GPT Image 2.6 Flare Official
gpt-image-2.6-flare:official is the public invocation ID for GPT Image 2.6 Flare. This variant is billed based on actual Token usage. It focuses on fast generation and editing, supports text-to-image generation and reference image editing, and uses the GPT Image 2.5 image API.
Bring this model into your workflow
Submit requests to the public API at api.acedata.cloud using the documented parameters, then use the results in your application.
- API host
api.acedata.cloud- model
gpt-image-2.6-flare:official
Input parameters and result formats vary by service. Use the public API for this model and follow its guide for generation, task retrieval and editing operations.
Specifications and API
- Creation Methods
- Text-to-image generation; reference image editing
- Output Formats
- PNG, JPEG, WebP
- Quality Options
- auto, low, medium, high, xhigh, max
Select a Model
Flare focuses on fast generation and editing, while Sunburst focuses on detailed composition and editing. Explicitly specify gpt-image-2.6-flare:official; do not use gpt-image-2.6 with the variant name omitted.
Text-to-Image Generation
Submit a prompt through the image generation API, describing the subject, scene, lighting, color palette, and aspect ratio. You can first generate one image to check the composition, then adjust the quality and size as needed.
Edit Reference Images
Submit image and prompt through the image editing API. JSON accepts image URLs, while multipart accepts local files; provide up to 16 reference images. Explain the role of each image and what needs to be preserved or modified.
Billing and Results
Billing is based on actual text input, reference image input, and image output Tokens, with the same rates as 2.5 official. Prices before a request are estimates; the final amount is based on usage records. By default, image links are read from data; when b64_json is selected, only one image is returned. For long-running tasks, you can pass async or callback_url, then use the original task_id to query the completed result.
Usage Limits
Use auto or WIDTHxHEIGHT for size. Width and height must be multiples of 16, the longest side must not exceed 3840, total pixels must be 655,360–8,294,400, and the aspect ratio must not exceed 3:1. n is 1–10, and b64_json requires n=1. This API does not currently support SVG/GIF. Version 2.6 does not configure cross-model substitution.
Frequently Asked Questions
Do generation and editing use the same model?
Yes, both endpoints use the full gpt-image-2.6-flare:official.
Are xhigh and max supported?
Yes, both generation and editing support them; higher quality may increase wait time and official usage.
How should the reverse suffix be understood?
It is an explicit alias for the corresponding standard version and is billed by the number of successfully generated images.
How is official billed?
It is billed by actual Token usage, with the same rates as 2.5 official, rather than a fixed per-image price.
What should I do if asynchronous waiting times out?
Keep the original task_id and query the task status to avoid submitting duplicate generation requests.
Use it in your favorite tools
Choose a development approach or application suited to this model and follow its setup guide.
↗Connect gpt-image-2.6-flare:official to Python SDK
Python SDK Integration Guide
SDK installation, authentication and examples↗Connect gpt-image-2.6-flare:official to TypeScript SDK
TypeScript SDK Integration Guide
SDK installation, authentication and examples
↗OpenAI Images Generations API
API parameters and request examples↗OpenAI Images Edits API
API parameters and request examplesQuickstart
This is only a basic call example. See the full docs for more parameters and advanced usage.
View Docs