OpenAI makes sense when your site already runs on an OpenAI Platform account and one more key is one key too many. The free plugin registers GPT-4.1 mini. Pro adds GPT-5 mini, at about 1.7 times the blended token price.
When to pick OpenAI
Pick OpenAI when you already have a paid Platform account and want the image SEO calls on the same invoice and the same usage dashboard as the rest of your work. On price it sits in the middle of the three: $0.70 per million tokens, against $2.00 for Claude 4.5 Haiku and $0.56 for Gemini 3.1 Flash-Lite. It is not the install default, so choosing it is always a deliberate change.
Platform account, not ChatGPT Plus
An OpenAI Platform account with billing is separate from a ChatGPT Plus subscription. Paying for ChatGPT Plus does not give you API access — they are billed independently. If you only have ChatGPT Plus, sign up at platform.openai.com and add a payment method for API use.
How to get an OpenAI API key
Create an OpenAI Platform account
Go to platform.openai.com and sign up, or sign in if you already have an account from earlier API work.
Add a payment method
Open Settings → Billing and add a card. Any trial credit on a new account expires, and the plugin never switches providers on a failed call — a request refused for billing comes back as the provider’s error, with the image left unoptimized.
Open the API keys page
Go to Dashboard → API keys, or straight to platform.openai.com/api-keys. This is the same link the plugin puts on the API Keys page.
Create a new secret key
Click Create new secret key, name it something you will recognize later — wordpress-image-seo — and copy it. OpenAI shows it once. OpenAI keys start with sk-, which is useful for telling keys apart in a password manager.
Paste it into the plugin
In WP Admin, go to Image SEO → API Keys, paste the key into the OpenAI GPT API card and click Save OpenAI Key. The status badge flips to Configured, the key is stored encrypted, and the plugin verifies it with a live call.
Pick a GPT model
Open the AI Settings metabox on the plugin dashboard and choose from the AI Model dropdown — gpt-4.1-mini on the free plugin, gpt-5-mini with Pro. The provider follows from the model id, so there is no separate provider switch to flip. Click Save Settings.
What Save and Test Key check
Saving no longer checks what a key looks like. Since 1.0.6 the only rejections are structural: an empty value, fewer than 8 or more than 512 characters, or a value containing spaces or control characters. Anything else is stored encrypted.
Verification happens after the save, as a zero-cost request to the provider’s models list — https://api.openai.com/v1/models for OpenAI. The Test Key button on the provider card repeats that request on demand and reports one of three results.
Test Key results
| Setting | Description |
|---|---|
valid
|
The provider accepted the key. The message reads "Key verified with the provider." |
invalid
|
OpenAI answered 400, 401 or 403. Its own error message is passed through unchanged, which is what separates a revoked key from an unpaid balance. |
unverified
|
The check could not complete: a network failure, a timeout or any other status. The key stays saved and can be tested again later. This is never reported as invalid. |
Results are cached for 5 minutes, or 1 minute after a network failure, so repeated clicks do not hammer the provider. A key that fails the test is still stored — the result reports, it does not block.
A key prefix is orientation, not validation
The sk- prefix helps you recognize the key in a password manager. The plugin ignores it. Providers change their key formats — Google changed theirs in 2026 — so a format check rejects valid keys sooner or later. Only the live test tells you whether a key works.
Free-tier OpenAI models
OpenAI models in the free plugin
| Feature | Model id | Blended price / 1M tokens | Output cap, full run |
|---|---|---|---|
| GPT-4.1 mini Cost-effective image analysis — the description the plugin shows in the dropdown. | gpt-4.1-mini | $0.70 | 400 tokens |
GPT-4.1 mini is the only OpenAI model the free plugin registers. It runs the tightest output cap of any free model: 400 tokens on a full run, against 1,024 for Claude 4.5 Haiku and 2,048 for the Gemini Flash-Lite models. That is enough for alt text, filename, title and keywords, and not much more.
The GPT models are also the only ones the plugin sends an explicit temperature with: 0.3 on a full run, 0.7 for keywords. The Claude and Gemini configurations leave temperature unset and take the provider default.
Pro-only OpenAI models Pro
Pro adds GPT-5 mini
With Image SEO Optimizer Pro active, GPT-5 mini joins the OpenAI group in the AI Model dropdown, listed after GPT-4.1 mini — within each provider group the plugin puts the newest model last. At $1.20 per million tokens against $0.70, it costs about 1.7 times as much, with a 600-token output cap instead of 400. Output varies between runs on either model; neither is deterministic.
OpenAI model added by Pro
| Feature | Model id | Blended price / 1M tokens | Output cap, full run Recommended |
|---|---|---|---|
| GPT-5 mini Cost-efficient reasoning for structured tasks — the description the plugin shows in the dropdown. | gpt-5-mini | $1.20 | 600 tokens |
GPT-5 mini is the smallest price step between a free model and its Pro counterpart anywhere in the model list. That makes it the cheapest way to test whether a bigger model changes anything on your images. Pro does not change the default model — a Pro site still runs Gemini 3.1 Flash-Lite until you pick something else.
These prices are per million tokens, not per image
The figures on this page are the blended per-million-token prices the plugin stores for each model and uses to estimate spend. Cost per image depends on image size, prompt length and how many fields you generate, so a per-image number would be a guess. The API Usage dashboard logs every call and shows what you actually spent. Checked against version 1.0.6 on 2026-08-12.
Next steps
Optimization Settings
Pick a model, batch size and request timeout for your chosen provider.
Prompts & Language
Tune the AI's voice with a prompt addon and pick from 133 output languages.
API Usage & Costs
Live dashboard of every AI call, per-provider breakdown, monthly spend.