GPT Image 2.5 Flare
Everyday generation and editing up to 4K, with xhigh and max quality tiers.
GPT Image 2.5 · Flare · Sunburst · REST API
GPT Image 2.5 API
Generate and edit images with OpenAI GPT Image 2.5 Flare and Sunburst, up to 4K and five quality tiers, with one API key and flat per-image credit quotes instead of token math. Preview the exact cost of any request, then poll for the result.
cURL · GPT Image 2.5 Flare
curl --request POST \
https://www.makeinfluencer.ai/api/v1/models/gpt-image-2.5-flare/generations \
--header "Authorization: Bearer $MAKEINFLUENCER_API_KEY" \
--header "Idempotency-Key: gpt-image-2.5-flare-001" \
--header "Content-Type: application/json" \
--data '{
"input": {
"prompt": "Studio product shot of a matte black water bottle on travertine, soft window light, legible label reading HYDRA",
"aspectRatio": "3:4",
"resolution": "2k",
"quality": "medium"
}
}'How It Works
Get Started
Create an API key
In Dashboard → Developer API → Keys, create a revocable mi_ key and send it as a Bearer token.
Preview the cost
POST the same input to preview-credits and get the exact credit quote back. Previews never charge.
Generate and poll
POST to /models/{modelId}/generations, receive HTTP 202 with a generation ID, then poll the image status endpoint until terminal is true.
GPT Image API pricing
GPT Image 2.5 per image, by resolution and quality
Live credit quotes for a single 1:1 request at each resolution and quality tier. Flare is the everyday generator, Sunburst is tuned for precision edits, and GPT Image 2 stays available for existing pipelines.
| Model ID | Model | Resolution · quality | Typical time | Credits per image |
|---|---|---|---|---|
| gpt-image-2.5-flare | OpenAI GPT Image 2.5 Flare | 1K · low | ~20s | 502 |
| gpt-image-2.5-flare | OpenAI GPT Image 2.5 Flare | 2K · low | ~20s | 1,003 |
| gpt-image-2.5-flare | OpenAI GPT Image 2.5 Flare | 4K · low | ~20s | 1,504 |
| gpt-image-2.5-flare | OpenAI GPT Image 2.5 Flare | 1K · medium | ~20s | 1,204 |
| gpt-image-2.5-flare | OpenAI GPT Image 2.5 Flare | 2K · medium | ~20s | 2,006 |
| gpt-image-2.5-flare | OpenAI GPT Image 2.5 Flare | 4K · medium | ~20s | 3,509 |
| gpt-image-2.5-flare | OpenAI GPT Image 2.5 Flare | 1K · high | ~20s | 4,512 |
| gpt-image-2.5-flare | OpenAI GPT Image 2.5 Flare | 2K · high | ~20s | 7,519 |
| gpt-image-2.5-flare | OpenAI GPT Image 2.5 Flare | 4K · high | ~20s | 13,534 |
| gpt-image-2.5-flare | OpenAI GPT Image 2.5 Flare | 4K · xhigh | ~20s | 24,061 |
| gpt-image-2.5-flare | OpenAI GPT Image 2.5 Flare | 4K · max | ~20s | 50,126 |
| gpt-image-2.5-sunburst | OpenAI GPT Image 2.5 Sunburst | 1K · medium · edit with 1 reference | ~20s | 1,955 |
| gpt-image-2 | OpenAI GPT Image 2 | 1K · medium | ~30s | 3,008 |
Quotes are calculated from the live model pricing when this page is built. Edits are priced on their own tier and add a charge for each reference image after the first. POST /models/{modelId}/preview-credits returns the exact cost of your own payload without charging.
Quickstart
Your first GPT Image 2.5 request
One POST creates the job and returns HTTP 202 with a generation ID. Add imageUrls to switch the same request to an edit, then poll the image status endpoint until terminal is true.
