---
title: "Retrieve endpoint status"
method: GET
path: "/management/v1/endpoints/{endpoint_id}"
---

# Retrieve endpoint status

`GET /management/v1/endpoints/{endpoint_id}`

## Request

- Base URL: `https://api.cerebras.ai`
- URL: `https://api.cerebras.ai/management/v1/endpoints/{endpoint_id}`
- Auth: HTTP bearer

## Path parameters

- `endpoint_id` string, required: Unique identifier for the endpoint. It is used as the [`model`](https://inference-docs.cerebras.ai/api-reference/chat-completions#param-model) field when making an inference request. Example: `my-org-gpt-oss-120b` ```bash curl --location 'https://api.cerebras.ai/v1/chat/completions' \ --header 'Content-Type: application/json' \ --header "Authorization: Bearer ${CEREBRAS_API_KEY}" \ --data '{ "model": "my-org-gpt-oss-120b", "messages": [{"content": "Hello!", "role": "user"}] }' ```

## Response `200`

Successful Response

- EndpointStatusResponse: A stable endpoint and the deployment records currently associated with it.
  - `name` string, required: Stable endpoint ID (e.g. `my-org-gpt-oss-120b`). This field is named `name` for API compatibility.
  - `model_arch_id` string, required: Name of the model architecture (e.g. `llama3.1-8b`, `gpt-oss-120b`).
  - `deployed_models` DeployedModel[], required: Deployment records currently associated with this endpoint. The field name is retained for API compatibility.
    - `id` string, required: Deployment ID for this running model version. This is the UUID generated when the deployment is created.
    - `model` string, required: Model version resource name in the format of `orgs/<org_name>/models/<model_arch_id>/versions/<version_id>`.
    - `version_alias` string, nullable: Original version reference from deploy request (alias or integer version ID as specified by user).
    - `created` integer, required: Unix timestamp (in seconds) when the deployment was created.
    - `state` 'not_started' | 'in_progress' | 'rolling_back' | 'rolled_back' | 'done' | 'error' | 'cancelled', required: Deployment rollout states for database storage.
    - `max_unavailable_replicas` integer, nullable: Maximum number of replicas that can be unavailable during rollout.
    - `rollout_replicas_updated` integer, nullable: Number of replicas that have been updated in the rollout.
    - `rollout_total_replicas` integer, nullable: Total number of replicas in the deployment.
    - `rollout_error_message` string, nullable: Error message from the rollout, if any.
  - `managing_org_name` string, nullable: Organization that has management access to this endpoint.
  - `created` integer, required: Unix timestamp (in seconds) when the endpoint was created.
  - `updated` integer, required: Unix timestamp (in seconds) when the endpoint was last updated.

---

[API](https://skmtc.dev/cerebras/apis/endpoint-management-orchestrator-api.md) - [All operations](https://skmtc.dev/cerebras/apis/endpoint-management-orchestrator-api/llms.txt) - [OpenAPI document](https://skmtc.dev/cerebras/apis/endpoint-management-orchestrator-api/revisions/1df093ca8f41?raw)