> ## Documentation Index
> Fetch the complete documentation index at: https://inference-docs.cerebras.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Deploy model to endpoint
This feature is in [Private Preview](/support/preview-releases). For access or more information, [contact us](https://www.cerebras.ai/contact) or reach out to your account representative.
Create a deployment of a model version behind a dedicated endpoint with the same underlying architecture. The endpoint remains the stable inference target while the deployment represents the running model version and serving configuration. The API queues the deployment operation and returns a deployment ID for tracking status.
## OpenAPI
````yaml post /management/v1/endpoints/{endpoint_id}:deployModel
openapi: 3.1.0
info:
title: Endpoint Management Orchestrator API
version: 1.0.0
servers:
- url: https://api.cerebras.ai
security:
- BearerAuth: []
paths:
/management/v1/endpoints/{endpoint_id}:deployModel:
post:
summary: Deploy model to endpoint
operationId: >-
deploy_model_to_endpoint_route_management_v1_endpoints__endpoint_id__deployModel_post
parameters:
- name: endpoint_id
in: path
required: true
schema:
type: string
title: Endpoint Id
description: >-
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"}]
}'
```
description: >-
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"}]
}'
```
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/EndpointDeployModelRequest'
examples:
deploy_model:
summary: Deploy a model version
value:
model: orgs/my-org/models/gpt-oss-120b/versions/1
deploy_by_alias:
summary: Deploy using version alias
value:
model: orgs/my-org/models/gpt-oss-120b/versions/production
responses:
'200':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/EndpointDeployResponse'
example:
name: 550e8400-e29b-41d4-a716-446655440000
done: false
response:
deployment_id: 550e8400-e29b-41d4-a716-446655440000
endpoint_id: my-org-gpt-oss-120b
org_name: my-org
model_arch_id: gpt-oss-120b
version_id: 1
created: 1736700000
updated: 1736700000
rollout_status: not_started
components:
schemas:
EndpointDeployModelRequest:
properties:
model:
type: string
title: Model
description: >-
Model version name in the format of
`orgs//models//versions/`,
where `` can be an integer version ID or a model version
alias.
additionalProperties: false
type: object
required:
- model
title: EndpointDeployModelRequest
EndpointDeployResponse:
description: >-
Long-running operation returned when a deployment is created behind an
endpoint.
properties:
name:
type: string
title: Name
description: >-
Operation name for API compatibility. Its value is the deployment
UUID and matches `response.deployment_id` when `response` is
present.
done:
type: boolean
title: Done
description: Whether the operation is complete.
response:
anyOf:
- $ref: '#/components/schemas/EndpointDeploymentOperation'
- type: 'null'
description: Deployment metadata captured at submission time.
additionalProperties: false
type: object
required:
- name
- done
title: EndpointDeployResponse
EndpointDeploymentOperation:
properties:
deployment_id:
type: string
title: Deployment Id
description: UUID for the deployment record.
endpoint_id:
type: string
title: Endpoint Id
description: >-
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:
type: string
title: Org Name
description: Owning organization for the deployment.
model_arch_id:
type: string
title: Model Arch Id
description: Name of the model architecture (e.g. `llama3.1-8b`, `gpt-oss-120b`).
version_id:
type: integer
title: Version Id
description: Version identifier for the deployed model.
version_alias:
anyOf:
- type: string
- type: 'null'
title: Version Alias
description: >-
Original version reference from deploy request (alias or integer
version ID as specified by user).
created:
type: integer
title: Created
description: Unix timestamp (in seconds) when the deployment record was created.
updated:
type: integer
title: Updated
description: >-
Unix timestamp (in seconds) when the deployment record was last
updated.
rollout_status:
anyOf:
- $ref: '#/components/schemas/DeploymentRolloutStatus'
- type: 'null'
description: Latest rollout status reported by the deployer, if any.
max_unavailable_replicas:
anyOf:
- type: integer
- type: 'null'
title: Max Unavailable Replicas
description: Maximum number of replicas that can be unavailable during rollout.
rollout_replicas_updated:
anyOf:
- type: integer
- type: 'null'
title: Rollout Replicas Updated
description: Number of replicas that have been updated in the rollout.
rollout_total_replicas:
anyOf:
- type: integer
- type: 'null'
title: Rollout Total Replicas
description: Total number of replicas in the deployment.
rollout_error_message:
anyOf:
- type: string
- type: 'null'
title: Rollout Error Message
description: Error message from the rollout, if any.
additionalProperties: false
type: object
required:
- deployment_id
- endpoint_id
- org_name
- model_arch_id
- version_id
- created
- updated
title: EndpointDeploymentOperation
DeploymentRolloutStatus:
type: string
enum:
- not_started
- in_progress
- rolling_back
- rolled_back
- done
- error
- cancelled
title: DeploymentRolloutStatus
description: Deployment rollout states for database storage.
securitySchemes:
BearerAuth:
type: http
scheme: bearer
description: >-
Management API key generated from the `Management API keys` section on
the `API keys` page at https://cloud.cerebras.ai. Use the format:
`Bearer `
````