You need an ABV API key to use the gateway. Sign up at app.abv.dev to get your key (it will look like sk_...)
New users receive $1 in free credits to test the gateway with real LLM models from OpenAI, Anthropic, and Googleâno provider API keys required to get started!
Create a file called first-request.ts (or .js if youâre not using TypeScript) and add this code:
Copy
import { ABVClient } from '@abvdev/client';// Initialize the client with your API keyconst abv = new ABVClient({ apiKey: 'sk_...' // Replace with your actual API key});// Make your first requestconst response = await abv.gateway.chat.completions.create({ provider: 'openai', model: 'gpt-4o-mini', messages: [ { role: 'user', content: 'Explain what an API gateway is in one sentence.' } ]});// Print the responseconsole.log(response.choices[0].message.content);
Run your code with node first-request.js (or ts-node first-request.ts for TypeScript). You should see an explanation of what an API gateway is appear in your terminal.
Now go to your ABV dashboard at app.abv.dev and click on the Traces section. Youâll see a trace for the request you just made. Click into it to see details like token usage, latency, and the full conversation.
This trace appeared automatically without you writing any logging code. The gateway captures every request with complete observability built in.
Now try switching providers to see how easy it is. Change your provider parameter from openai to anthropic and the model to claude-sonnet-4-5:
Copy
const response = await abv.gateway.chat.completions.create({ provider: 'anthropic', // Changed from 'openai' model: 'claude-sonnet-4-5', // Changed from 'gpt-4o-mini' messages: [ { role: 'user', content: 'Explain what an API gateway is in one sentence.' } ]});
Run your code again. Notice that you didnât need to change anything else. The same code structure works with both providers. This is the power of the gatewayâs unified interface.
Hardcoding your API key in your code is not a good practice, especially if youâre committing code to version control. The client library supports reading your API key from an environment variable:
Copy
export ABV_API_KEY=sk_...
Then initialize the client without explicitly passing the key:
Copy
const abv = new ABVClient(); // Automatically uses ABV_API_KEY
Most real applications donât just send a single user message. They set up a system message that configures the modelâs behavior:
Copy
const response = await abv.gateway.chat.completions.create({ provider: 'openai', model: 'gpt-4o-mini', messages: [ { role: 'system', content: 'You are a helpful assistant who explains technical concepts clearly and concisely.' }, { role: 'user', content: 'What is an API gateway?' } ]});
The system message doesnât change the structure of your code, but it does influence how the model responds. Youâll typically use system messages to set the tone, persona, or constraints for your AI application.
Create a file called first_request.py and add this code:
Copy
from abvdev import ABV# Initialize the client with your API keyabv = ABV(api_key='sk_...') # Replace with your actual API key# Make your first requestresponse = abv.gateway.chat.completions.create( provider='openai', model='gpt-4o-mini', messages=[ {'role': 'user', 'content': 'Explain what an API gateway is in one sentence.'} ])# Print the responseprint(response['choices'][0]['message']['content'])
Run your code with python first_request.py. You should see an explanation appear in your terminal.
Visit your ABV dashboard at app.abv.dev and navigate to Traces. Your request appears there with complete details about what happened, including token counts and timing information.
This observability is built in automatically. The gateway traces every request without requiring any logging code from you.
Now try switching providers. Change your provider parameter from openai to anthropic and the model to claude-sonnet-4-5:
Copy
response = abv.gateway.chat.completions.create( provider='anthropic', # Changed from 'openai' model='claude-sonnet-4-5', # Changed from 'gpt-4o-mini' messages=[ {'role': 'user', 'content': 'Explain what an API gateway is in one sentence.'} ])
Run your code again. The same code structure works with both providersâyou just changed one parameter.
Most real applications set up a system message that configures the modelâs behavior:
Copy
response = abv.gateway.chat.completions.create( provider='openai', model='gpt-4o-mini', messages=[ { 'role': 'system', 'content': 'You are a helpful assistant who explains technical concepts clearly and concisely.' }, { 'role': 'user', 'content': 'What is an API gateway?' } ])
The system message influences how the model responds without changing the code structure. Youâll typically use system messages to set the tone, persona, or constraints for your AI application.
When you created the ABV client, you provided your API key. This key authenticates your requests to ABVâs gateway service. The client handles all the authentication details automaticallyâyou never need to think about headers, tokens, or auth flows.
Building the Request
When you called abv.gateway.chat.completions.create(), you provided three key pieces of information:
Provider: Which AI service to route the request to (OpenAI, Anthropic, or Gemini)
Model: Which specific model to use (like gpt-4o-mini or claude-sonnet-4-5)
Messages: The conversation to send to the model
Gateway Processing
The gateway received your request, created a trace, translated it into the providerâs expected format, sent it to the provider, received the response, translated it back to standard format, completed the trace, and returned the response to your code.
Reading the Response
The response contains a choices array because the API supports generating multiple completions for a single request (controlled by the n parameter, which defaults to 1). Each choice has a message object with the content that the model generated.
Automatic Observability
Meanwhile, the trace captured everything about this interaction: what you asked, what the model responded with, how many tokens were used (which affects cost), and how long it took. All of this is available in your dashboard automatically.
Provider Flexibility
When you switched providers, you only changed one parameter. The gateway handled all the differences between OpenAIâs API format and Anthropicâs API format automatically. This is the core value of the unified interfaceâprovider flexibility without code rewrites.
