Bulk-replace the entire model catalogue

curl --request PUT \
  --url https://{host}/v2/workspaces/slug:llm-gateway/webhooks/v1/models \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "models": [
    {
      "model_id": "<string>",
      "display": {},
      "capabilities": {},
      "limits": {},
      "failover": "<string>",
      "end_of_life": "2023-12-25",
      "dimensions": "<unknown>",
      "supported_dimensions": "<unknown>",
      "metrics": "<unknown>",
      "provider_config": "<unknown>",
      "pricing": "<unknown>",
      "tags": "<unknown>",
      "org_slugs": "<unknown>",
      "enabled": "<unknown>"
    }
  ]
}
'

const options = {
  method: 'PUT',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    models: [
      {
        model_id: '<string>',
        display: {},
        capabilities: {},
        limits: {},
        failover: '<string>',
        end_of_life: '2023-12-25',
        dimensions: '<unknown>',
        supported_dimensions: '<unknown>',
        metrics: '<unknown>',
        provider_config: '<unknown>',
        pricing: '<unknown>',
        tags: '<unknown>',
        org_slugs: '<unknown>',
        enabled: '<unknown>'
      }
    ]
  })
};

fetch('https://{host}/v2/workspaces/slug:llm-gateway/webhooks/v1/models', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

import requests

url = "https://{host}/v2/workspaces/slug:llm-gateway/webhooks/v1/models"

payload = { "models": [
        {
            "model_id": "<string>",
            "display": {},
            "capabilities": {},
            "limits": {},
            "failover": "<string>",
            "end_of_life": "2023-12-25",
            "dimensions": "<unknown>",
            "supported_dimensions": "<unknown>",
            "metrics": "<unknown>",
            "provider_config": "<unknown>",
            "pricing": "<unknown>",
            "tags": "<unknown>",
            "org_slugs": "<unknown>",
            "enabled": "<unknown>"
        }
    ] }
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

{
  "upserted": 123,
  "pruned": 123,
  "inserted": 123,
  "deleted": 123
}

{
  "error": "<string>",
  "message": "<string>",
  "code": "<string>",
  "details": {},
  "status": 123,
  "retryAfter": 123,
  "provider": "<string>",
  "model": "<string>",
  "provider_error_type": "<string>"
}

{
  "error": "<string>",
  "message": "<string>",
  "code": "<string>",
  "details": {},
  "status": 123,
  "retryAfter": 123,
  "provider": "<string>",
  "model": "<string>",
  "provider_error_type": "<string>"
}

{
  "error": "<string>",
  "message": "<string>",
  "code": "<string>",
  "details": {},
  "status": 123,
  "retryAfter": 123,
  "provider": "<string>",
  "model": "<string>",
  "provider_error_type": "<string>"
}

{
  "error": "<string>",
  "message": "<string>",
  "code": "<string>",
  "details": {},
  "status": 123,
  "retryAfter": 123,
  "provider": "<string>",
  "model": "<string>",
  "provider_error_type": "<string>"
}

{
  "error": "<string>",
  "message": "<string>",
  "code": "<string>",
  "details": {},
  "status": 123,
  "retryAfter": 123,
  "provider": "<string>",
  "model": "<string>",
  "provider_error_type": "<string>"
}

Models

Bulk-replace the entire model catalogue

Reconciles the models collection to the provided list. Used by the platform Models page “Import” flow.

Non-destructive reconcile. Every incoming model is upserted (keyed on model_id) in a single bulk write, then the models absent from the list are pruned. The catalogue is never emptied mid-flight: a failure returns 500 BULK_REPLACE_FAILED and leaves the previous catalogue in place (plus any rows already upserted).

Body must be { "models": [...] } (max 500 items). Each item must carry at least model_id and type.
An empty list clears the whole catalogue, and is refused with 400 CONFIRMATION_REQUIRED unless confirm_clear_all: true is sent.
Cache (global.models_cache) is fully invalidated.
Emits a model.bulk_replaced audit event.
Rate-limited: 2 calls per 60 seconds per consumer (ModelsBulkReplace).

