For AI agents: markdown of this page — /docs-content-en/ai/credentials/fetch-models.md documentation index — /llms.txt

Fetch the model catalog

POST /v1/ai/credentials/:id/fetch-models

Fetches the list of models from a Custom provider via its GET /v1/models endpoint and saves each one as an AiModel bound to this key. If the provider does not support /v1/models — the operation returns a successful response with a hint to add models manually.

The endpoint works only with the custom-openai-compat provider — for other providers the model catalog is fixed and managed by the platform.

Parameters

Parameter Type Required Description
id (path) string yes Custom key ID from GET /v1/ai/credentials

No request body is sent.

Examples

curl — personal key

Terminal 
curl -X POST https://vibecode.bitrix24.com/v1/ai/credentials/cred_custom_xyz/fetch-models \
  -H "X-Api-Key: YOUR_API_KEY"

curl — OAuth application

Terminal 
curl -X POST https://vibecode.bitrix24.com/v1/ai/credentials/cred_custom_xyz/fetch-models \
  -H "X-Api-Key: YOUR_APP_KEY" \
  -H "Authorization: Bearer USER_SESSION_TOKEN"

JavaScript — personal key

javascript 
const id = 'cred_custom_xyz'
const res = await fetch(`https://vibecode.bitrix24.com/v1/ai/credentials/${id}/fetch-models`, {
  method: 'POST',
  headers: { 'X-Api-Key': 'YOUR_API_KEY' },
})

const { data } = await res.json()
console.log(`Added: ${data.added}, updated: ${data.updated}, marked deprecated: ${data.deprecated}`)

JavaScript — OAuth application

javascript 
const id = 'cred_custom_xyz'
const res = await fetch(`https://vibecode.bitrix24.com/v1/ai/credentials/${id}/fetch-models`, {
  method: 'POST',
  headers: {
    'X-Api-Key': 'YOUR_APP_KEY',
    'Authorization': 'Bearer USER_SESSION_TOKEN',
  },
})

const { data } = await res.json()
if (data.error === 'PROVIDER_LIST_MODELS_UNAVAILABLE') {
  console.log('The provider does not support GET /v1/models — add models manually:', data.hint)
}

Response fields

Field Type Description
success boolean Always true
data.added number Number of new AiModel records
data.updated number Number of updated records (models that were already in the key's catalog)
data.deprecated number Number of models that were previously fetched but are no longer returned by the provider — their status is automatically changed to DEPRECATED
data.error string Only on a provider error: PROVIDER_LIST_MODELS_UNAVAILABLE
data.hint string A hint on what to do next, returned on error
data.message string The message from the provider on error

Response example

Successful catalog fetch:

JSON 
{
  "success": true,
  "data": {
    "added": 5,
    "updated": 12,
    "deprecated": 0
  }
}

The provider does not support GET /v1/models (for example, Minimax):

JSON 
{
  "success": true,
  "data": {
    "added": 0,
    "updated": 0,
    "deprecated": 0,
    "error": "PROVIDER_LIST_MODELS_UNAVAILABLE",
    "hint": "add models manually: POST /v1/ai/credentials/cred_custom_xyz/models",
    "message": "OpenAI API 404: page not found"
  }
}

Error response example

400 not_custom_provider — the key does not belong to a Custom provider:

JSON 
{
  "success": false,
  "error": {
    "code": "not_custom_provider",
    "message": "fetch-models is only available for custom-openai-compat provider"
  }
}

Errors

HTTP Code Description
400 not_custom_provider The endpoint works only with the custom-openai-compat provider
404 not_found A key with this id was not found or does not belong to you
403 scope_missing The API key lacks the vibe:ai scope

Full list of common API errors — Errors.

Catalog fetch limit: 10 requests per minute (one bucket per portal).

Known specifics

Idempotent. Re-running does not create duplicates: models with an already existing modelId are updated (the name, contextLength, maxOutputTokens fields), new ones are added, and those no longer in the provider's catalog get the DEPRECATED status (usage history is preserved).

Prices are zero. Fetched models default to inputPrice = 0, outputPrice = 0 — BYOK means you pay the provider directly. Platform billing skips such records.

Alternative on PROVIDER_LIST_MODELS_UNAVAILABLE. If the provider does not return a model catalog — add each model manually via POST /v1/ai/credentials/:id/models. This is needed for Minimax (api.minimax.io), some corporate vLLM installations, and other services without GET /v1/models.

The OpenAiAdapter filter kicks in. Under the hood the endpoint uses GET /v1/models through OpenAiAdapter, which filters responses by the gpt- prefix. If your Custom service returns models without this prefix (Minimax abab6.5-chat, Cohere, etc.) — fetch-models returns added: 0. Use manual registration.

See also