> ## Documentation Index > Fetch the complete documentation index at: https://docs.verbex.ai/llms.txt > Use this file to discover all available pages before exploring further. # Get LLM model > Retrieve one LLM model by its `llm_model_id`. Use it to confirm that a model is `ACTIVE` and that its `llm_type` array contains the agent's `llm_type` before you send it as `llm.llm_id`. Only `ACTIVE` models are returned. A model that does not exist or is not `ACTIVE` returns `404`. A key that resolves to neither a workspace nor an organization returns `400`. The response uses the v3 envelope: `status` (lowercase), `message` and `data`. Null fields are omitted. To browse the catalog, use [List LLM models](/api-reference/llm-models/list-llm-models). ## OpenAPI ````yaml /api-reference/openapi.json get /v2/llm-models/{llm_model_id} openapi: 3.1.0 info: title: Verbex Platform API description: API for managing AI agents, calls, phone numbers, and more. version: 1.0.0 servers: [] security: [] tags: - name: Knowledge Bases description: >- Create and manage knowledge bases, ingest documents into them, and search them semantically. **Authentication.** Every request carries a bearer token: `Authorization: Bearer `. That is the only credential a client sends. The gateway resolves your identity from it and injects the tenant headers the service reads internally, so clients never send `x-user-org-id` or `x-verbex-id` themselves. **Tenancy is enforced on every route.** A knowledge base belongs to one organization and one user. Requesting one your token does not own returns `404 Knowledge base not found`, never `403`. This is deliberate: a nonexistent ID, a malformed ID and someone else's ID are indistinguishable in the response, so the API cannot be used to probe for other tenants' data. If you get a `404` on an ID you are certain exists, suspect the token before you suspect the ID. **Ingestion is asynchronous.** File upload and website crawl both answer `202` as soon as the material is stored and the job is queued. Parsing, chunking, embedding and indexing happen afterwards in a worker. Poll the document status endpoint until it reports `completed` before expecting search to see the content. That gap is the most common source of "why isn't my data showing up". **There is no document update endpoint.** Every submission mints a new `document_id`, so re-uploading a file or re-crawling the same URLs creates a second document while the first remains. To refresh material, delete then resubmit — and note that the sequence is not atomic. - name: AI Agents v3 description: >- Create, read, update and delete AI agents. v3 selects the LLM, speech-to-text model and voice by catalog id, and wraps every response in a standard envelope. It replaces the deprecated AI Agents v2 operations, which stop working on November 30, 2026. See [Migrate from v2 to v3](/api-reference/ai-agents-v3/migrate-from-v2). - name: LLM Models description: >- The LLM model catalog. Look up the `llm_model_id` to send as `llm.llm_id` when you create or update an agent. - name: Speech Providers description: >- The speech-to-text and text-to-speech provider catalogs. Look up the `provider_id`, `model_id` and `voice_id` to send when you create or update an agent. paths: /v2/llm-models/{llm_model_id}: get: tags: - LLM Models summary: Get LLM model description: >- Retrieve one LLM model by its `llm_model_id`. Use it to confirm that a model is `ACTIVE` and that its `llm_type` array contains the agent's `llm_type` before you send it as `llm.llm_id`. Only `ACTIVE` models are returned. A model that does not exist or is not `ACTIVE` returns `404`. A key that resolves to neither a workspace nor an organization returns `400`. The response uses the v3 envelope: `status` (lowercase), `message` and `data`. Null fields are omitted. To browse the catalog, use [List LLM models](/api-reference/llm-models/list-llm-models). operationId: get_llm_model_v2 parameters: - name: llm_model_id in: path required: true description: Catalog id of the model. schema: type: string title: Llm Model Id responses: '200': description: The model content: application/json: schema: $ref: '#/components/schemas/ApiResponseLlmModel' example: status: success message: LLM model retrieved successfully data: llm_model_id: 9d259647-d5ec-423d-96a9-2750980e8ecb llm_type: - simple - flow model_provider: openai provider_display_name: OpenAI model_name: gpt-4o-mini model_type: builtIn model_display_name: GPT-4o mini language_code: - en-US - ja-JP model_description: Fast, low-cost general-purpose model. is_realtime_model: false pca_enabled: true latency_in_ms: 600 max_tokens: 4096 model_temperature: 0.7 priority: 10 created_by_user_id: usr_admin01 modified_by_user_id: usr_admin01 created_at: '2026-05-04T08:00:00Z' modified_at: '2026-09-12T11:20:00Z' status: