---
title: "Deploy model to endpoint"
method: POST
path: "/management/v1/endpoints/{endpoint_id}:deployModel"
---

# Deploy model to endpoint

`POST /management/v1/endpoints/{endpoint_id}:deployModel`

## Request

- Base URL: `https://api.cerebras.ai`
- URL: `https://api.cerebras.ai/management/v1/endpoints/{endpoint_id}:deployModel`
- 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"}] }' ```

## Request body

- EndpointDeployModelRequest
  - `model` string, required: Model version name in the format of `orgs/<org_name>/models/<model_arch_id>/versions/<version_id>`, where `<version_id>` can be an integer version ID or a model version alias.

## Response `200`

Successful Response

- EndpointDeployResponse: Long-running operation returned when a deployment is created behind an endpoint.
  - `name` string, required: Operation name for API compatibility. Its value is the deployment UUID and matches `response.deployment_id` when `response` is present.
  - `done` boolean, required: Whether the operation is complete.
  - `response` EndpointDeploymentOperation
    - `deployment_id` string, required: UUID for the deployment record.
    - `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"}] }' ```
    - `org_name` string, required: Owning organization for the deployment.
    - `model_arch_id` string, required: Name of the model architecture (e.g. `llama3.1-8b`, `gpt-oss-120b`).
    - `version_id` integer, required: Version identifier for the deployed model.
    - `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 record was created.
    - `updated` integer, required: Unix timestamp (in seconds) when the deployment record was last updated.
    - `rollout_status` 'not_started' | 'in_progress' | 'rolling_back' | 'rolled_back' | 'done' | 'error' | 'cancelled': 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.

---

[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)