# Elastic Stack (ELK Stack) Inference API

**Canonical:** https://apis.io/apis/elk-stack/elk-stack-inference-api/  
**Provider:** Elastic Stack (ELK Stack) — https://apis.io/providers/elk-stack/  
**Base URL:** https://{elasticsearch_endpoint}  
**Documentation:** https://www.elastic.co/docs/api/doc/elasticsearch/

Elastic Stack (ELK Stack) Inference API is one of 132 APIs that [Elastic Stack (ELK Stack)](https://apis.io/providers/elk-stack/) publishes on the [APIs.io](https://apis.io/) network, described by a machine-readable OpenAPI specification. Tagged areas include Inference. The published artifact set on APIs.io includes an OpenAPI specification, API documentation, and an API reference.

The inference API from Elastic Stack (ELK Stack) — 40 operation(s) for inference.

## Operations (48)

| Method | Path | Summary |
|---|---|---|
| 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 |
| GET | `/_inference/_region_policy` | Get the inference region policy |
| PUT | `/_inference/_region_policy` | Create or update the inference region policy |
| DELETE | `/_inference/_region_policy` | Delete the inference region policy |
| POST | `/_inference/embedding/{inference_id}` | Perform dense embedding inference on the service |
| GET | `/_inference` | Get an inference endpoint |
| GET | `/_inference/{task_type}/_all` | 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}/{fireworksai_inference_id}` | Create a Fireworks AI 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 |

## Machine-readable artifacts (8)

- **OpenAPI** — https://raw.githubusercontent.com/api-evangelist/elk-stack/refs/heads/main/openapi/elk-stack-inference-api-openapi.yml
- **Documentation** — https://www.elastic.co/docs/reference/elasticsearch
- **APIReference** — https://www.elastic.co/docs/api/doc/elasticsearch/
- **SourceCode** — https://github.com/elastic/elasticsearch-specification
- **Documentation** — https://www.elastic.co/docs/reference/kibana
- **APIReference** — https://www.elastic.co/docs/api/doc/kibana/
- **SourceCode** — https://github.com/elastic/kibana
- **ToolCrosswalk** — https://raw.githubusercontent.com/api-evangelist/elk-stack/refs/heads/main/mcp/elk-stack-tool-crosswalk.yml

## Other Elastic Stack (ELK Stack) APIs (12)

- [Elastic Cloud API](https://apis.io/apis/elk-stack/elastic-cloud-api/)
- [Elastic Stack (ELK Stack) Accounts API](https://apis.io/apis/elk-stack/elk-stack-accounts-api/)
- [Elastic Stack (ELK Stack) Actions API](https://apis.io/apis/elk-stack/elk-stack-actions-api/)
- [Elastic Stack (ELK Stack) agent builder API](https://apis.io/apis/elk-stack/elk-stack-agent-builder-api/)
- [Elastic Stack (ELK Stack) Alerting API](https://apis.io/apis/elk-stack/elk-stack-alerting-api/)
- [Elastic Stack (ELK Stack) Alerting V2 API](https://apis.io/apis/elk-stack/elk-stack-alerting-v2-api/)
- [Elastic Stack (ELK Stack) Analytics API](https://apis.io/apis/elk-stack/elk-stack-analytics-api/)
- [Elastic Stack (ELK Stack) APM agent configuration API](https://apis.io/apis/elk-stack/elk-stack-apm-agent-configuration-api/)
- [Elastic Stack (ELK Stack) APM agent keys API](https://apis.io/apis/elk-stack/elk-stack-apm-agent-keys-api/)
- [Elastic Stack (ELK Stack) APM annotations API](https://apis.io/apis/elk-stack/elk-stack-apm-annotations-api/)
- [Elastic Stack (ELK Stack) APM server schema API](https://apis.io/apis/elk-stack/elk-stack-apm-server-schema-api/)
- [Elastic Stack (ELK Stack) APM sourcemaps API](https://apis.io/apis/elk-stack/elk-stack-apm-sourcemaps-api/)

## Tags

Inference

---

Profiled by [API Evangelist](https://apievangelist.com) and published on [APIs.io](https://apis.io/apis/elk-stack/elk-stack-inference-api/). The API's provider profile, Kin Score and agent-readiness rating are at https://apis.io/providers/elk-stack/.