Primary use stated or inferred cautiously from official documentation.
O
OPENAI / gpt-image-2.6-sunburst
GPT Image 2.6 Sunburst
OpenAI image generation and editing model released on November 4, 2026. Sunburst focuses on detailed compositions and precise edits. It accepts text and images, complexity control, annotations to guide changes, and SVG and GIF output workflows. It has its own API identity and a separate profile from Flare.
01 / SUMMARY
The essential
Maximum input capacity when published by the source.
Documented maximum generation limit.
Verified availability channels.
Primary functional family and verified specialties.
Declared terms for API access, model weights, or self-hosting.
02 / TECHNICAL SHEET
Limits and integration
| API ID | gpt-image-2.6-sunburst |
|---|---|
| Model type | Image |
| Access model | Paid proprietary |
| License | Proprietary |
| Deployment | Hosted API |
| Release | 04 NOV 2026 |
| Knowledge cutoff | Not published |
| Entrance | Text · Image |
| Exit | Image |
| Context window | Not published |
| maximum output | Image; SVG and GIF through documented workflows |
| Reasoning | Not published |
| Published tools | |
| Structured Outings | Not published |
| Batch processing | Not published |
| Prompt cache | Not published |
| Fine-tuning | Not published |
| Verified platforms | OpenAI API |
Illustrations, product assets and edits guided by a reference image. Complexity controls planning and quality controls rendering. These are different settings. Review text, geometry and visual continuity in each result using examples of the intended application.
The model card verifies generation and editing through the Images API. Endpoints, resolutions and limits from earlier models are not automatically inherited. SVG output may add the cost of the model authoring the file. A GIF does not establish general-purpose video generation. Images can contain errors and require rights and usage review.
03 / CAPABILITIES
What it can do
Orientation
Illustrations, product assets and edits guided by a reference image. Complexity controls planning and quality controls rendering. These are different settings. Review text, geometry and visual continuity in each result using examples of the intended application.
Context
Not published · Image; SVG and GIF through documented workflows
Tools and integration
Not published
Access
Images API
Input modalities
TextImage
04 / PRICES
Documented cost
| Concept | Worth | Unit/condition |
|---|---|---|
| Standard input | 5 USD text · 8 USD image / 1M tokens | Standard API rate |
| Cached input | 1.25 USD text · 2 USD image / 1M tokens | Reading reused prefixes |
| Cache write or storage | Not published | The condition varies by provider |
| Standard output | 30 USD / 1M image tokens | May include reasoning tokens |
| Batch input | Not published | Asynchronous processing |
| Batch output | Not published | Asynchronous processing |
Prices per million tokens are 5 USD for input text, 1.25 USD for cached text, 8 USD for input images, 2 USD for cached images and 30 USD for output images. These are not per-image prices. Size, quality and usage change the total. Text and image tokens have different rates and must be budgeted separately.
i Prices change and may depend on level, region or context length. Check the source before making a decision.
05 / EVALUATIONS
How to read the results
“
No public numeric scores specific to this version have been verified. Quality or speed positioning comes from official documentation and is not an Inferama measurement. A reproducible comparison must fix the prompt, references, complexity, quality, format and sample count, and measure actual cost and latency.
i No verified numeric score for the exact version.
Inferama only highlights a “best result” when the metric, test set, configuration, and date allow for an equivalent comparison. The supplier's figures are presented as claims from its own source.
06 / VERSIONS
Chronology
GPT Image 2.6 Sunburst
Version added to Inferama's verified catalog.
07 / SOURCES