> ## Documentation Index
> Fetch the complete documentation index at: https://docs.apiyi.com/llms.txt
> Use this file to discover all available pages before exploring further.

# GPT-Image-2.6: Faster Creation and Editing

> OpenAI GPT-Image-2.6 Flare and Sunburst are live on APIYI with faster generation, GIF, SVG and image markup. Complexity is currently unsupported; pricing is unchanged.

## Key Highlights

* **Two models are live**: APIYI offers `gpt-image-2.6-flare` and `gpt-image-2.6-sunburst` through the standard `/v1/images/generations` and `/v1/images/edits` endpoints
* **50% faster generation**: OpenAI reports a 50% speed improvement for Images 2.6, with Flare generating in as little as six seconds at `low` quality
* **Clear roles**: Flare targets rapid iteration and better layouts, while Sunburst emphasizes detail and edit consistency at medium and high quality
* **New upstream creative controls**: GIF generation, SVG export, image markup, and a `complexity` setting were announced with Images 2.6
* **Unchanged pricing**: Text input, image input, and image output remain \$5 / \$8 / \$30 per 1M tokens, with the same cached-input rates as 2.5

## Background

OpenAI released Images 2.6 on November 4, 2026, across ChatGPT, Codex, and the API. According to the announcement, these channels now generate about 4 billion images each week, or more than 500 million per day. This release focuses on shortening the path from draft to finished asset while preserving characters, products, and brand details across edits.

The API retains the two-model lineup. `gpt-image-2.6-flare` handles fast generation and everyday editing, while `gpt-image-2.6-sunburst` targets detailed compositions and demanding retouching. Both are now available on APIYI, so existing GPT-Image integrations can start with the same Images API request structure and change only the `model` field.

## Deep Dive

### Choosing between the two models

> [card] Flare: rapid iteration and layouts
>
> Designed for interactive generation, social assets, product imagery, and batch drafts. OpenAI reports 50% faster generation overall and as little as six seconds at low quality, alongside improved layouts for posters and product visuals.

> [card] Sunburst: detailed, consistent editing
>
> Designed for complex visuals, brand assets, and multi-turn retouching. At `medium` or `high` quality, Sunburst prioritizes detail and preserves people, products, and brand elements more consistently across edits.

A practical workflow is to explore compositions with Flare and move images that need refinement to Sunburst. Both models share the same token rates, but latency and output-token consumption still vary with the prompt, dimensions, quality setting, and current load.

| Item | `gpt-image-2.6-flare` | `gpt-image-2.6-sunburst` |
| - | - | - |
| Official role | Fast generation and editing | Detailed visual work and editing |
| Speed information | As little as six seconds at `low` quality | No fixed generation-time commitment |
| Main improvement | Layout quality and iteration speed | Detail and edit consistency at medium/high quality |
| Recommended use | Drafts, social content, interactive editing | Complex compositions, brand assets, multi-turn retouching |

> [!WARNING]
>
> The 50% speed improvement and six-second figure are OpenAI's claims. Six seconds is a best-case result at low quality, not a latency guarantee for every request. Actual timing depends on dimensions, quality, prompt complexity, and live capacity.

### Four new upstream capabilities

* **GIF generation**: Create looping GIFs from a prompt for brand mascots, reactions, memes, and animated storyboards.
* **Image markup**: Mark specific areas of an image so editing instructions can target the intended region more precisely.
* **SVG export**: Carry designs into websites, apps, and print workflows without a separate bitmap-to-vector conversion step.
* **`complexity` control (currently unsupported)**: This upstream setting controls scene-planning effort, but APIYI currently ignores it silently. Requests do not fail, but the field has no effect. Do not send or rely on it.

> [!NOTE]
>
> These capabilities were announced by OpenAI with Images 2.6. Validate GIF, SVG and image markup with a single request in your own integration first; `complexity` is currently unsupported and silently ignored. For both official-relay models, use only the standard Images API endpoints: `/v1/images/generations` and `/v1/images/edits`.

