Responses

​

Example

<?php

require 'vendor/autoload.php';

use AIStats\Sdk\AIStats;

$apiKey = getenv('AI_STATS_API_KEY');
$client = new AIStats(apiKey: $apiKey);

$response = $client->createResponse([
    'model' => 'openai/gpt-4.1',
    'input' => [
        [
            'role' => 'user',
            'content' => [
                [
                    'type' => 'output_text',
                    'text' => 'Summarise this text'
                ]
            ]
        ]
    ],
    'temperature' => 0.7,
    'stream' => false
]);
echo $response['output'][0]['content'][0]['text'];

​

Key parameters

• model (required): Target model id.
• input (required): Ordered array of input items (messages, tool calls, etc.).
• temperature (0–2): Higher = more random.
• top_p (0–1): Nucleus sampling control.
• max_output_tokens (int): Hard cap on tokens generated per response.
• Tools: tools (definitions), tool_choice (auto/none/specific), max_tool_calls (int), parallel_tool_calls (bool).
• Logprobs: top_logprobs (0–20) to return per-token logprobs.
• Output: service_tier, store (bool), stream (bool).
• Metadata: metadata (object) for passthrough, reasoning (object) for effort hints.
• Gateway extras: usage (bool to request usage), meta (bool to include meta block).

​

Returns