List LLMs

GET

/v1/convai/llm/list

GET

/v1/convai/llm/list

curl https://api.elevenlabs.io/v1/convai/llm/list

{
  "llms": [
    {
      "llm": "gemini-2.5-flash",
      "is_checkpoint": false,
      "max_tokens_limit": 8192,
      "max_context_limit": 1048576,
      "supports_image_input": true,
      "supports_document_input": true,
      "supports_parallel_tool_calls": true,
      "available_reasoning_efforts": [
        "none"
      ],
      "deprecation_info": {
        "llm": "gpt-4o-mini",
        "is_deprecated": true,
        "is_in_warning_period": true,
        "is_in_fallback_period": false,
        "fallback_percentage": 0,
        "provider_deprecation_date": "2025-06-01T00:00:00Z",
        "replacement_model": "gpt-4o",
        "deprecation_config": {
          "warning_start_days": 30,
          "fallback_start_days": 14,
          "fallback_complete_days": 7,
          "fallback_start_percentage": 25,
          "fallback_complete_percentage": 100
        }
      },
      "regional_processing_surcharge": {
        "multiplier": 1.1
      }
    }
  ],
  "default_deprecation_config": {
    "warning_start_days": 30,
    "fallback_start_days": 14,
    "fallback_complete_days": 7,
    "fallback_start_percentage": 25,
    "fallback_complete_percentage": 100
  }
}

Returns a list of available LLM models that can be used with agents, including their capabilities and any deprecation status. The response is filtered based on the data residency of the deployment and any compliance requirements (e.g. HIPAA) of the workspace subscription.

Resposta

Successful Response

llmslist of objects

List of all available LLM models that can be used with agents.

default_deprecation_configobject

The default deprecation timing configuration used for models without a custom override.

Erros

422

Llm List Request Unprocessable Entity Error

Cabeçalhos

Resposta

Erros