Build next-gen apps with gpt-image-2
Pricing
Text to Image / Image Edit · Image
Per 1M Tokens- Official Price
- Input $5.00 / Output $30.00
- TokenLab Price
- Input $3.50 / Output $21.00
- Discount
- 30%
| Official PricePer 1M Tokens | TokenLab PricePer 1M Tokens | Discount | |
|---|---|---|---|
| Text to Image / Image Edit · Image | Input $5.00 / Output $30.00 | Input $3.50 / Output $21.00 | 30% |
| Cache Read | $1.25 | $0.875 | 30% |
One-click test
Sign in once and Web Agent keeps this model, prompt, and request preset for you.
Test gpt-image-2 in Web Agent. Run the recommended text-to-image image request at /v1/images/generations, then show the request body, returned image or task status, and model-specific constraints.
API workbench
The default route for production. The code sample below uses this endpoint with the format you pick.
curl -X POST "https://api.tokenlab.sh/v1/images/generations" \
-H "Authorization: Bearer sk-xxx" \
-H "Content-Type: application/json" \
-d '{
"operation": "text-to-image",
"quality": "auto",
"size": "auto",
"model": "gpt-image-2",
"prompt": "A minimalist product photo of matte black headphones on a soft blue background."
}'Use cases
Best forText to Image
Producing product imagery, illustrations, and design variations
Product visuals
Make campaign images, catalog scenes, and design directions from a few prompts.
Iterative editing
Try edits and variations using the request shape this model already accepts.
Creative QA
Sanity-check prompt behavior, output count, and response mode before you ship.
Side-by-side test
Compare real response quality, latency, and price for production defaults.
Prompt examples
Generate a clean product shot of matte black headphones on a soft blue gradient.
Edit the source image into a premium ecommerce hero with natural shadows.
Give me three visual directions for a developer-tool launch banner.
Cost Calculator
FAQ
How much does gpt-image-2 cost?
On TokenLab, gpt-image-2 costs Input $3.50 / Output $21.00 Per 1M Tokens. The pricing table above shows the full breakdown.
What is gpt-image-2 best for?
gpt-image-2 is a strong fit for Text to Image, Image Edit. You can call it through TokenLab with one API key.
How do I call the gpt-image-2 API?
Get a TokenLab API key, then send your request to https://api.tokenlab.sh/v1/images/generations. The API workbench above has a recommended endpoint and copy-ready code.
Which endpoint should gpt-image-2 use?
Use https://api.tokenlab.sh/v1/images/generations as the default for gpt-image-2. If a provider-native format is supported, the API workbench shows that endpoint too.
Can I test gpt-image-2 before integrating it?
Yes. Try in Web Agent opens a ready test for gpt-image-2 and keeps your prompt after sign-in, so you don’t lose context.
Which operations does gpt-image-2 support?
gpt-image-2 supports Image Edit, Text to Image. Pick an operation in the API workbench above to see the matching endpoint and code sample.
