Your Web optimization information to the ChatGPT API

ChatGPT announced the rollout of its API (GPT 3.5 Turbo) on March 1. 

I’m bullish on ChatGPT’s utility for several completely different Web optimization-related features like keyword research, local SEO, content, and link building. Having spent a lot time utilizing ChatGPT, I’m additionally painfully conscious of its limitations.

Whereas the API received’t be a panacea (and the online interface is definitely significantly better for some duties), it will probably assist handle among the shortcomings of the online interface.

This text will present you easy methods to maximize ChatGPT’s API with particular Web optimization use circumstances.

Tips on how to use the ChatGPT API

To leverage the ChatGPT API, you want to have the ability to entry the API within the first place. ChatGPT’s dad or mum firm OpenAI has intensive documentation for utilizing the API.

When you’re seeking to study extra about constructing a software or interacting immediately with the API there’s additionally a great walk-through here.

You can too use AppsScript to question the ChatGPT API in Google Sheets, which we’ll stroll via right here step-by-step.

No matter your method, you’ll want to start out by getting an API key.

Getting your ChatGPT API key

After you have an OpenAI account, you’ll be able to generate your API key both by following this link whereas logged in or clicking View API keys within the profile dropdown:

ChatGPT - View API keys

Then click on Create new secret key.

ChatGPT - Create new secret key

Copy the API key you generated.

ChatGPT - API key generated

Connecting the ChatGPT API to Google Sheets

There’s a simple approach to join ChatGPT to Google Sheets (h/t Keith Mint).

First, create a brand new Google Sheet, then click on on Extensions and select Apps Script:

ChatGPT API - Google Sheets extension

You then paste the next code (along with your API key rather than YOUR API KEY):

const MAX_TOKENS = 800;
const TEMPERATURE = 0.9;

perform AI_ChatGPT(immediate, temperature = 0.4, mannequin = "gpt-3.5-turbo") {
  const url = "";
  const payload = {
    mannequin: mannequin,
    messages: [
      { role: "system", content: "You are a helpful assistant." },
      { role: "user", content: prompt },
    temperature: TEMPERATURE,
    max_tokens: MAX_TOKENS,
  const choices = {
    contentType: "utility/json",
    headers: { Authorization: "Bearer " + SECRET_KEY },
    payload: JSON.stringify(payload),
  const res = JSON.parse(UrlFetchApp.fetch(url, choices).getContentText());
  return res.decisions[0].message.content material.trim();

Click on save inside Apps Script:

ChatGPT API - Apps Script

Then you should utilize the next perform format to use a immediate to a cell:


ChatGPT Google Sheet prompt formula

As Mint factors out in his article, you may as well reference a cell if you wish to have a number of cells use prompts that refer again to 1 cell (just like the title or matter of a weblog put up):

ChatGPT - Google Sheet prompt formula with multiple cells

Within the instance above, I used easy prompts just like the one pictured, then created a second paragraph for this matter. (We’ll stroll via extra particular purposes for the API shortly.) 

ChatGPT API pricing

Earlier than you begin leveraging the ChatGPT API for Web optimization duties, it’s important to grasp the pricing.

The value for the gpt-3.5-turbo API (the ChatGPT API) is $0.002 per 1,000 tokens, which is 10x cheaper than the prevailing GPT-3.5 API.

To higher perceive what the pricing really winds up wanting like, you’ll want to perceive how tokens work.

ChatGPT API tokens

OpenAI has a good breakdown and a useful free tokenizer tool that can assist you decide what number of tokens a selected textual content will likely be and the way the textual content is damaged down (in case you’ll want to cut back the variety of tokens for a immediate or response).

A number of key issues to remember:

  • By default, the API can return a most of 4,096 tokens.
  • Tokens are a illustration of how a lot textual content your immediate and response are. It is a key issue, as longer prompts can shorten your response output.
  • Textual content is translated into tokens and roughly breaks all the way down to round 4 characters in English.

OpenAI additionally offered this useful breakdown of how tokens are calculated from textual content:

  • 1 token ~= 4 chars in English
  • 1 token ~= ¾ phrases
  • 100 tokens ~= 75 phrases


  • 1-2 sentence ~= 30 tokens
  • 1 paragraph ~= 100 tokens
  • 1,500 phrases ~= 2048 tokens

To get extra context on how tokens stack up, contemplate this:

  • Wayne Gretzky’s quote, “You miss 100% of the photographs you don’t take,” accommodates 11 tokens.
  • OpenAI’s charter accommodates 476 tokens.
  • The transcript of the U.S. Declaration of Independence accommodates 1,695 tokens.

So when you used a brief immediate to generate a 1,500-word article, it will be lower than half a cent.

Get the day by day publication search entrepreneurs depend on.

Particular API use circumstances for Web optimization

The API may also help with quite a lot of the identical Web optimization-related duties because the ChatGPT internet interface, however the two have some important variations, making some duties higher for one than the opposite.

Understanding that can make it easier to decide which to make use of for Web optimization duties.

