Axiom Docs

This page explains how to set up instrumentation in your TypeScript generative AI app using Axiom AI SDK.

Axiom AI SDK is an open-source project and welcomes your contributions. For more information, see the GitHub repository.

Alternatively, instrument your app manually. For more information on instrumentation approaches, see LLM observability.

Prerequisite

Install the Axiom AI SDK by running the following:

npm i @axiomhq/ai

Set the AXIOM_TOKEN and AXIOM_DATASET environment variables using an API token and the name of a dataset you want to send telemetry to.

Instrument AI SDK calls

Axiom AI SDK provides helper functions for Vercel AI SDK to wrap your existing AI model client. The wrapAISDKModel function takes an existing AI model object and returns an instrumented version that automatically generates trace data for every call. Choose one of the following common Vercel AI SDK providers. For the full list of providers, see the Vercel documentation.

OpenAI
Anthropic
Gemini
Grok

Run the following in your terminal to install the Vercel AI SDK and the OpenAI provider.
npm i ai @ai-sdk/openai

Create the file src/shared/openai.ts with the following content:

/src/shared/openai.ts

import { createOpenAI } from '@ai-sdk/openai';
import { wrapAISDKModel } from 'axiom/ai';

const openaiProvider = createOpenAI({
  apiKey: process.env.OPENAI_API_KEY,
});

// Wrap the model to enable automatic tracing
export const gpt4o = wrapAISDKModel(openaiProvider('gpt-4o'));
export const gpt4oMini = wrapAISDKModel(openaiProvider('gpt-4o-mini'));

Run the following in your terminal to install the Vercel AI SDK and the Anthropic provider.
npm i ai @ai-sdk/anthropic

Create the file src/shared/anthropic.ts with the following content:

/src/shared/anthropic.ts

import { createAnthropic } from '@ai-sdk/anthropic';
import { wrapAISDKModel } from 'axiom/ai';

const anthropicProvider = createAnthropic({
  apiKey: process.env.ANTHROPIC_API_KEY,
});

// Wrap the model to enable automatic tracing
export const claude35Sonnet = wrapAISDKModel(anthropicProvider('claude-3-5-sonnet-20241022'));
export const claude35Haiku = wrapAISDKModel(anthropicProvider('claude-3-5-haiku-20241022'));

Run the following in your terminal to install the Vercel AI SDK and the Gemini provider.
npm i ai @ai-sdk/google

Create the file src/shared/gemini.ts with the following content:

/src/shared/gemini.ts

import { createGoogleGenerativeAI } from '@ai-sdk/google';
import { wrapAISDKModel } from 'axiom/ai';

const geminiProvider = createGoogleGenerativeAI({
  apiKey: process.env.GEMINI_API_KEY,
});

// Wrap the model to enable automatic tracing
export const gemini20Flash = wrapAISDKModel(geminiProvider('gemini-2.0-flash-exp'));
export const gemini15Pro = wrapAISDKModel(geminiProvider('gemini-1.5-pro'));

Run the following in your terminal to install the Vercel AI SDK and the Grok provider.
npm i ai @ai-sdk/xai

Create the file src/shared/grok.ts with the following content:

/src/shared/grok.ts

import { createXai } from '@ai-sdk/xai';
import { wrapAISDKModel } from 'axiom/ai';

const grokProvider = createXai({
  apiKey: process.env.XAI_API_KEY,
});

// Wrap the model to enable automatic tracing
export const grokBeta = wrapAISDKModel(grokProvider('grok-beta'));
export const grok2Mini = wrapAISDKModel(grokProvider('grok-2-mini'));

To instrument calls without a Vercel AI SDK provider, use the generic Vercel AI Gateway provider.

Gateway provider

To instrument calls without a Vercel AI SDK provider, use the generic Vercel AI Gateway provider. For more information, see the Vercel documentation.

Run the following in your terminal to install the Vercel AI SDK:
npm i ai

Create the file src/shared/openai.ts with the following content:

/src/shared/openai.ts

import { createGateway } from 'ai';
import { wrapAISDKModel } from 'axiom';

const gateway = createGateway({
  apiKey: process.env.OPENAI_API_KEY,
});

// Wrap the model to enable automatic tracing
export const gpt4o = wrapAISDKModel(gateway('openai/gpt-4o'));

The rest of the page explains how to work with OpenAI. The process is similar for other LLMs.

