Developer Management

Create New Endpoint

post/v1/developer/{developer_id}/create-endpoint

Request

  • Base URL: https://api.oneinfer.ai (the document declares no server; this is the origin it was published from)
  • URL: https://api.oneinfer.ai/v1/developer/{developer_id}/create-endpoint
  • Auth: HTTP bearer

Path parameters

developer_idstring required

Query parameters

provider_name'novita' | 'aws' | 'nebius_ai' | 'verda' | 'runpod' | 'vastai' | 'vultr' | 'azure' | 'e2e_networks' required

Request body

model_idstring nullable

HuggingFace model ID (e.g., 'Qwen/Qwen2.5-7B-Instruct')

endpoint_idstring nullable

Endpoint ID (auto-generated if not provided). If provided, uses existing endpoint instead of creating new one

instance_idstring nullable

Existing GPU instance ID to use as the deployment target

namestring nullable

Endpoint name (auto-generated if not provided)

max_concurrencyinteger nullable

Max concurrent requests

gpu_countinteger nullable

Number of GPUs

gpu_idstring nullable

GPU type ID

idle_timeout_secondsinteger
template_idstring nullable
huggingface_image_urlstring nullable
volume_sizenumber nullable

Additional volume size in GB (Verda: volume, Novita AI: network storage)

regionstring nullable

Deployment region

commandstring nullable

Container command/args

environmentobject nullable

Environment variables for the deployment

hf_tokenstring nullable

Hugging Face API token for private models

Response

Successful Response

unknown required

Changes

No recorded changes to this operation across all 1 revision of this API.