ChatGPT API vs. internet interface

The most important variations embody the next:

Scale and bulk duties

If you wish to combine ChatGPT with an present utility or spreadsheet, you will want to make use of the API. 

Moreover, the API will likely be your buddy if you wish to carry out a selected perform utilized throughout a number of cases (e.g., generate meta descriptions for a number of key phrases).

High quality-tuning and relationship between prompts

Presently, ChatGPT’s API doesn’t assist fine-tuning. When you create a number of prompts via the API, they will not have a relationship. 

You’ll be able to create a system message to use to a number of prompts and responses, however OpenAI has stated that these are continuously at the moment ignored by the gpt-3.5-turbo API. 

This implies when you have a job that requires a number of prompts and for ChatGPT to maintain the context of a whole dialog, you will need to use the online interface.

Character limits

The API has a token restrict of 4,096 which interprets to round 16,384 characters per interplay for every immediate and response

Character limits for the online interface can range, however typically, the immediate and response are restricted to round 2,048 characters, or 4,096. 

So for duties that require extra intensive prompts or extra important responses, the API will likely be a greater possibility. 

There are additionally extra choices for structuring prompts and duties in a method that provides you a lengthier mixed output when you’re utilizing code relatively than one thing just like the Google Sheets integration.


Once more, the API is priced by utilization (and affords a free trial with $18 price of tokens), and the online interface at the moment affords a free model and a $20/mo. paid model. 

Instance ChatGPT API prompts

Let us take a look at particular use circumstances the place you’d need to contemplate the API over the online interface.

Title tags and meta descriptions

An apparent use case the place the API is sensible is having ChatGPT generate title tags or meta descriptions at scale.

You need to use related prompts to those who work within the internet interface right here, however when you construction them correctly and lay out your spreadsheet proper, you’ll be able to take the primary immediate after which rapidly apply that to a number of URLs or key phrases: 

ChatGPT API - Title tags and meta descriptions

Be aware that the free plan notably is price restricted, so you might have errors the place the cells day out, through which case you’ll want to delete and re-paste:

ChatGPT API - Google Sheets errors

And as at all times, understand that:

  • ChatGPT cannot crawl the online, so it is both utilizing prior data of a URL from the coaching interval or an assumption in regards to the URL primarily based on phrases within the URL to generate options
  • ChatGPT’s output can typically be fallacious or deceptive and must be edited.

You need to use this similar format for title tags. (I will have an article focusing particularly on utilizing ChatGPT to generate and replace title tags popping out quickly).

Longer content material and put up outlines

You need to use the online interface in ChatGPT to create chunks of content material and descriptions fairly simply.

If you wish to make an extended article or if you are going to create a sequence of outlines on completely different subjects, nevertheless, it may be a clunky expertise.

The API is smoother for these duties.

First, you’ll be able to chunk off a put up you wrote into sections. Then line up the sections and pull your immediate down:

ChatGPT API - longer content and post outlines

Alternatively, you might have ChatGPT generate a number of outlines that you just then have a author (or writers) fill in:

ChatGPT API - article outlines

Then, you might have the API write the content material one part at a time:

ChatGPT API - write article sections

Once more, right here you might take these prompts, load them one after the other throughout the define (altering every immediate for the suitable part), after which simply pull the identical formulation throughout a number of outlines and have quite a lot of textual content particular to the subsections of every put up generated.

My expertise is that this helps you keep away from token limits, and even pedestrian prompts just like the one above mixed with having ChatGPT create an overview will generate higher content material than when you ask the software to “write a weblog put up.” 

Past that, you’ll be able to additional enhance content material high quality by doing issues like:

  • Ask it to incorporate particular phrases (both since you need them on the web page otherwise you need to add inside hyperlinks for that phrase).
  • Feed it statistics or quotes to work into particular sections of the put up. (That is notably useful when you have a subject that requires up-to-date ways and statistics, provided that GPT-3 was not educated on latest knowledge.)
  • Tweak your prompts to output the tone and formatting you need (extra on this shortly).

And, as at all times, layer on human modifying.


There are a number of FAQ-related features the API may also help with.

First off, you’ll be able to generate an inventory of FAQ inquiries to be related to a weblog put up:


Subsequent, you’ll be able to have the ChatGPT API reply these (once more: proceed with warning in relation to output high quality and accuracy):

ChatGPT API - FAQs - answers


You can too have ChatGPT generate schemas for you throughout a number of pages. 

On this case, we are able to apply FAQ schema to the FAQs it created for us:

ChatGPT API - Schema

Convert content material to HTML

One other cool use case for ChatGPT is to transform textual content to HTML. 

First, let’s convert our put up from textual content to HTML:

ChatGPT API - Convert content to HTML

A number of issues to notice right here:

  • As you’ll be able to see, the headers in every part had been initially formatted with paragraph tags. I fastened this within the immediate by including, “Format the header of the part as an h2, and every other headlines on this part as an h3.”
  • I wasn’t capable of mix your entire put up (which was round 1100 phrases) into one cell to be transformed to HTML, so I needed to chunk it off and gave particular directions in my immediate for every cell to verify ChatGPT did not layer within the formatting for a whole HTML doc in each cell.
  • You may additionally get some wonky formatting, like extra quotes you did not anticipate within the output. 

