Get all LLM configurations of the user's Organization

GET

/api/v2/organizations/llm-configs

This endpoint provides access to all available Large Language Model (LLM) configurations within the system.
It serves as a catalog from which clients can explore model options, including deployment details, availability status, and default preferences.

Query Parameters:

model_deployment (str): Filter by model deployment. Optional.

Returns:

A list of all LLM configurations available in the system.

Current Version: 2.1.0

Changelog:

2.1.0: user_options field added to each config in the response, highlighting what configurable parameters are paired to model.

Request

Query Params

Header Params

Responses

🟢200OK

application/json

Success

Bodyapplication/json

🟠400Bad Request

🟠403Record Not Found

🟠404Server Error

🔴500

🔴503

Request Example

Shell

JavaScript

Java

Swift

curl --location --globoff 'https:///api/v2/organizations/llm-configs?model_deployment=' \
--header 'Organization-Id;' \
--header 'Ocp-Apim-Subscription-Key: ' \
--header 'Authorization: Bearer '

Response Example

200 - LLM configs list

{
    "success": true,
    "message": "LLM configurations retrieved successfully",
    "data": {
        "llm_configs": [
            {
                "id": 1,
                "organization": 1,
                "model_name": "claude-opus-4-8",
                "model_provider": "anthropic",
                "model_deployment": [
                    "chat"
                ],
                "endpoint": "https://api.anthropic.com/v1/messages",
                "release_date": "2025-01-01",
                "temperature": 0.7,
                "top_p": 1,
                "max_tokens": 8096,
                "reasoning_effort": "medium",
                "type": "Anthropic",
                "context_length": 200000,
                "pricing": 0.015,
                "supports_function_calling": true,
                "is_reasoning_model": true,
                "is_enabled": true,
                "is_default": true,
                "tokens_per_minute": 40000,
                "requests_per_minute": 50,
                "parameters": {
                    "model": "claude-opus-4-8",
                    "model_provider": "anthropic",
                    "api_key": "<your-api-key>",
                    "base_url": "https://<resource>.services.ai.azure.com/anthropic/",
                    "thinking": {
                        "type": "adaptive",
                        "display": "omitted"
                    },
                    "max_tokens": 64000,
                    "output_config": {
                        "effort": "medium"
                    }
                },
                "user_options": {
                    "effort": {
                        "labels": [
                            "minimal",
                            "low",
                            "medium",
                            "high"
                        ],
                        "default": "medium"
                    }
                }
            }
        ]
    }
}

Get all Configurations of user's Organization