← Back to Docs

Your First Request

A step-by-step guide to making your first chat completion request with AllRoutes.

Overview

This guide walks you through making your first API call to AllRoutes, from getting your API key to handling the response and checking your usage.

Step 1: Get Your API Key

  1. Sign up or log in at allroutes.ai/dashboard
  2. Go to Settings > API Keys
  3. Click Create New Key, give it a name, and copy the key
  4. Store it securely as an environment variable:
export ALLROUTES_API_KEY="allroutes_sk_..."

Step 2: Install Your SDK

Choose the SDK for your language:

# Python (requires 3.8+)
pip install allroutes

# Node.js / TypeScript (requires Node 18+)
npm install @allroutes/sdk

# Go (requires 1.21+)
go get github.com/allroutes-ai/allroutes-go/allroutes

Step 3: Send a Completion Request

Python

import os
from allroutes import AllRoutesClient

client = AllRoutesClient(api_key=os.environ["ALLROUTES_API_KEY"])

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What are the three laws of thermodynamics?"},
    ],
    temperature=0.7,
    max_tokens=500,
)

print(response.content)

Node.js

import AllRoutes from "@allroutes/sdk";

const client = new AllRoutes({ apiKey: process.env.ALLROUTES_API_KEY });

const completion = await client.chat.completions.create({
  model: "gpt-4o",
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "What are the three laws of thermodynamics?" },
  ],
  temperature: 0.7,
  max_tokens: 500,
});

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

cURL

curl https://api.allroutes.ai/v1/chat/completions \
  -H "Authorization: Bearer $ALLROUTES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "What are the three laws of thermodynamics?"}
    ],
    "temperature": 0.7,
    "max_tokens": 500
  }'

Step 4: Handle the Response

The API returns an OpenAI-compatible JSON response:

{
  "id": "chatcmpl-abc123def456",
  "object": "chat.completion",
  "created": 1714000000,
  "model": "gpt-4o",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The three laws of thermodynamics are..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 28,
    "completion_tokens": 156,
    "total_tokens": 184
  }
}

Response Fields

FieldDescription
idUnique identifier for the completion
modelThe model that generated the response
choices[].message.contentThe generated text
choices[].finish_reasonWhy generation stopped: stop, length, tool_calls
usage.prompt_tokensNumber of tokens in the input
usage.completion_tokensNumber of tokens generated
usage.total_tokensTotal tokens consumed

Step 5: Check Usage and Cost

After making requests, check your credit balance and usage:

Python

credits = client.get_credits()
print(f"Balance: ${credits['balance_usd']:.2f} USD")
print(f"Lifetime spend: ${credits['lifetime_spend_usd']:.2f} USD")

Node.js

const credits = await client.getCredits();
console.log(`Balance: $${credits.balance_usd.toFixed(2)} USD`);

cURL

curl https://api.allroutes.ai/v1/credits \
  -H "Authorization: Bearer $ALLROUTES_API_KEY"

Error Handling

Always wrap API calls in error handling:

import httpx
from allroutes import AllRoutesClient

client = AllRoutesClient(api_key="allroutes_sk_...")

try:
    response = client.chat.completions.create(
        model="gpt-4o",
        messages=[{"role": "user", "content": "Hello!"}],
    )
except httpx.HTTPStatusError as e:
    if e.response.status_code == 401:
        print("Invalid API key")
    elif e.response.status_code == 429:
        print("Rate limit exceeded, try again later")
    elif e.response.status_code == 402:
        print("Insufficient credits")
    else:
        print(f"API error {e.response.status_code}: {e.response.text}")
except httpx.TransportError as e:
    print(f"Network error: {e}")

The SDKs automatically retry on transient errors (5xx and 429) with exponential backoff.

See Also