Logs

Each log entry provides useful data such as the timestamp, request type, LLM used, tokens generated, thinking tokens and cost. For multimodal models, Logs will also show the image sent with vision/image models, as well as the image generated. By clicking on an entry, a side panel opens up, revealing the entire raw data with the request and response objects. This detailed log can be invaluable when troubleshooting issues or understanding specific interactions. It provides full transparency into each request and response, enabling you to see exactly what data was sent and received. Each log on the AI Gateway has a unique URL. You can copy the link from the address bar and directly share it with anyone in your org.

Request Status Guide

The Status column on the Logs page gives you a snapshot of the gateway activity for every request. The AI Gateway features—Cache, Retries, Fallback, Loadbalance are tracked here with their exact states (disabled, triggered, etc.), making it a breeze to monitor and optimize your usage. Common Queries Answered:

Is the cache working?: Enabled caching but unsure if it’s active? The Status column will confirm it for you.
How many retries happened?: Curious about the retry count for a successful request? See it in a glance.
Fallback and Loadbalance: Want to know if load balance is active or which fallback option was triggered? See it in a glance.

Option	🔴 Inactive State	🟢 Possible Active States
Cache	Cache Disabled	Cache Miss,Cache Refreshed,Cache Hit,Cache Semantic Hit
Retry	Retry Not Triggered	Retry Success on Tries,Retry Failed
Fallback	Fallback Disabled	Fallback Active
Loadbalance	Loadbalancer Disabled	Loadbalancer Active

Manual Feedback

As you’re viewing logs, you can also add manual feedback on the logs to be analysed and filtered later. This data can be viewed on the feedback analytics dashboards.

Config IDs in Logs

If your request has an attached Config, you can see the relevant Config ID separately in the log’s details on the AI Gateway. And to dig deeper, you can just click on the ID and the AI Gateway will take you to the Config where you can view the full details.

DO NOT TRACK

The DO NOT TRACK option allows you to process requests without logging the request and response data. When enabled, only high-level statistics like tokens used, cost, and latency will be recorded, while the actual request and response content will be omitted from the logs. This feature is particularly useful when dealing with sensitive data or complying with data privacy regulations. It ensures that you can still capture critical operational metrics without storing potentially sensitive information in your logs. To enable DO NOT TRACK for a specific request, set the debug flag to false when instantiating your the AI Gateway or OpenAI client, or include the x-portkey-debug:false header with your request.

cURL
OpenAI Python
OpenAI Node

curl 'https://aigw.portkey.ai/v1/chat/completions' \
    -H 'Content-Type: application/json' \
    -H 'x-portkey-provider: $OPENAI_PROVIDER' \
    -H 'Authorization: Bearer $PORTKEY_API_KEY' \
    -H 'x-portkey-debug: false' \
    -d '{
    "model": "gpt-4o",
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant"
      },
      {
        "role": "user",
        "content": "what is a portkey?"
      }
    ]
}'

from openai import OpenAI

client = OpenAI(
    api_key="PORTKEY_API_KEY",
    base_url="https://aigw.portkey.ai/v1",
    default_headers={"x-portkey-debug": False}
)

chat_complete = client.chat.completions.create(
    model="@OPENAI_PROVIDER/gpt-4",
    messages=[{"role": "user", "content": "Say this is a test"}],
)

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

import OpenAI from 'openai';

const openai = new OpenAI({
  apiKey: "PORTKEY_API_KEY",
  baseURL: "https://aigw.portkey.ai/v1",
  defaultHeaders: { "x-portkey-debug": false }
});

async function main() {
  const chatCompletion = await openai.chat.completions.create({
    messages: [{ role: 'user', content: 'Say this is a test' }],
    model: '@OPENAI_PROVIDER/gpt-3.5-turbo',
  });
  console.log(chatCompletion.choices);
}

main();

Introduction

Product

Request Status Guide

Manual Feedback

Config IDs in Logs

DO NOT TRACK

Side-by-side comparison on how a `debug:false` request will be logged

​Share Logs with Teammates

​Request Status Guide

​Manual Feedback

​Config IDs in Logs

​DO NOT TRACK

​Side-by-side comparison on how a debug:false request will be logged

Share Logs with Teammates

Request Status Guide

Manual Feedback

Config IDs in Logs

DO NOT TRACK

Side-by-side comparison on how a `debug:false` request will be logged