Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.stellartools.dev/llms.txt

Use this file to discover all available pages before exploring further.

The @stellartools/aisdk-adapter package wraps Vercel AI SDK functions with metered billing. Each call checks the customer’s credit balance, runs the model, and charges by token usage.

​
Install

npm install @stellartools/aisdk-adapter ai

​
Usage

The adapter exports generateText, generateObject, streamText, and streamObject directly. Pass your StellarTools config alongside the usual AI SDK options. 
import { generateText } from "@stellartools/aisdk-adapter";
import { openai } from "@ai-sdk/openai";

const response = await generateText({
  api_key: process.env.STELLAR_TOOLS_API_KEY!,
  product_id: "prod_llm_ai",
  customer_id: "cust_xxx",
  model: openai("gpt-4o"),
  prompt: "Write a haiku about Stellar",
});

console.log(response.text);
Streaming: 
import { streamText } from "@stellartools/aisdk-adapter";
import { openai } from "@ai-sdk/openai";

await streamText({
  api_key: process.env.STELLAR_TOOLS_API_KEY!,
  product_id: "prod_llm_ai",
  customer_id: "cust_xxx",
  model: openai("gpt-4o"),
  messages: [{ role: "user", content: "Hello" }],
});
The preflight check runs before the model call. If the customer does not have enough credits, the adapter throws before any tokens are used.

​
Options

​
api_key
string
required
Your StellarTools API key.
​
product_id
string
required
The credit product ID to charge for usage.
​
customer_id
string
required
The StellarTools customer ID to bill.