Add context

The withSpan function allows you to add crucial business context to your traces. It creates a parent span around your LLM call and attaches metadata about the capability and step that you execute.

/src/app/page.tsx

import { withSpan } from 'axiom/ai';
import { generateText } from 'ai';
import { gpt4o } from '@/shared/openai';

export default async function Page() {
  const userId = 123;

  // Use withSpan to define the capability and step
  const res = await withSpan({ capability: 'get_capital', step: 'generate_answer' }, (span) => {
    // You have access to the OTel span to add custom attributes
    span.setAttribute('user_id', userId);

    return generateText({
      model: gpt4o, // Use the wrapped model
      messages: [
        {
          role: 'user',
          content: 'What is the capital of Spain?',
        },
      ],
    });
  });

  return <p>{res.text}</p>;
}

Instrument tool calls

For many AI capabilities, the LLM call is only part of the story. If your capability uses tools to interact with external data or services, observing the performance and outcome of those tools is critical. Axiom AI SDK provides the wrapTool and wrapTools functions to automatically instrument your Vercel AI SDK tool definitions. The wrapTool helper takes your tool’s name and its definition and returns an instrumented version. This wrapper creates a dedicated child span for every tool execution, capturing its arguments, output, and any errors.

/src/app/generate-text/page.tsx

import { tool } from 'ai';
import { z } from 'zod';
import { wrapTool } from 'axiom/ai';
import { generateText } from 'ai';
import { gpt4o } from '@/shared/openai';

// In your generateText call, provide wrapped tools
const { text, toolResults } = await generateText({
  model: gpt4o,
  messages: [
    { role: 'system', content: 'You are a helpful assistant.' },
    { role: 'user', content: 'How do I get from Paris to Berlin?' },
  ],
  tools: {
    // Wrap each tool with its name
    findDirections: wrapTool(
      'findDirections', // The name of the tool
      tool({
        description: 'Find directions to a location',
        inputSchema: z.object({
          from: z.string(),
          to: z.string(),
        }),
        execute: async (params) => {
          // Your tool logic here...
          return { directions: `To get from ${params.from} to ${params.to}, use a teleporter.` };
        },
      })
    )
  }
});

Complete example

Example of how all three instrumentation functions work together in a single, real-world example:

/src/app/page.tsx

import { withSpan, wrapAISDKModel, wrapTool } from 'axiom/ai';
import { generateText, tool } from 'ai';
import { createOpenAI } from '@ai-sdk/openai';
import { z } from 'zod';

// 1. Create and wrap the AI model client
const openaiProvider = createOpenAI({
  apiKey: process.env.OPENAI_API_KEY,
});
const gpt4o = wrapAISDKModel(openaiProvider('gpt-4o'));

// 2. Define and wrap your tool(s)
const findDirectionsTool = wrapTool(
  'findDirections', // The tool name must be passed to the wrapper
  tool({
    description: 'Find directions to a location',
    inputSchema: z.object({ from: z.string(), to: z.string() }),
    execute: async ({ from, to }) => ({
      directions: `To get from ${from} to ${to}, use a teleporter.`,
    }),
  })
);

// 3. In your application logic, use `withSpan` to add context
//    and call the AI model with your wrapped tools.
export default async function Page() {
  const userId = 123;

  const { text } = await withSpan({ capability: 'get_directions', step: 'generate_ai_response' }, async (span) => {
    // You have access to the OTel span to add custom attributes
    span.setAttribute('user_id', userId);

    return generateText({
      model: gpt4o, // Use the wrapped model
      messages: [
        { role: 'system', content: 'You are a helpful assistant.' },
        { role: 'user', content: 'How do I get from Paris to Berlin?' },
      ],
      tools: {
        findDirections: findDirectionsTool, // Use the wrapped tool
      },
    });
  });

  return <p>{text}</p>;
}

This demonstrates the three key steps to rich observability:

wrapAISDKModel: Automatically captures telemetry for the LLM provider call
wrapTool: Instruments the tool execution with detailed spans
withSpan: Creates a parent span that ties everything together under a business capability

What’s next?

After sending traces to Axiom:

View your traces in Console
Set up monitors and alerts based on your AI telemetry data
Learn about the GenAI APL functions for querying AI telemetry

​Prerequisite

​Instrument AI SDK calls

​Add context

​Instrument tool calls

​Complete example

​What’s next?

Prerequisite

Instrument AI SDK calls

Add context

Instrument tool calls

Complete example

What’s next?