Skip to main content
Use generateText with aiStats(modelId) for one-shot completions. 
import { aiStats } from "@ai-stats/ai-sdk-provider";
import { generateText } from "ai";

const result = await generateText({
  model: aiStats("openai/gpt-5-nano"),
  prompt: "Write a concise summary of AI Stats Gateway.",
});

console.log(result.text);

​
With chat history

import { aiStats } from "@ai-stats/ai-sdk-provider";
import { generateText } from "ai";

const result = await generateText({
  model: aiStats("openai/gpt-5-nano"),
  messages: [
    { role: "system", content: "You are a terse assistant." },
    { role: "user", content: "Give me three bullet points on retrieval augmentation." },
  ],
});

console.log(result.text);

​
Per-model settings

import { aiStats } from "@ai-stats/ai-sdk-provider";
import { generateText } from "ai";

const result = await generateText({
  model: aiStats("openai/gpt-5-nano", {
    temperature: 0.2,
    topP: 0.9,
    maxTokens: 300,
  }),
  prompt: "Draft a release note for an API update.",
});

console.log(result.text);

​
Prompt vs messages

  • Use prompt for quick single-turn requests.
  • Use messages for multi-turn context and role control.
  • Keep model IDs dynamic by querying /v1/gateway/models (see Model Discovery).
Last modified on March 16, 2026