Create an Anthropic inference endpoint

PUT /_inference/{task_type}/{anthropic_inference_id}

Auth

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

Required privileges

Cluster privileges manage_inference

Path parameters

task_type enum required: The task type. The valid task types for the model to perform are completion and chat_completion. NOTE: The chat_completion task type only supports streaming and only through the _stream API.; Values: completion chat_completion
anthropic_inference_id string required: The unique identifier of the inference endpoint.

Query parameters

timeout string · default: 30s: Specifies the amount of time to wait for the inference endpoint to be created.

Request body

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 anthropic service.
task_settings object: Settings to configure the inference task. These settings are specific to the task type you specified.

Response

application/json

chunking_settings object: The chunking configuration object. Applies only to the embedding, sparse_embedding and text_embedding task types. Not applicable to the rerank, completion, or chat_completion task types.
service string required: The service type
service_settings object required: Settings specific to the service
task_settings object: Task settings specific to the service and task type
inference_id string required: The inference Id
task_type enum required: The task type; Values: completion chat_completion

Examples

Request Console 1 / 8 languages

Run PUT _inference/chat_completion/anthropic_chat_completion to create an inference endpoint that performs a chat completion task.

Console Kibana Dev Tools

PUT _inference/chat_completion/anthropic_chat_completion
{
    "service": "anthropic",
    "service_settings": {
        "api_key": "Anthropic-Api-Key",
        "model_id": "claude-sonnet-4-5"
    },
    "task_settings": {
        "max_tokens": 1024
    }
}

JavaScript Elasticsearch JavaScript Client

const response = await client.inference.put({
  task_type: "chat_completion",
  inference_id: "anthropic_chat_completion",
  inference_config: {
    service: "anthropic",
    service_settings: {
      api_key: "Anthropic-Api-Key",
      model_id: "claude-sonnet-4-5",
    },
    task_settings: {
      max_tokens: 1024,
    },
  },
});

Python Elasticsearch Python Client

resp = client.inference.put(
    task_type="chat_completion",
    inference_id="anthropic_chat_completion",
    inference_config={
        "service": "anthropic",
        "service_settings": {
            "api_key": "Anthropic-Api-Key",
            "model_id": "claude-sonnet-4-5"
        },
        "task_settings": {
            "max_tokens": 1024
        }
    },
)

curl Shell

curl -X PUT "$ELASTICSEARCH_URL/_inference/chat_completion/anthropic_chat_completion" \
  -H "Authorization: ApiKey $ELASTIC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "service": "anthropic",
    "service_settings": {
      "api_key": "Anthropic-Api-Key",
      "model_id": "claude-sonnet-4-5"
    },
    "task_settings": {
      "max_tokens": 1024
    }
  }'

Java Elasticsearch Java Client

client.inference().put(p -> p
    .inferenceId("anthropic_chat_completion")
    .taskType(TaskType.ChatCompletion)
    .inferenceConfig(i -> i
        .service("anthropic")
        .serviceSettings(JsonData.fromJson("""
{"api_key":"Anthropic-Api-Key","model_id":"claude-sonnet-4-5"}
"""))
        .taskSettings(JsonData.fromJson("""
{"max_tokens":1024}
"""))
    )
);

C# Elasticsearch .NET Client

var response = await client.Inference
    .PutAsync(new PutInferenceRequest()
    {
        InferenceId = "anthropic_chat_completion",
        TaskType = TaskType.ChatCompletion,
        InferenceConfig = new()
        {
            Service = "anthropic",
            ServiceSettings = JsonSerializer.Deserialize<JsonElement>("""
            {
              "api_key": "Anthropic-Api-Key",
              "model_id": "claude-sonnet-4-5"
            }
            """),
            TaskSettings = JsonSerializer.Deserialize<JsonElement>("""
            {
              "max_tokens": 1024
            }
            """)
        }
    });

PHP Elasticsearch PHP Client

$resp = $client->inference()->put([
    "task_type" => "chat_completion",
    "inference_id" => "anthropic_chat_completion",
    "body" => [
        "service" => "anthropic",
        "service_settings" => [
            "api_key" => "Anthropic-Api-Key",
            "model_id" => "claude-sonnet-4-5",
        ],
        "task_settings" => [
            "max_tokens" => 1024,
        ],
    ],
]);

Ruby Elasticsearch Ruby Client

response = client.inference.put(
  task_type: "chat_completion",
  inference_id: "anthropic_chat_completion",
  body: {
    "service": "anthropic",
    "service_settings": {
      "api_key": "Anthropic-Api-Key",
      "model_id": "claude-sonnet-4-5"
    },
    "task_settings": {
      "max_tokens": 1024
    }
  }
)

Response

{
  "chunking_settings": {
    "max_chunk_size": 250,
    "overlap": 100,
    "sentence_overlap": 1,
    "separator_group": "string",
    "separators": [
      "string"
    ],
    "strategy": "sentence"
  },
  "service": "string",
  "service_settings": {},
  "task_settings": {},
  "inference_id": "string",
  "task_type": "completion"
}

Generated from the API spec

Request Console 1 / 8 languages

Run PUT _inference/completion/anthropic_completion to create an inference endpoint that performs a completion task.

Console Kibana Dev Tools

PUT _inference/completion/anthropic_completion
{
    "service": "anthropic",
    "service_settings": {
        "api_key": "Anthropic-Api-Key",
        "model_id": "Model-ID"
    },
    "task_settings": {
        "max_tokens": 1024
    }
}

JavaScript Elasticsearch JavaScript Client

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 Elasticsearch Python Client

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 Shell

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 Elasticsearch Java Client

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# Elasticsearch .NET Client

var response = await client.Inference
    .PutAsync(new PutInferenceRequest()
    {
        InferenceId = "anthropic_completion",
        TaskType = TaskType.Completion,
        InferenceConfig = new()
        {
            Service = "anthropic",
            ServiceSettings = JsonSerializer.Deserialize<JsonElement>("""
            {
              "api_key": "Anthropic-Api-Key",
              "model_id": "Model-ID"
            }
            """),
            TaskSettings = JsonSerializer.Deserialize<JsonElement>("""
            {
              "max_tokens": 1024
            }
            """)
        }
    });

PHP Elasticsearch PHP Client

$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 Elasticsearch Ruby Client

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
    }
  }
)

Response

{
  "chunking_settings": {
    "max_chunk_size": 250,
    "overlap": 100,
    "sentence_overlap": 1,
    "separator_group": "string",
    "separators": [
      "string"
    ],
    "strategy": "sentence"
  },
  "service": "string",
  "service_settings": {},
  "task_settings": {},
  "inference_id": "string",
  "task_type": "completion"
}

Generated from the API spec