximum size of a chunk in words. This value cannot be higher than `300` or lower than `20` (for `sentence` strategy) or `10` (for `word` strategy). - `overlap` (number · default: 100) — optional The number of overlapping words for chunks. It is applicable only to a `word` chunking strategy. This value cannot be higher than half the `max_chunk_size` value. - `sentence_overlap` (number · default: 1) — optional The number of overlapping sentences for chunks. It is applicable only for a `sentence` chunking strategy. It can be either `1` or `0`. - `strategy` (string · default: sentence) — optional The chunking strategy: `sentence` or `word`. - `service` (enum) — required The type of service supported for the specified task type. In this case, `anthropic`. Values: `anthropic` - `service_settings` (object) — required Settings used to install the inference model. These settings are specific to the `watsonxai` service. - `api_key` (string) — required A valid API key for the Anthropic API. - `model_id` (string) — required The name of the model to use for the inference task. Refer to the Anthropic documentation for the list of supported models. - `rate_limit` (object) — optional This setting helps to minimize the number of rate limit errors returned from Anthropic. By default, the `anthropic` service sets the number of requests allowed per minute to 50. - `requests_per_minute` (number) — optional The number of requests allowed per minute. - `task_settings` (object) — optional Settings to configure the inference task. These settings are specific to the task type you specified. - `max_tokens` (number) — required For a `completion` task, it is the maximum number of tokens to generate before stopping. - `temperature` (number) — optional For a `completion` task, it is the amount of randomness injected into the response. For more details about the supported range, refer to Anthropic documentation. - `top_k` (number) — optional For a `completion` task, it specifies to only sample from the top K options for each subsequent token. It is recommended for advanced use cases only. You usually only need to use `temperature`. - `top_p` (number) — optional For a `completion` task, it specifies to use Anthropic's nucleus sampling. In nucleus sampling, Anthropic computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches the specified probability. You should either alter `temperature` or `top_p`, but not both. It is recommended for advanced use cases only. You usually only need to use `temperature`. ## Response `application/json` - `chunking_settings` (object) Chunking configuration object - `max_chunk_size` (number · default: 250) The maximum size of a chunk in words. This value cannot be higher than `300` or lower than `20` (for `sentence` strategy) or `10` (for `word` strategy). - `overlap` (number · default: 100) The number of overlapping words for chunks. It is applicable only to a `word` chunking strategy. This value cannot be higher than half the `max_chunk_size` value. - `sentence_overlap` (number · default: 1) The number of overlapping sentences for chunks. It is applicable only for a `sentence` chunking strategy. It can be either `1` or `0`. - `strategy` (string · default: sentence) The chunking strategy: `sentence` or `word`. - `service` (string) The service type - `service_settings` (object) Settings specific to the service - `task_settings` (object) Task settings specific to the service and task type - `inference_id` (string) The inference Id - `task_type` (enum) The task type Values: `completion` ## Code examples #### Console ```console PUT _inference/completion/anthropic_completion { "service": "anthropic", "service_settings": { "api_key": "Anthropic-Api-Key", "model_id": "Model-ID" }, "task_settings": { "max_tokens": 1024 } } ``` #### JavaScript ```javascript const response = await client.inference.put({ task_type: "completion", inference_id: "anthropic_completion", inference_config: { service: "anthropic", service_settings: { api_key: "Anthropic-Api-Key", model_id: "Model-ID", }, task_settings: { max_tokens: 1024, }, }, }); ``` #### Python ```python resp = client.inference.put( task_type="completion", inference_id="anthropic_completion", inference_config={ "service": "anthropic", "service_settings": { "api_key": "Anthropic-Api-Key", "model_id": "Model-ID" }, "task_settings": { "max_tokens": 1024 } }, ) ``` #### curl ```curl curl -X PUT "$ELASTICSEARCH_URL/_inference/completion/anthropic_completion" \ -H "Authorization: ApiKey $ELASTIC_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "service": "anthropic", "service_settings": { "api_key": "Anthropic-Api-Key", "model_id": "Model-ID" }, "task_settings": { "max_tokens": 1024 } }' ``` #### Java ```java client.inference().put(p -> p .inferenceId("anthropic_completion") .taskType(TaskType.Completion) .inferenceConfig(i -> i .service("anthropic") .serviceSettings(JsonData.fromJson("{\"api_key\":\"Anthropic-Api-Key\",\"model_id\":\"Model-ID\"}")) .taskSettings(JsonData.fromJson("{\"max_tokens\":1024}")) ) ); ``` #### C# ```c# var response = await client.Inference .PutAsync(new PutInferenceRequest() { InferenceId = "anthropic_completion", TaskType = TaskType.Completion, InferenceConfig = new() { Service = "anthropic", ServiceSettings = JsonSerializer.Deserialize(""" { "api_key": "Anthropic-Api-Key", "model_id": "Model-ID" } """), TaskSettings = JsonSerializer.Deserialize(""" { "max_tokens": 1024 } """) } }); ``` #### PHP ```php $resp = $client->inference()->put([ "task_type" => "completion", "inference_id" => "anthropic_completion", "body" => [ "service" => "anthropic", "service_settings" => [ "api_key" => "Anthropic-Api-Key", "model_id" => "Model-ID", ], "task_settings" => [ "max_tokens" => 1024, ], ], ]); ``` #### Ruby ```ruby response = client.inference.put( task_type: "completion", inference_id: "anthropic_completion", body: { "service": "anthropic", "service_settings": { "api_key": "Anthropic-Api-Key", "model_id": "Model-ID" }, "task_settings": { "max_tokens": 1024 } } ) ```