ACTIVE operation_type: GET '400': description: No tenant scope content: application/json: schema: $ref: '#/components/schemas/V3ErrorResponse' example: status: error message: Both workspaceId and organizationId are missing '404': description: No active model with that id content: application/json: schema: $ref: '#/components/schemas/V3ErrorResponse' example: status: error message: LLM model not found components: schemas: ApiResponseLlmModel: type: object title: ApiResponse properties: status: type: string enum: - success - error title: Status description: 'Outcome of the request: `success` or `error`, in lowercase.' message: type: string title: Message description: Human-readable message about the result. data: $ref: '#/components/schemas/LlmModelDetail' description: The LLM model. V3ErrorResponse: type: object title: ErrorResponse properties: status: type: string enum: - error title: Status description: 'Outcome of the request: `success` or `error`, in lowercase.' message: type: string title: Message description: Human-readable message about the result. error_details: anyOf: - additionalProperties: type: string type: object - type: 'null' title: Error Details description: >- Field path to message, for validation failures. Omitted when there are none. LlmModelDetail: allOf: - $ref: '#/components/schemas/LlmModel' - type: object properties: operation_type: type: string title: Operation Type description: Always `GET`. type: object title: LlmModelDetail description: An LLM model returned by id. Null fields are omitted. LlmModel: type: object title: LlmModel description: >- An LLM model in the catalog. List items include every field, with explicit `null`s. properties: llm_model_id: type: string title: Llm Model Id description: >- Catalog id. Send it as `llm.llm_id` when you create or update an agent. llm_type: type: array items: type: string enum: - simple - agentic - flow title: Llm Type description: >- Agent types this model supports. It must contain the agent's `llm_type`. model_provider: anyOf: - type: string - type: 'null' title: Model Provider description: Provider key, for example `openai`. provider_display_name: anyOf: - type: string - type: 'null' title: Provider Display Name description: Provider name for display. model_name: anyOf: - type: string - type: 'null' title: Model Name description: Provider model name, for example `gpt-4o-mini`. model_type: anyOf: - type: string enum: - builtIn - custom - type: 'null' title: Model Type description: >- `builtIn` for platform models, `custom` for models your organization added. model_display_name: anyOf: - type: string - type: 'null' title: Model Display Name description: Model name for display. language_code: anyOf: - items: type: string type: array - type: 'null' title: Language Code description: Language codes the model supports. model_description: anyOf: - type: string - type: 'null' title: Model Description description: Description of the model. is_realtime_model: anyOf: - type: boolean - type: 'null' title: Is Realtime Model description: Whether the model is a realtime model. pca_enabled: anyOf: - type: boolean - type: 'null' title: Pca Enabled description: Whether the model can run post-call analysis. latency_in_ms: anyOf: - type: integer - type: 'null' title: Latency In Ms description: Expected latency in milliseconds. tag: anyOf: - type: string - type: 'null' title: Tag description: Optional label for grouping. max_tokens: anyOf: - type: integer - type: 'null' title: Max Tokens description: Maximum tokens per response. model_temperature: anyOf: - type: number - type: 'null' title: Model Temperature description: >- Default temperature. A new agent that omits `model_temperature` takes this value. priority: anyOf: - type: integer - type: 'null' title: Priority description: Sort weight. Higher numbers appear first. organization_id: anyOf: - type: string - type: 'null' title: Organization Id description: Owning organization of a custom model. workspace_id: anyOf: - type: string - type: 'null' title: Workspace Id description: Owning workspace of a custom model. created_by_user_id: anyOf: - type: string - type: 'null' title: Created By User Id description: User who created the model. modified_by_user_id: anyOf: - type: string - type: 'null' title: Modified By User Id description: User who last changed the model. created_at: anyOf: - type: string format: date-time - type: 'null' title: Created At description: Creation time. modified_at: anyOf: - type: string format: date-time - type: 'null' title: Modified At description: Last change time. status: type: string enum: - ACTIVE - INACTIVE - DELETED title: Status description: >- Lifecycle status. Only `ACTIVE` models can be referenced by an agent. required: - llm_model_id ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.