v1

latestOpenAPI 3.0.3MIT2026-07-132953108.7 KB
Provider Management

Add Provider

Add a new AI provider configuration with API keys, network settings, and concurrency options.

post/api/providers

Request body

provider'openai' | 'anthropic' | 'azure' | 'bedrock' | 'cohere' | 'vertex' | 'mistral' | 'ollama' | 'groq' | 'sgl' required

AI model provider

Example request

{
  "provider": "openai",
  "keys": [
    {
      "value": "env.OPENAI_API_KEY",
      "weight": 1,
      "models": [
        "gpt-4o",
        "gpt-4o-mini"
      ],
      "azure_key_config": {
        "endpoint": "https://your-resource.openai.azure.com",
        "deployments": {
          "gpt-4o": "gpt-4o-deployment"
        },
        "api_version": "2024-02-15-preview"
      },
      "vertex_key_config": {
        "project_id": "your-project-id",
        "region": "us-central1",
        "auth_credentials": "env.VERTEX_AUTH_CREDENTIALS"
      },
      "bedrock_key_config": {
        "access_key": "env.AWS_ACCESS_KEY_ID",
        "secret_key": "env.AWS_SECRET_ACCESS_KEY",
        "session_token": "env.AWS_SESSION_TOKEN",
        "region": "us-east-1",
        "arn": "arn:aws:iam::123456789012:role/BedrockRole",
        "deployments": {
          "gpt-4o": "gpt-4o-deployment"
        }
      }
    }
  ],
  "network_config": {
    "timeout": 30,
    "max_retries": 3
  },
  "concurrency_and_buffer_size": {
    "concurrency": 10,
    "buffer_size": 100
  },
  "proxy_config": {
    "url": "http://proxy.example.com:8080"
  }
}

Response

Provider added successfully

status'success' required

Operation status

messagestring required

Success message

Example response

{
  "status": "success",
  "message": "Operation completed successfully"
}