Vercel AI SDK

The @useautumn/gateway package integrates Autumn with the Vercel AI SDK, automatically tracking token usage for every generateText or streamText call. No manual trackTokens calls needed.

Setup

1. Install the package

npm install @useautumn/gateway

pnpm add @useautumn/gateway

yarn add @useautumn/gateway

bun add @useautumn/gateway

Requires Node.js 22+, ESM imports, and autumn-js and ai (v7) as peer dependencies. AI SDK 6 applications should stay on the previous gateway release.

2. Wrap your model

Use withAutumn to wrap any AI SDK language model. It intercepts generate and stream calls, reads the token usage from the response, and reports it to Autumn automatically.

import { Autumn } from "autumn-js";
import { anthropic } from "@ai-sdk/anthropic";
import { withAutumn } from "@useautumn/gateway/ai-sdk";

const autumn = new Autumn({ secretKey: "am_sk_test_1234" });

const model = withAutumn({
  autumn,
  model: anthropic("claude-sonnet-4-5-20250514"),
  customerId: "user_123",
});

3. Use as normal

The wrapped model works exactly like a regular AI SDK model. Token usage is tracked in the background after each call.

import { generateText, streamText } from "ai";

// Generate — usage tracked automatically
const { text } = await generateText({
  model,
  prompt: "Explain quantum computing in one paragraph",
});

// Stream — usage tracked when the stream finishes
const result = streamText({
  model,
  prompt: "Write a short poem about recursion",
});

for await (const chunk of result.textStream) {
  process.stdout.write(chunk);
}

Token pools

The wrapper normalizes the AI SDK’s usage object into the exclusive token pools that trackTokens expects: text input (excluding cached tokens), text output (excluding reasoning tokens), cache reads, cache writes, and reasoning tokens. Each pool is billed at the model’s published rate, so cached and reasoning-heavy requests are priced correctly without any extra work.

Model ID format

The wrapped model constructs the modelId sent to Autumn using provider/model format, derived from the AI SDK model’s provider and modelId fields. This must match a valid provider and model key from Models.dev. For example:

@ai-sdk/anthropic → anthropic/claude-sonnet-4-5-20250514
@ai-sdk/openai → openai/gpt-4o
@ai-sdk/google → google/gemini-2.5-pro

OpenAI, Anthropic, and Google provider names are normalized automatically, including dotted SDK namespaces such as openai.responses, anthropic.messages, and google.generative-ai. Vercel’s gateway namespace maps to vercel. Dots and slashes in the model ID are preserved. Other provider names pass through unchanged. For a custom mapping, use providerId. Explicit overrides are used verbatim:

import { createOpenRouter } from "@openrouter/ai-sdk-provider";

const openrouter = createOpenRouter();

const model = withAutumn({
  autumn,
  model: openrouter("anthropic/claude-opus-4.6"),
  customerId: "user_123",
  providerId: "openrouter",  // Override provider prefix
});
// Sends modelId as "openrouter/anthropic/claude-opus-4.6"

Options

Parameter	Type	Required	Description
`autumn`	`Autumn`	Yes	Your Autumn SDK client instance
`model`	`LanguageModelV4`	Yes	The AI SDK 7 language model to wrap
`customerId`	`string`	Yes	The Autumn customer ID to attribute usage to
`providerId`	`string`	No	Explicit pricing provider, used verbatim instead of the normalized model provider
`featureId`	`string`	No	Target a specific AI credit system feature. Auto-detected if you only have one
`entityId`	`string`	No	Entity ID for entity-scoped balance tracking
`properties`	`Record<string, unknown>`	No	Additional properties to attach to each usage event

Full example

import { Autumn } from "autumn-js";
import { openai } from "@ai-sdk/openai";
import { generateText } from "ai";
import { withAutumn } from "@useautumn/gateway/ai-sdk";

const autumn = new Autumn({ secretKey: process.env.AUTUMN_SECRET_KEY! });

async function chat(customerId: string, message: string) {
  const model = withAutumn({
    autumn,
    model: openai("gpt-4o"),
    customerId,
  });

  const { text } = await generateText({
    model,
    prompt: message,
  });

  return text;
}

Tracking failures are caught and logged to the console — they won’t break your AI features. Check your server logs if usage isn’t appearing in Autumn.

Getting Started

Configure Pricing

Billing & Subscriptions

Customers

Additional Resources

Setup

1. Install the package

2. Wrap your model

3. Use as normal

Token pools

Model ID format

Options

Full example

​Setup

​1. Install the package

​2. Wrap your model

​3. Use as normal

​Token pools

​Model ID format

​Options

​Full example

Setup

1. Install the package

2. Wrap your model

3. Use as normal

Token pools

Model ID format

Options

Full example