Elastic

Elastic Inference API

Inference APIs enable you to use certain services, such as built-in machine learning models (ELSER, E5), models uploaded through Eland, Cohere, OpenAI, Azure, Google AI Studio or Hugging Face. For built-in models and models uploaded through Eland, the inference APIs offer an alternative way to use and manage trained models. However, if you do not plan to use the inference APIs to use these models or if you want to use non-NLP models, use the machine learning trained model APIs.

GitHub OpenAPI

Operations 43

POST /_inference/chat_completion/{inference_id}/_stream Perform chat completion inference on the service #
POST /_inference/completion/{inference_id} Perform completion inference on the service #
GET /_inference/{inference_id} Get an inference endpoint #
PUT /_inference/{inference_id} Create an inference endpoint #
POST /_inference/{inference_id} Perform inference on the service #
DELETE /_inference/{inference_id} Delete an inference endpoint #
GET /_inference/{task_type}/{inference_id} Get an inference endpoint #
PUT /_inference/{task_type}/{inference_id} Create an inference endpoint #
POST /_inference/{task_type}/{inference_id} Perform inference on the service #
DELETE /_inference/{task_type}/{inference_id} Delete an inference endpoint #
POST /_inference/embedding/{inference_id} Perform dense embedding inference on the service #
GET /_inference Get an inference endpoint #
PUT /_inference/{task_type}/{ai21_inference_id} Create a AI21 inference endpoint #
PUT /_inference/{task_type}/{alibabacloud_inference_id} Create an AlibabaCloud AI Search inference endpoint #
PUT /_inference/{task_type}/{amazonbedrock_inference_id} Create an Amazon Bedrock inference endpoint #
PUT /_inference/{task_type}/{amazonsagemaker_inference_id} Create an Amazon SageMaker inference endpoint #
PUT /_inference/{task_type}/{anthropic_inference_id} Create an Anthropic inference endpoint #
PUT /_inference/{task_type}/{azureaistudio_inference_id} Create an Azure AI studio inference endpoint #
PUT /_inference/{task_type}/{azureopenai_inference_id} Create an Azure OpenAI inference endpoint #
PUT /_inference/{task_type}/{cohere_inference_id} Create a Cohere inference endpoint #
PUT /_inference/{task_type}/{contextualai_inference_id} Create an Contextual AI inference endpoint #
PUT /_inference/{task_type}/{custom_inference_id} Create a custom inference endpoint #
PUT /_inference/{task_type}/{deepseek_inference_id} Create a DeepSeek inference endpoint #
PUT /_inference/{task_type}/{elasticsearch_inference_id} Create an Elasticsearch inference endpoint #
PUT /_inference/{task_type}/{elser_inference_id} Create an ELSER inference endpoint #
PUT /_inference/{task_type}/{googleaistudio_inference_id} Create an Google AI Studio inference endpoint #
PUT /_inference/{task_type}/{googlevertexai_inference_id} Create a Google Vertex AI inference endpoint #
PUT /_inference/{task_type}/{groq_inference_id} Create a Groq inference endpoint #
PUT /_inference/{task_type}/{huggingface_inference_id} Create a Hugging Face inference endpoint #
PUT /_inference/{task_type}/{jinaai_inference_id} Create an JinaAI inference endpoint #
PUT /_inference/{task_type}/{llama_inference_id} Create a Llama inference endpoint #
PUT /_inference/{task_type}/{mistral_inference_id} Create a Mistral inference endpoint #
PUT /_inference/{task_type}/{nvidia_inference_id} Create an Nvidia inference endpoint #
PUT /_inference/{task_type}/{openai_inference_id} Create an OpenAI inference endpoint #
PUT /_inference/{task_type}/{openshiftai_inference_id} Create an OpenShift AI inference endpoint #
PUT /_inference/{task_type}/{voyageai_inference_id} Create a VoyageAI inference endpoint #
PUT /_inference/{task_type}/{watsonx_inference_id} Create a Watsonx inference endpoint #
POST /_inference/rerank/{inference_id} Perform reranking inference on the service #
POST /_inference/sparse_embedding/{inference_id} Perform sparse embedding inference on the service #
POST /_inference/completion/{inference_id}/_stream Perform streaming completion inference on the service #
POST /_inference/text_embedding/{inference_id} Perform text embedding inference on the service #
PUT /_inference/{inference_id}/_update Update an inference endpoint #
PUT /_inference/{task_type}/{inference_id}/_update Update an inference endpoint #

Documentation

📖
Documentation
https://www.elastic.co/docs/api/doc/elasticsearch
📖
Documentation
https://www.elastic.co/docs/api/doc/kibana
📖
Documentation
https://www.elastic.co/docs/api/doc/cloud

Specifications

⚙
OpenAPI
https://raw.githubusercontent.com/api-evangelist/elastic/refs/heads/main/openapi/elastic-inference-api-openapi.yml

Schemas & Data

📊
JSONSchema
https://raw.githubusercontent.com/api-evangelist/elastic/refs/heads/main/json-schema/elastic-saved-object-schema.json

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this
  • find_apisBrowse and filter every API in the catalog.
  • get_api_artifactsOne API's artifacts, grouped by type.
  • get_openapiThe primary OpenAPI for this API.
  • find_similar_apisAPIs that look like this one.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This API 
curl "https://apis.io/api/v1/apis/elastic-inference-api"
All apis 
curl "https://apis.io/api/v1/apis?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

elastic-inference-api-openapi.yml Raw ↑ 
openapi: 3.2.0
info:
  title: Elasticsearch Inference API
  description: 'Elasticsearch provides REST APIs that are used by the UI components and can be called directly to configure and access Elasticsearch features.

    ## Documentation source and versions

    This documentation is derived from the main branch of the elasticsearch-specification repository. It is provided under license Attribution-NonCommercial-NoDerivatives 4.0 International.

    This documentation contains work-in-progress information for future Elastic Stack releases.'
  license:
    name: Apache 2.0
    url: https://github.com/elastic/elasticsearch-specification/blob/main/LICENSE
  version: ''
security:
- apiKeyAuth: []
- basicAuth: []
- bearerAuth: []
tags:


# --- truncated at 32 KB (439 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/elastic/refs/heads/main/openapi/elastic-inference-api-openapi.yml