Create a new model for a provider

POST

/v1/llm-providers/{provider_id}/models

• Production API

Parameters

Path Parameters

provider_id

required

string

Provider ID (prefixed, e.g., prov_…)

Request Body ^required

Request to create a new LLM model for a provider

object

capabilities

List of capabilities this model supports (e.g., “chat”, “vision”, “tools”).

Array<string>

Example

[
  "chat",
  "vision",
  "tools"
]

display_name

required

Human-readable display name for the model.

string

Example

GPT-4o

enabled

Whether this model should be enabled (visible in UI model pickers).

boolean

is_favorite

Whether this model should be marked as a favorite for quick access.

boolean

model_id

required

The model identifier used by the provider’s API (e.g., “gpt-4”, “claude-3-opus”).

string

Example

gpt-4o

Responses

201

Model created

Wrapper that adds self_url and view_url to a serialized resource.

Uses self_url (not url) for the API link to avoid collision with resources that already have a url field (e.g. McpServer).

object

capabilities

required

Array<string>

created_at

required

string format: date-time

display_name

required

string

enabled

required

Whether this model is enabled (visible in UI model pickers). All models are available via API regardless of this flag.

boolean

id

required

string

Example

model_01933b5a00007000800000000000001

is_favorite

required

boolean

model_id

required

string

provider_id

required

string

Example

provider_01933b5a00007000800000000000001

source

required

How the model was added to the system

string

Allowed values: manual discovered predefined

status

required

LLM model status

string

Allowed values: active disabled

updated_at

required

string format: date-time

self_url

required

Full API endpoint URL for this resource.

string

view_url

required

Full UI URL for viewing this resource.

string

400

Invalid provider ID

404

Provider not found

500

Internal error