Skip to main content
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
Requires autumn-js and ai (v6+) as peer dependencies.

​
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
If the AI SDK provider name doesn’t match the Models.dev provider key, use the providerId option to override it: 
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

ParameterTypeRequiredDescription
autumnAutumnYesYour Autumn SDK client instance
modelLanguageModelV3YesThe AI SDK language model to wrap
customerIdstringYesThe Autumn customer ID to attribute usage to
providerIdstringNoOverride the provider prefix in the model name sent to Autumn. Falls back to the model’s provider field
featureIdstringNoTarget a specific AI credit system feature. Auto-detected if you only have one
entityIdstringNoEntity ID for entity-scoped balance tracking
propertiesRecord<string, unknown>NoAdditional 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.