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

Add a model manually

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

Registers a single model bound to a Custom key. Used for providers that do not expose a catalog via GET /v1/models (Minimax, a corporate vLLM/Ollama, Cohere). The endpoint works only with the custom-openai-compat provider.

Parameters

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

Request fields (body)

Field Type Required Default Description
modelId string yes — The model ID at the provider. Used as the model in requests to /v1/chat/completions
name string no value of modelId Display name of the model
contextLength number no 8192 Maximum context size in tokens
maxOutputTokens number no 4096 Maximum tokens in the response

Examples

curl — personal key

Terminal 
curl -X POST https://vibecode.bitrix24.com/v1/ai/credentials/cred_custom_xyz/models \
  -H "X-Api-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "modelId": "abab6.5-chat",
    "name": "MiniMax abab6.5-chat",
    "contextLength": 32768,
    "maxOutputTokens": 8192
  }'

curl — OAuth application

Terminal 
curl -X POST https://vibecode.bitrix24.com/v1/ai/credentials/cred_custom_xyz/models \
  -H "X-Api-Key: YOUR_APP_KEY" \
  -H "Authorization: Bearer USER_SESSION_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "modelId": "abab6.5-chat",
    "name": "MiniMax abab6.5-chat",
    "contextLength": 32768,
    "maxOutputTokens": 8192
  }'

JavaScript — personal key

javascript 
const id = 'cred_custom_xyz'
const res = await fetch(`https://vibecode.bitrix24.com/v1/ai/credentials/${id}/models`, {
  method: 'POST',
  headers: {
    'X-Api-Key': 'YOUR_API_KEY',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    modelId: 'abab6.5-chat',
    name: 'MiniMax abab6.5-chat',
    contextLength: 32768,
    maxOutputTokens: 8192,
  }),
})

const { data } = await res.json()
console.log('Registered model with id:', data.id)

JavaScript — OAuth application

javascript 
const id = 'cred_custom_xyz'
const res = await fetch(`https://vibecode.bitrix24.com/v1/ai/credentials/${id}/models`, {
  method: 'POST',
  headers: {
    'X-Api-Key': 'YOUR_APP_KEY',
    'Authorization': 'Bearer USER_SESSION_TOKEN',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({ modelId: 'abab6.5-chat' }),
})

const { data } = await res.json()
console.log('Done:', data.modelId)

Response fields

Field Type Description
success boolean Always true on success
data.id string Unique ID of the AiModel record (needed for deletion)
data.modelId string The registered modelId
data.name string Model name
data.contextLength number The saved context size

Response example

HTTP status 201 Created:

JSON 
{
  "success": true,
  "data": {
    "id": "aimodel_xyz789",
    "modelId": "abab6.5-chat",
    "name": "MiniMax abab6.5-chat",
    "contextLength": 32768
  }
}

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": "Manual model registration is only available for custom-openai-compat provider"
  }
}

Errors

HTTP Code Description
400 invalid_request The modelId field was not passed or the schema is violated
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.

Model registration limit: 30 requests per minute.

Known specifics

Idempotent. A repeat call with the same modelId updates the existing record (the name, contextLength, maxOutputTokens fields) instead of creating a duplicate.

modelId matches the provider's. Pass exactly the identifier the provider expects in the request model. For example, for Minimax — abab6.5-chat, and for a corporate vLLM — the name the model was loaded under.

Price is zero. Custom-provider models are always registered with a zero price (inputPrice = 0, outputPrice = 0). Platform billing skips such records — you pay the provider directly.

See also