PUT

models

Bulk-replace the entire model catalogue

curl --request PUT \
  --url https://{host}/v2/workspaces/slug:llm-gateway/webhooks/v1/models \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "models": [
    {
      "model_id": "<string>",
      "display": {},
      "capabilities": {},
      "limits": {},
      "failover": "<string>",
      "end_of_life": "2023-12-25",
      "dimensions": "<unknown>",
      "supported_dimensions": "<unknown>",
      "metrics": "<unknown>",
      "provider_config": "<unknown>",
      "pricing": "<unknown>",
      "tags": "<unknown>",
      "org_slugs": "<unknown>",
      "enabled": "<unknown>"
    }
  ]
}
'

const options = {
  method: 'PUT',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    models: [
      {
        model_id: '<string>',
        display: {},
        capabilities: {},
        limits: {},
        failover: '<string>',
        end_of_life: '2023-12-25',
        dimensions: '<unknown>',
        supported_dimensions: '<unknown>',
        metrics: '<unknown>',
        provider_config: '<unknown>',
        pricing: '<unknown>',
        tags: '<unknown>',
        org_slugs: '<unknown>',
        enabled: '<unknown>'
      }
    ]
  })
};

fetch('https://{host}/v2/workspaces/slug:llm-gateway/webhooks/v1/models', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

import requests

url = "https://{host}/v2/workspaces/slug:llm-gateway/webhooks/v1/models"

payload = { "models": [
        {
            "model_id": "<string>",
            "display": {},
            "capabilities": {},
            "limits": {},
            "failover": "<string>",
            "end_of_life": "2023-12-25",
            "dimensions": "<unknown>",
            "supported_dimensions": "<unknown>",
            "metrics": "<unknown>",
            "provider_config": "<unknown>",
            "pricing": "<unknown>",
            "tags": "<unknown>",
            "org_slugs": "<unknown>",
            "enabled": "<unknown>"
        }
    ] }
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

{
  "upserted": 123,
  "pruned": 123,
  "inserted": 123,
  "deleted": 123
}

{
  "error": "<string>",
  "message": "<string>",
  "code": "<string>",
  "details": {},
  "status": 123,
  "retryAfter": 123,
  "provider": "<string>",
  "model": "<string>",
  "provider_error_type": "<string>"
}

{
  "error": "<string>",
  "message": "<string>",
  "code": "<string>",
  "details": {},
  "status": 123,
  "retryAfter": 123,
  "provider": "<string>",
  "model": "<string>",
  "provider_error_type": "<string>"
}

{
  "error": "<string>",
  "message": "<string>",
  "code": "<string>",
  "details": {},
  "status": 123,
  "retryAfter": 123,
  "provider": "<string>",
  "model": "<string>",
  "provider_error_type": "<string>"
}

{
  "error": "<string>",
  "message": "<string>",
  "code": "<string>",
  "details": {},
  "status": 123,
  "retryAfter": 123,
  "provider": "<string>",
  "model": "<string>",
  "provider_error_type": "<string>"
}

{
  "error": "<string>",
  "message": "<string>",
  "code": "<string>",
  "details": {},
  "status": 123,
  "retryAfter": 123,
  "provider": "<string>",
  "model": "<string>",
  "provider_error_type": "<string>"
}

Authorizations

Authorization

string

header

required

User-bound credential carrying an identity: either a session JWT or a user access token (at:*) generated from the user settings UI. Send as Authorization: Bearer <token>. Org API keys (iak_*) are not accepted here - they carry no user identity. Use the x-prismeai-api-key header instead (see OrgApiKeyAuth).

Body

application/json

models

object[]

required

Replacement catalogue (max 500 items).

Maximum array length: 500

Hide child attributes

models.model_id

string

required

Maximum string length: 128

models.type

enum<string>

required

Available options:

completion,

embeddings,

image_generation,

transcription

Maximum string length: 64

models.display

object

models.capabilities

object

models.limits

object

models.failover

string

Maximum string length: 128

models.region

enum<string> | null

Available options:

world,

eu-west,

eu-north,

us-east,

us-west,

asia,

null

Maximum string length: 64

models.end_of_life

string<date> | null

models.dimensions

any

models.supported_dimensions

any

models.metrics

any

models.provider_config

any

models.pricing

any

models.tags

any

models.org_slugs

any

models.enabled

any

confirm_clear_all

boolean

Required (true) when models is empty, to confirm wiping the entire catalogue. Ignored otherwise.

Response

Bulk replace summary.

upserted

integer

required

Number of models inserted or updated (the full incoming list).

pruned

integer

required

Number of stale models removed (absent from the new list).

inserted

integer

required

Backward-compatible alias for upserted.

deleted

integer

required

Backward-compatible alias for pruned.

Introduction

Platform API

Agent Creator API

LLM Gateway API

Governance API

Knowledges API

Collections API

Bulk-replace the entire model catalogue

Authorizations

Body

Response