> ## Documentation Index
> Fetch the complete documentation index at: https://dialnexa.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Get LLM

> Fetch a single LLM record from DialNexa's supported model catalogue, including provider, context window, and supported features.

<Warning>
  **Legacy endpoint - deprecated.** Unversioned endpoints are scheduled for removal on **July 31, 2026**. Use the [`/v1` version](/docs/api-reference/v1/llms/get) for new integrations. This endpoint remains available for existing integrations until then.
</Warning>

Returns the full record for a single LLM in DialNexa's supported model catalogue. The response includes the model's stable `id`, the upstream `provider` (for example OpenAI, Anthropic, Google, or a hosted open-weights model), the display `name`, the context window size, and which conversational features are supported (such as function calling and JSON mode).

## When to use this

Use this endpoint when you have an `llm_id` saved on an agent configuration or in your own database and you need to resolve it into a human-readable label, confirm the model is still active, or check what features the model supports before sending an agent update.

* **Agent build UIs** typically fetch this when rendering the LLM selection for an already-saved agent so the dropdown can display the correct provider, name, and capability badges.
* **Migration tooling** that retires a deprecated model uses this to confirm the target model still exists before bulk-updating agents.
* **Cost-aware dashboards** read the provider and tier from this endpoint to attribute spend per model in internal reports.

If you need the full list of available LLMs, call [List LLMs](/docs/api-reference/v1/llms/list) instead. That endpoint is the canonical catalogue and is paginated.

## Path parameters

| Parameter | Description                          |
| --------- | ------------------------------------ |
| `id`      | The LLM ID, for example `llm_gpt4o`. |

## Errors

* `404 Not Found` is returned when the `id` does not match a supported LLM. This usually means the model has been deprecated and removed, or the ID was mistyped.
* `401 Unauthorized` is returned when the API key is missing, malformed, or revoked. See [Authentication](/docs/api-reference/authentication).

## Related endpoints

* [List LLMs](/docs/api-reference/v1/llms/list): fetch every LLM the platform currently supports.
* [Update Agent](/docs/api-reference/v1/agents/update): change the LLM assigned to an existing agent.
* [LLMs and conversation behavior](/docs/voice-ai/llms-and-conversation-behavior): guidance on choosing an LLM for your use case.


## OpenAPI

````yaml GET /llms/{id}
openapi: 3.0.0
info:
  title: DialNexa API
  description: >-
    Public REST API for the DialNexa voice AI platform. Versioned endpoints are
    under /v1; unversioned endpoints are legacy and deprecated.
  version: 1.0.0
servers:
  - url: https://api.dialnexa.com
    description: DialNexa production API
security:
  - bearer: []
tags:
  - name: API Keys
  - name: Agent Functions
  - name: Agents V1
  - name: Agents2
  - name: Batch Calls
  - name: Batch Calls V1
  - name: Call Logs
  - name: Calls
  - name: Calls V1
  - name: Campaign Leads
  - name: Campaigns
  - name: External Webhooks
  - name: Knowledge Base
  - name: Knowledge Base V1
  - name: LLMs
  - name: LLMs V1
  - name: Languages
  - name: Languages V1
  - name: Organization Phone Numbers
  - name: Organization Phone Numbers V1
  - name: Phone Number Pricing
  - name: Phone Number Pricing V1
  - name: Transcribers
  - name: Transcribers V1
  - name: User Webhooks
  - name: User Webhooks V1
  - name: V1
  - name: Voices
  - name: Voices V1
  - name: Webcall
  - name: Workflow Leads
  - name: Workflow Leads V1
  - name: Workflows
  - name: Workflows V1
paths:
  /llms/{id}:
    get:
      tags:
        - LLMs
      summary: Get LLM by ID
      description: >-
        **Legacy endpoint - deprecated, scheduled for removal on July 31,
        2026.** Use the `/v1` version for new integrations. 
      operationId: LlmsController_findById
      parameters:
        - name: id
          required: true
          in: path
          description: ID of the LLM
          schema:
            type: string
      responses:
        '200':
          description: LLM found
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Llm'
        '404':
          description: LLM not found
      deprecated: true
components:
  schemas:
    Llm:
      type: object
      properties:
        id:
          type: string
          example: llm_abc123
          description: Signed LLM ID
      required:
        - id
  securitySchemes:
    bearer:
      scheme: bearer
      bearerFormat: JWT
      type: http

````