## Practical Use

### Code samples

This example uses only the existing Images API for basic generation and editing. Install the OpenAI Python SDK and set the `APIYI_API_KEY` environment variable:

```python theme={null}
import base64
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["APIYI_API_KEY"],
    base_url="https://api.apiyi.com/v1"
)

# Flare: quickly draft a product poster
flare = client.images.generate(
    model="gpt-image-2.6-flare",
    prompt="A minimalist specialty coffee poster with morning light and space reserved for a headline",
    size="1536x1024",
    quality="low"
)
with open("coffee-flare.png", "wb") as f:
    f.write(base64.b64decode(flare.data[0].b64_json))

# Sunburst: refine the scene while preserving product and brand details
with open("coffee-product.png", "rb") as image:
    sunburst = client.images.edit(
        model="gpt-image-2.6-sunburst",
        image=image,
        prompt="Keep the packaging, logo, and text unchanged; use a warm wooden coffee-shop table as the background",
        size="1024x1024",
        quality="high"
    )
with open("coffee-sunburst.png", "wb") as f:
    f.write(base64.b64decode(sunburst.data[0].b64_json))
```

### Best practices

1. **Draft before refining**: Explore compositions with Flare at low quality, then use Sunburst for final assets to reduce iteration time.
2. **State what must not change**: Include constraints such as "keep the packaging, logo, and text unchanged" to reduce detail drift during edits.
3. **Measure cost from responses**: Equal token rates do not guarantee equal per-image costs. Record input and output token usage in production.
4. **Validate new fields separately**: Test GIF, SVG and image markup independently before adoption. Do not send `complexity`; it is currently ignored silently and has no effect.

## Pricing and Availability

### Pricing

Both models have identical rates on APIYI, aligned with OpenAI's official pricing:

| Item | Price per 1M tokens |
| - | - |
| Text input | \$5.00 |
| Cached text input | \$1.25 |
| Image input | \$8.00 |
| Cached image input | \$2.00 |
| Image output | \$30.00 |

Prices are aligned with OpenAI and may change. The [live model pricing directory](https://docs.apiyi.com/en/models/index.md) is authoritative; this table was checked against `model-registry.json` on November 5, 2026.

### Available groups

Both models are available in `Default`, `image2Enterprise`, and `SVIP`. Use `Default` for initial integration checks, and follow your existing group strategy for enterprise or higher-stability workloads. Model IDs and endpoints remain the same across groups.

### Stack recharge promotions

These are default list prices. Recharge bonuses and group discounts can reduce the effective cost; the console reflects the actual charge. See [Recharge promotions](https://docs.apiyi.com/en/faq/recharge-promotions.md).

## Summary and Recommendations

GPT-Image-2.6 keeps the two-model strategy: Flare accelerates everyday generation and layout iteration, while Sunburst prioritizes detailed compositions and multi-turn edit consistency, all without changing the 2.5 price list. Existing GPT-Image users can begin with a model-name change in a staged rollout before adopting the new upstream creative controls.

* **Everyday generation, poster drafts, and batch assets**: choose `gpt-image-2.6-flare`
* **Brand assets, complex compositions, and multi-turn retouching**: choose `gpt-image-2.6-sunburst`
* **Production integrations**: verify existing generation and editing first, then adopt new capabilities individually and evaluate actual token usage and latency

> [!NOTE]
>
> **Sources and verification date**:
>
> * OpenAI announcement: `openai.com/index/introducing-images-2-6/`
> * OpenAI model pages: `developers.openai.com/api/docs/models/gpt-image-2.6-flare`, `developers.openai.com/api/docs/models/gpt-image-2.6-sunburst`
> * OpenAI system card: `deploymentsafety.openai.com/chatgpt-images-2-6`
> * APIYI model registry: `docs.apiyi.com/model-registry.json`
> * Sources and pricing verified on November 5, 2026


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.