Update a managed ML model (instance admin)

curl --request PATCH \
  --url https://paradigm.lighton.ai/api/v3/instance/ml-models/{uuid} \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "name": "<string>",
  "technical_name": "<string>",
  "litellm_model": "<string>",
  "model_type": "<string>",
  "endpoint": "<string>",
  "max_model_len": 123,
  "enabled": true,
  "default": true,
  "parser": true,
  "is_default_reranker": true,
  "deployment_type": "<string>",
  "use_vllm_guided_choice": true
}
'

import requests

url = "https://paradigm.lighton.ai/api/v3/instance/ml-models/{uuid}"

payload = {
    "name": "<string>",
    "technical_name": "<string>",
    "litellm_model": "<string>",
    "model_type": "<string>",
    "endpoint": "<string>",
    "max_model_len": 123,
    "enabled": True,
    "default": True,
    "parser": True,
    "is_default_reranker": True,
    "deployment_type": "<string>",
    "use_vllm_guided_choice": True
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.patch(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'PATCH',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    name: '<string>',
    technical_name: '<string>',
    litellm_model: '<string>',
    model_type: '<string>',
    endpoint: '<string>',
    max_model_len: 123,
    enabled: true,
    default: true,
    parser: true,
    is_default_reranker: true,
    deployment_type: '<string>',
    use_vllm_guided_choice: true
  })
};

fetch('https://paradigm.lighton.ai/api/v3/instance/ml-models/{uuid}', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

{
  "id": "d612ede5-16b6-4d7b-b01b-5afb873b26bb",
  "name": "alfred-ft5",
  "technical_name": "alfred-ft5",
  "litellm_model": "hosted_vllm/alfred-ft5",
  "model_type": "Large Language Model",
  "endpoint": "http://models-gra11-afe6f177.lighton.ai:30424/v1/",
  "max_model_len": 32768,
  "deployment_type": "Self-Hosted",
  "enabled": true,
  "is_default": false,
  "is_parser": false,
  "is_default_reranker": false,
  "use_vllm_guided_choice": true,
  "start_messages_template": null,
  "health": {
    "status": "healthy",
    "is_healthy": true,
    "last_checked_at": "2026-08-12T09:31:44.512000Z"
  }
}

{
  "detail": "Instance admin access required."
}

{
  "detail": "ML model d612ede5-16b6-4d7b-b01b-5afb873b26bb not found."
}

{
  "detail": "System is under maintenance.",
  "error": "service_maintenance",
  "mode": "full_shutdown",
  "reason": "<string>",
  "started_at": "2023-11-07T05:31:56Z",
  "endpoint_category_names": [
    "<string>"
  ]
}

PATCH

api

instance

ml-models

{uuid}

Update a managed ML model (instance admin)

curl --request PATCH \
  --url https://paradigm.lighton.ai/api/v3/instance/ml-models/{uuid} \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "name": "<string>",
  "technical_name": "<string>",
  "litellm_model": "<string>",
  "model_type": "<string>",
  "endpoint": "<string>",
  "max_model_len": 123,
  "enabled": true,
  "default": true,
  "parser": true,
  "is_default_reranker": true,
  "deployment_type": "<string>",
  "use_vllm_guided_choice": true
}
'

import requests

url = "https://paradigm.lighton.ai/api/v3/instance/ml-models/{uuid}"

payload = {
    "name": "<string>",
    "technical_name": "<string>",
    "litellm_model": "<string>",
    "model_type": "<string>",
    "endpoint": "<string>",
    "max_model_len": 123,
    "enabled": True,
    "default": True,
    "parser": True,
    "is_default_reranker": True,
    "deployment_type": "<string>",
    "use_vllm_guided_choice": True
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.patch(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'PATCH',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    name: '<string>',
    technical_name: '<string>',
    litellm_model: '<string>',
    model_type: '<string>',
    endpoint: '<string>',
    max_model_len: 123,
    enabled: true,
    default: true,
    parser: true,
    is_default_reranker: true,
    deployment_type: '<string>',
    use_vllm_guided_choice: true
  })
};

fetch('https://paradigm.lighton.ai/api/v3/instance/ml-models/{uuid}', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

{
  "id": "d612ede5-16b6-4d7b-b01b-5afb873b26bb",
  "name": "alfred-ft5",
  "technical_name": "alfred-ft5",
  "litellm_model": "hosted_vllm/alfred-ft5",
  "model_type": "Large Language Model",
  "endpoint": "http://models-gra11-afe6f177.lighton.ai:30424/v1/",
  "max_model_len": 32768,
  "deployment_type": "Self-Hosted",
  "enabled": true,
  "is_default": false,
  "is_parser": false,
  "is_default_reranker": false,
  "use_vllm_guided_choice": true,
  "start_messages_template": null,
  "health": {
    "status": "healthy",
    "is_healthy": true,
    "last_checked_at": "2026-08-12T09:31:44.512000Z"
  }
}

{
  "detail": "Instance admin access required."
}

{
  "detail": "ML model d612ede5-16b6-4d7b-b01b-5afb873b26bb not found."
}

{
  "detail": "System is under maintenance.",
  "error": "service_maintenance",
  "mode": "full_shutdown",
  "reason": "<string>",
  "started_at": "2023-11-07T05:31:56Z",
  "endpoint_category_names": [
    "<string>"
  ]
}

Authorizations

Authorization

string

header

required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Path Parameters

uuid

string<uuid>

required

Body

name

string | null

Human-friendly display name.

technical_name

string | null

Unique technical identifier used for routing.

litellm_model

string | null

Underlying LiteLLM provider routing string (e.g. hosted_vllm/my-model). Distinct from technical_name — omit to keep the current value.

model_type

string | null

Model type (e.g. Large Language Model, Embedding Model).

endpoint

string | null

Model serving endpoint URL.

max_model_len

integer | null

Maximum context length in tokens.

enabled

boolean | null

Whether the model is active.

default

boolean | null

Whether this is the default generation model.

parser

boolean | null

Whether the model can be used as a parser.

is_default_reranker

boolean | null

Whether this is the default reranker.

deployment_type

string | null

Deployment type (Self-Hosted or External).

use_vllm_guided_choice

boolean | null

Use vLLM guided_choice for constrained decoding.

Response

string<uuid>

required

Unique ID for this model.

name

string

required

Display name.

technical_name

string

required

Instance-wide unique technical name used for routing.

model_type

string

required

Model type.

enabled

boolean

required

Whether the model is active instance-wide.

is_default

boolean

required

Whether this is the platform default generation model.

is_parser

boolean

required

Whether the model can be used as a parser.

is_default_reranker

boolean

required

Whether this is the default reranker.

use_vllm_guided_choice

boolean

required

Use vLLM guided_choice for constrained decoding.

health

object

required

Health of the model as of the last periodic gateway healthcheck. Read from cache — reading this endpoint never triggers a check.

Show child attributes

litellm_model

string | null

Underlying LiteLLM provider routing string (e.g. hosted_vllm/my-model).

endpoint

string | null

Model serving endpoint URL.

max_model_len

integer | null

Maximum context length in tokens.

deployment_type

string | null

Deployment type (Self-Hosted or External).

start_messages_template

string | null

Start messages template name.

Usage

Models

Workspaces

Users

User Groups

Companies

Update a managed ML model (instance admin)

Authorizations

Path Parameters

Body

Response