Text Completions

Text completions generate a continuation of a single prompt. Unlike chat completions, which are designed for multi-turn conversations, completions take one block of text and return the model’s continuation of it. Learn more about the difference.

Text completions are served by Google models through the endpoint below.

Request

URL: https://ai.purlabs.xyz/google/completions

Request Method: POST

TS Request Interface


interface Request {
	model?: string;
	prompt: string;
};

Request API Reference

Parameter	Type	Required	Description
`prompt`	`string`	Required	The text prompt for the model to complete.
`model`	`string`	Optional	The model to use, such as `gemini-pro`. `bard` is accepted as a deprecated alias. Refer to the Listing Available Models page for more information.

Example JSON Request Body


{
  "model": "gemini-pro",
  "prompt": "Hello, how are you?"
}

Response

TS Response Interface


interface Response {
	id: string;
	object: 'completion';
	created: number;
	model: string;
	choices: {
		index: number;
		message: {
			role: 'assistant';
			content: string;
		};
		finish_reason: any;
	}[];
	leftUsages: {
		prompt_tokens: number;
		completion_tokens: number;
		total_tokens: number;
	};
	overwritten: boolean;
	provider: string;
	cache?: {
		status: 500,
		error: {
			message: 'Some of our providers returned with errors. Errors are automatically reported to our developers.';
			records: {
				provider: string;
				response: {
					status: number;
					data?: any;
				};
			}[];
		};
	};
} | {
	status: 500,
	message: string;
	records: {
		provider: string;
		response: {
			status: number;
			data?: any;
		};
	}[];
};

Example JSON Response


{
    "id": "anr8pycazxmyqfcmwwp8dg",
    "object": "completion",
    "created": 1692564194,
    "model": "gemini-pro",
    "choices": [{
        "index": 0,
        "message": {
            "role": "assistant",
            "text": "Hello! I am doing well, thank you for asking. How can I help you today?"
        },
        "finish_reason": "stop"
    }],
    "leftUsages": {},
	"cache": {
        "status": 500,
        "error": {
            "message": "Some of our providers returned with errors. Errors are automatically reported to our developers.",
            "records": [
                {
                    "provider": "provider-1",
                    "response": {
                        "status": 404,
                        "data": "404 Not Found"
                    }
                },
                {
                    "provider": "provider-2",
                    "response": {
                        "status": 403,
                        "data": "403 Forbidden"
                    }
                },
                {
                    "provider": "provider-3",
                    "response": {
                        "status": 504,
                        "data": "timeout of 60000ms exceeded"
                    }
                }
            ]
        }
    }
}