As with all facets of ChatGPT, preserve refining your prompts and at all times verify the output.

Now that now we have our put up in HTML, we are able to begin to do some cool issues with inside linking.

We will inform ChatGPT so as to add inside hyperlinks from particular phrases to particular pages anyplace within the HTML we simply generated:

ChatGPT API - Add internal links

If we had been making a cluster of pages, we may create guidelines particular to every web page and apply them to the related HTML.

This fashion, every thing we generate is interlinked the best way we would like, the HTML is able to go, and the FAQ schema is added appropriately.

I attempted to create a rule that was a bit of extra difficult, asking ChatGPT to hyperlink phrases. Here’s what I added to my immediate:

  • “Any time you see the phrases making and snigger inside 5 phrases of one another, create a hyperlink with these two phrases and the entire phrases in between them to”

Right here is the hyperlink that was added:

ChatGPT API - Wrong hyperlinks

That is not what I requested for, and in addition, it did not hyperlink each occasion of stand-up as I requested it to.

I will have to refine my prompts and verify my outputs.

Outreach templates

When you’re reaching out to a number of locations for hyperlink outreach or visitor put up placements, you should utilize the ChatGPT API to create a number of outreach templates for you:

ChatGPT API - Outreach templates

When you have completely different sorts of templates, get artistic with making use of these prompts throughout completely different outreach targets.

Utilizing the online interface and the API in tandem (a.okay.a., carry your prompts)

Two issues are true:

  • The API is best for bigger tasks and performs many prompts concurrently.
  • The online interface is continuously higher at getting you to a wonderful output since you’ll be able to shuttle with ChatGPT to offer context, evaluate the output, present suggestions, and so forth.

One approach to get one of the best of each worlds is to create your immediate within the internet interface after which apply it to a number of objects by way of the API.

Let us take a look at a selected instance from this put up. My inside linking immediate did not work by way of the API. It is difficult to troubleshoot by way of the API as a result of you’ll be able to’t give ChatGPT suggestions or ask why the immediate failed.

Enter, immediate technology by way of the online!

My typical ChatGPT course of is to: 

  • Give it chunks of context.
  • Test for understanding. 
  • Assessment the output for errors and provides it extra suggestions to attain my desired outcome.

To have the ability to do that for inside linking guidelines, let’s begin with the online interface to wash up our ChatGPT immediate.

First, I need to give ChatGPT some context. (Bear in mind: ChatGPT would not find out about its personal API!) 

I need to give it details about the API, share the HTML I am beginning with, share the immediate I used, and share the output I received after which ask ChatGPT to diagnose the problem and rewrite the immediate for me.

Let’s examine the way it goes:

ChatGPT web - Prompt creation

When you do not pre-empt it, ChatGPT will repeatedly interrupt you to fireside (continuously irrelevant) solutions and options (like an keen scholar who did not do the studying).

I copied and pasted the textual content from this page in 4 prompts, the HTML I used to be making an attempt so as to add hyperlinks to, the total Sheets perform I would used, and the output I would gotten.

Subsequent, I lastly shared the problem with the output:

ChatGPT web - Prompt creation for Google Sheets

After which ChatGPT fastened the immediate for me.

ChatGPT web - Fixed prompt Google Sheets

Properly, it wasn’t really fastened.

ChatGPT web - Prompt syntax error

ChatGPT is relentlessly well mannered even when you’re getting a bit testy, and after I shared the immediate, it analyzed it for me:

ChatGPT Web Prompt Feedback 800x557

The options on HTML dimension are good ones, however I used to be nonetheless getting the error:

ChatGPT web - Google Sheet max character limit

This time, the immediate labored!

To deal with the max tokens difficulty, I can go to Apps Script to regulate that quantity:

ChatGPT API - Google Sheet fix character limit

Or clearly, if I am not utilizing Sheets, it isn’t prone to be a difficulty (till I hit the 4096 tokens).

Get artistic and search for options

Web optimization purposes for the ChatGPT API go effectively past what’s listed right here. 

When you’re looking out for tactics to make use of the platform and might get artistic you will discover many extra purposes like:

  • Programmatic options: You’ll be able to transcend Google Sheets to seek out thrilling and scalable makes use of for the ChatGPT API.
  • Combining a number of APIs: Take into consideration the way you may be capable of use the ChatGPT API in unison with APIs like Google Search Console, Ahrefs, Semrush or related. What issues do you need to clear up? 
  • Extra environment friendly or higher workflows: Take inventory of the duties you and your group full day by day. Are there objects that ChatGPT’s API could possibly both mean you can just do as effectively however extra effectively, or to enhance your work product round?

With the latest release of GPT-4, extra alternatives for leveraging the platform will probably proceed to crop up.

Opinions expressed on this article are these of the visitor writer and never essentially Search Engine Land. Employees authors are listed here.

Source link

Add a Comment

Your email address will not be published. Required fields are marked *