Quick Start

1. Get your API Key

Create an account and get your API key from Settings → API Keys.

2. Choose Your Integration

Vercel AI SDK

Recommended for new projectsUse Vercel AI SDK for multi-provider support with a unified API. Switch between OpenAI, Anthropic, Google, and 20+ other providers without changing your code.

Provider SDKs

For existing integrationsWrap your existing provider SDK clients (Anthropic, OpenAI, Mistral, etc.) for instant observability.

Quick Example: Vercel AI SDK

Install dependencies

npm install observ-sdk ai @ai-sdk/openai

Wrap your model

import { Observ } from "observ-sdk";
import { openai } from "@ai-sdk/openai";
import { generateText } from "ai";

const observ = new Observ({
  apiKey: "your-observ-api-key",
  recall: true, // Enable semantic caching
});

// Wrap the model
const model = observ.wrap(openai("gpt-4"));

Use it normally

const result = await generateText({
  model,
  prompt: "What is TypeScript?",
});

console.log(result.text);

View traces in dashboard

All your LLM calls are now automatically traced! View them in the Dashboard.

Quick Example: Provider SDKs

TypeScript
Python

Install dependencies

npm install observ-sdk @anthropic-ai/sdk

Wrap your client

import Anthropic from "@anthropic-ai/sdk";
import Observ from "observ-sdk";

const ob = new Observ({
  apiKey: "your-observ-api-key",
  recall: true,
});

const client = new Anthropic({ apiKey: "your-anthropic-key" });
const wrappedClient = ob.anthropic(client);

Use it normally

const response = await wrappedClient.messages.create({
  model: "claude-sonnet-4-20250514",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Hello!" }],
});

console.log(response.content[0].text);

Install dependencies

pip install observ-sdk anthropic

Wrap your client

import anthropic
from observ import Observ

ob = Observ(
    api_key="your-observ-api-key",
    recall=True,
)

client = anthropic.Anthropic(api_key="your-anthropic-key")
wrapped_client = ob.anthropic(client)

Use it normally

response = wrapped_client.messages.create(
    model="claude-sonnet-4-20250514",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello!"}],
)

print(response.content[0].text)

What’s Next?

Session Tracking

Group related calls with session IDs

Custom Metadata

Attach metadata to your traces

View Dashboard

Analyze your LLM usage

Set recall: true to enable semantic caching and reduce costs by up to 85% on similar prompts.

Getting Started

Usage

Features

1. Get your API Key

2. Choose Your Integration

Vercel AI SDK

Provider SDKs

Quick Example: Vercel AI SDK

Quick Example: Provider SDKs

What’s Next?

Session Tracking

Custom Metadata

View Dashboard

​1. Get your API Key

​2. Choose Your Integration

Vercel AI SDK

Provider SDKs

​Quick Example: Vercel AI SDK

​Quick Example: Provider SDKs

​What’s Next?

Session Tracking

Custom Metadata

View Dashboard

1. Get your API Key

2. Choose Your Integration

Quick Example: Vercel AI SDK

Quick Example: Provider SDKs

What’s Next?