POST
https://www.makeinfluencer.ai/api/v1/models/gpt-image-2.5-flare/generationscURL
curl --request POST \
https://www.makeinfluencer.ai/api/v1/models/gpt-image-2.5-flare/generations \
--header "Authorization: Bearer $MAKEINFLUENCER_API_KEY" \
--header "Idempotency-Key: gpt-image-2.5-flare-001" \
--header "Content-Type: application/json" \
--data '{
"input": {
"prompt": "Studio product shot of a matte black water bottle on travertine, soft window light, legible label reading HYDRA",
"aspectRatio": "3:4",
"resolution": "2k",
"quality": "medium"
}
}'POST · preview-credits · no charge
curl --request POST \
https://www.makeinfluencer.ai/api/v1/models/gpt-image-2.5-flare/preview-credits \
--header "Authorization: Bearer $MAKEINFLUENCER_API_KEY" \
--header "Content-Type: application/json" \
--data '{
"input": {
"prompt": "Studio product shot of a matte black water bottle on travertine, soft window light, legible label reading HYDRA",
"aspectRatio": "3:4",
"resolution": "2k",
"quality": "medium"
}
}'GET · poll until terminal
curl \
https://www.makeinfluencer.ai/api/v1/generations/image/GENERATION_ID \
--header "Authorization: Bearer $MAKEINFLUENCER_API_KEY"Features
What you get with the GPT Image API
01
Flare and Sunburst, one contract
gpt-image-2.5-flare, gpt-image-2.5-sunburst and gpt-image-2 share one request shape: a prompt plus optional imageUrls, aspectRatio, resolution and quality.
02
Up to 4K and five quality tiers
Render at 1K, 2K or 4K with low, medium, high, xhigh or max quality, and pay only for the tier you ask for.
03
Edits with up to 16 references
Add imageUrls and the same request becomes an edit. Sunburst keeps faces, products and layouts intact across up to 16 references.
04
Per-image quotes, not token math
Every request has a fixed credit quote you can check with preview-credits before you spend, from the balance you already use in the app.
05
Safe retries
Send an Idempotency-Key header and a retried request with the same body replays the original response instead of starting a second job.
06
Also in Claude and Cursor
The same models are available through the MCP connector, so an agent can generate GPT Image 2.5 images on your account.
Price check
OpenAI's own list price for GPT Image 2.5
Public list prices for comparable requests elsewhere, verified 29 September 2026, next to our credit quote for the same request. Our credits come from the balance you already use in the app, and preview-credits returns the exact figure before you spend anything.
| Model | Provider | Their list price | Their example | Our model ID | Our credits, same request |
|---|---|---|---|---|---|
| GPT Image 2.5 Flare and Sunburst | OpenAI API | $30 per 1M image output tokens, $8 per 1M image input tokens, $5 per 1M text input tokens | Token-based, so cost varies with size and quality | gpt-image-2.5-flare | 1,204 (1K · medium) |
Third-party prices are copied from each provider's public model page on 29 September 2026 and can change at any time. Sources: https://developers.openai.com/api/docs/models/gpt-image-2.5-flare.
Choosing a GPT Image model
Flare, Sunburst or GPT Image 2?
Start on Flare at 1K low or medium for drafts, raise quality and resolution only for the images you keep, and send precision edits to Sunburst. Switching is a one-word change to the model ID.
GPT Image 2.5 Sunburst
Precision edits that keep faces, products and layouts intact across up to 16 references.
GPT Image 2
The previous generation, kept for pipelines that already depend on it.
Practical workflow
- 1
Create a key
Dashboard → Developer API → Keys. Keys start with mi_.
- 2
Upload references
POST /assets/presign, upload, then pass the URL in imageUrls.
- 3
Preview and generate
Quote the body with preview-credits, then POST it to generations.
- 4
Poll and store
Poll GET /generations/image/{id} and save the URLs from urls.
GPT Image is an OpenAI model family. MakeInfluencer.ai is an independent API provider and is not affiliated with or endorsed by OpenAI.
Trusted by over 300,000+ creators
FAQ
Frequently Asked Questions
Ship GPT Image 2.5 in your product today
Create an API key, preview a request and generate your first GPT Image 2.5 image in a few minutes.
Start creating in minutes · Pay as you go