← Voltar aos guias

First Claude API Call in 5 Minutes with 59API

Why this guide exists

If you want to try Claude in a real app without spending time on provider-specific setup, this walkthrough gets you from zero to a working request in about five minutes. We’ll use 59API, an AI API relay that gives developers low-cost, pay-as-you-go access to Claude models like Opus, Sonnet, Haiku, and Fable, plus GPT models, through a single OpenAI-compatible interface.

The big advantage is simplicity: you do not need to rewrite your app for a custom SDK. 59API works with the OpenAI SDK and is also compatible with Claude Code, Codex, and other OpenAI-style clients. That means you can test faster, switch models more easily, and keep costs under control.

One more reason developers like it: 59API is designed to be among the cheapest relays available while still using native, official-quality models with no downgrade. If you care about output quality and budget, that combination is hard to beat. There is also a referral rebate, which is useful if you plan to share it with teammates or an audience.

Step 1: Create your 59API account and get a key

Start by signing up for 59API and generating an API key in the dashboard. You will use that key exactly like you would with any OpenAI-compatible provider.

• Log in to your 59API account
• Create a new API key
• Copy it somewhere secure
• Keep the base URL handy: https://api.59api.com

At this point, you do not need to manage separate Claude credentials or model-specific onboarding. The relay handles the API layer for you.

Step 2: Install the OpenAI SDK

If you already use the OpenAI SDK, you are nearly done. If not, install it in your project.

• Python: pip install openai
• Node.js: npm install openai

This guide uses the OpenAI SDK because 59API is fully compatible with it. That compatibility is important: it lets you keep your code familiar while routing requests to Claude through 59API.

Step 3: Make your first request

Here is a minimal Python example you can run right away. It sends a simple prompt to Claude through 59API.

Python

from openai import OpenAI

client = OpenAI(
api_key="YOUR_59API_KEY",
base_url="https://api.59api.com/v1"
)

response = client.chat.completions.create(
model="claude-sonnet",
messages=[
{"role": "user", "content": "Write a one-sentence hello from Claude."}
]
)

print(response.choices[0].message.content)

If you prefer Node.js, the pattern is the same.

Node.js

import OpenAI from "openai";

const client = new OpenAI({
apiKey: process.env.API_KEY,
baseURL: "https://api.59api.com/v1"
});

const response = await client.chat.completions.create({
model: "claude-sonnet",
messages: [
{ role: "user", content: "Write a one-sentence hello from Claude." }
]
});

console.log(response.choices[0].message.content);

When you run either example, you should see a Claude-generated response returned through the 59API endpoint. That proves your key, base URL, and model name are all wired up correctly.

Step 4: Pick the right Claude model

Choosing a model depends on the job you want done.

• Claude Haiku for fast, low-cost tasks
• Claude Sonnet for a strong balance of quality and price
• Claude Opus for the hardest reasoning or highest-stakes tasks
• Claude Fable if your workflow supports it and you want to test another model tier

A practical approach is to start with Sonnet for general development, then switch to Haiku for simple summaries or extraction tasks. Because 59API is pay-as-you-go, you can test these tradeoffs without a heavy commitment.

Step 5: Move from test prompt to production

Once the first call works, productionizing is mostly about reliability and cost discipline.

• Store your API key in an environment variable, not in source control
• Add retries for temporary network errors
• Log prompt size and response latency
• Set reasonable max token limits
• Use the smallest model that still meets quality requirements

If you are already using Claude Code or an OpenAI SDK-based application, 59API reduces migration friction because your client logic stays mostly the same. That can save hours when you are experimenting, prototyping, or shipping a new feature under deadline.

Why developers choose 59API

For many teams, the main appeal is a combination of cost, compatibility, and quality. 59API offers cheap access to Claude and GPT models, official-quality outputs, and a clean OpenAI-style integration path. That makes it a practical choice for indie builders, startups, and agencies that want to keep inference costs predictable.

It is also useful when you want to compare models side by side or route different workloads to different tiers without changing your entire stack. In short: you get a simple developer experience without giving up model quality.

What to do next

You now have the essentials: an API key, an OpenAI-compatible client, a base URL, and a working Claude request. From here, you can build chat features, content workflows, extraction pipelines, or internal tools with very little setup.

If you want a low-cost way to keep experimenting with Claude while staying close to production-ready patterns, sign up for 59API and try your first request today.

Preços · Docs