---
title: "Create Dedicated Endpoint"
method: POST
path: "/v0/dedicated_endpoints"
tags: ["dedicated-endpoints"]
---

# Create Dedicated Endpoint

`POST /v0/dedicated_endpoints`

## Query parameters

- `ai_project_id` string, nullable — Project ID to create endpoint

## Request body

- DedicatedEndpointCreateRequest
  - `name` string, required
  - `description` string
  - `model_name` string, required
  - `flavor_name` string, required
  - `gpu_type` 'gpu-l40s-d' | 'gpu-l40s-a' | 'gpu-h100-sxm' | 'gpu-h200-sxm' | 'gpu-b200-sxm' | 'gpu-b200-sxm-a' | 'gpu-b300-sxm', required
  - `region` 'eu-north1' | 'us-central1' | 'us-north1' | 'eu-west1' | 'eu-west2' | 'me-west1' | 'uk-south1' | 'tf-eu1' | 'tf-uk1' | 'tf-us1' | 'tf-us2' | 'tf-us3' | 'tf-us4' | 'tf-ca1', required
  - `gpu_count` integer, required
  - `custom_weights_id` string, nullable
  - `scaling` EndpointScaling, required
    - `min_replicas` integer, required
    - `max_replicas` integer, required

## Response `201`

Successful Response

- DedicatedEndpointCreationResponse
  - `endpoint` DedicatedEndpoint, required
    - `id` string, required
    - `name` string, required
    - `description` string, required
    - `enabled` boolean, required
    - `routing_key` string, required
    - `model_name` string, required
    - `flavor_name` string, required
    - `region` string, required
    - `gpu_type` 'gpu-l40s-d' | 'gpu-l40s-a' | 'gpu-h100-sxm' | 'gpu-h200-sxm' | 'gpu-b200-sxm' | 'gpu-b200-sxm-a' | 'gpu-b300-sxm', required
    - `gpu_count` integer, required
    - `custom_weights_id` string, nullable, required
    - `scaling` EndpointScaling, required
      - `min_replicas` integer, required
      - `max_replicas` integer, required
    - `deployment` EndpointDeploymentStatus, required
      - `ready_replicas` integer, required
      - `status` 'starting' | 'running' | 'updating' | 'stopping' | 'stopped' | 'error', required
      - `readiness` 'ready' | 'partially_ready' | 'not_ready', required
    - `created_at` string, date-time, required

## Other responses

- `422` — Validation Error

---

[API](https://skmtc.net/nebius/apis/nebius-openai-compatible-inference-api.md) · [All operations](https://skmtc.net/nebius/apis/nebius-openai-compatible-inference-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/nebius/nebius-openai-compatible-inference-api/versions/0fb323abba3c/schema)