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

# GPT Image 2.5 Launch: Official Forwarding, Per-Call Billing, and Web Routes

> Integrate GPT Image 2.5 Flare and Sunburst through official-forward or $0.03/call routes, check snapshots and token billing, and use gpt-image-2-web in Default for the latest GPT web version 2.5.

GPT Image 2.5 Flare and Sunburst are available in LaoZhang API **official-forward groups**, using the existing GPT Image 2 official-forward integration and the same token rates. Default continues to use `gpt-image-2-web`, which now runs the latest GPT web version, 2.5.

Per-call billing is available with `gpt-image-2.5-flare-vip` and `gpt-image-2.5-sunburst-vip`, each at **\$0.03/call**, using the same integration as `gpt-image-2-vip`.

* **Published**: September 9, 2026
* **Last checked**: September 9, 2026
* **Status**: Active; available

## Choose a model and route

| Need                            | Model ID                     | Current version                                           | Group and billing                                          |
| ------------------------------- | ---------------------------- | --------------------------------------------------------- | ---------------------------------------------------------- |
| Prioritize generation speed     | `gpt-image-2.5-flare`        | `gpt-image-2.5-flare-2026-09-08`                          | Official-forward groups; token billing                     |
| Prioritize precise editing      | `gpt-image-2.5-sunburst`     | `gpt-image-2.5-sunburst-2026-09-08`                       | Official-forward groups; token billing                     |
| Per-call generation and editing | `gpt-image-2.5-flare-vip`    | Per-call model ID                                         | Default; \$0.03/call                                       |
| Per-call generation and editing | `gpt-image-2.5-sunburst-vip` | Per-call model ID                                         | Default; \$0.03/call                                       |
| Latest GPT web version 2.5      | `gpt-image-2-web`            | Web version 2.5; not a specific official-forward snapshot | Default; currently \$0.03/call, subject to console pricing |

Both Flare and Sunburst generate and edit images. Choose Flare for speed, Sunburst for edit precision, or offer both in your app. Official forwarding uses `Sora2Official` or `GPTImage2 Sora2 Enterprise`; per-call access uses Default and model IDs ending in `-vip`.

## What users should do

* **Existing GPT Image 2 official-forward integrations**: confirm that your [token](https://api2.laozhang.ai/token) permits the target model, keep the Images API endpoint and authentication, and change `model` to start calling. Use `POST /v1/images/generations` for generation and `POST /v1/images/edits` for editing.
* **Existing per-call integrations**: keep the per-call token, endpoint, and request structure used for `gpt-image-2-vip`, then change `model` to `gpt-image-2.5-flare-vip` or `gpt-image-2.5-sunburst-vip`.
* **Default web-route integrations**: keep `model="gpt-image-2-web"`; switching to Flare / Sunburst is unnecessary for this web update.
* **Other existing routes**: this notice does not require a universal migration. To adopt 2.5 official forwarding, verify the model, group, and usage-based billing settings.

Find generation, editing, image-saving examples, and dimension options in the [GPT Image 2.5 integration guide](/en/api-capabilities/gpt-image-2-5). After a request, view the model, usage, and charge in [call logs](https://api2.laozhang.ai/log).

## Frequently asked questions

### Do matching GPT Image 2 rates mean the same cost per image?

No. The official-forward token rates match, but models, quality, dimensions, and reference images can change consumption and the total price. See the [billing guidance](/en/api-capabilities/gpt-image-2-5) and [current console pricing](https://api2.laozhang.ai/account/pricing); contact support for enterprise quotes.

### Can Default directly call Flare or Sunburst?

Unsuffixed Flare / Sunburst require a usage-billed token in an official-forward group. Default can use `gpt-image-2.5-flare-vip` and `gpt-image-2.5-sunburst-vip` at \$0.03/call each. Its web entry remains `gpt-image-2-web`.

### Which size and quality values should per-call requests use?

Both per-call models support 1K, 2K, and 4K output with `low`, `medium`, or `high` quality; `xhigh` / `max` are not supported. Start with `size="2048x2048"` and `quality="medium"`. Omit a field when you do not need to specify it. See [size and quality parameters](/en/api-capabilities/gpt-image-2-5) for the full size table and examples.

### Can I pin a model version?

For official forwarding, set `model` to a full dated snapshot ID from the table. Per-call models use IDs ending in `-vip`, and web access uses `gpt-image-2-web`. Neither entry uses the dated official-forward snapshot IDs.

## References and related documentation

* Official OpenAI sources: [image generation guide](https://developers.openai.com/api/docs/guides/image-generation), [Flare model and snapshots](https://developers.openai.com/api/docs/models/gpt-image-2.5-flare), and [Sunburst model and snapshots](https://developers.openai.com/api/docs/models/gpt-image-2.5-sunburst).
* LaoZhang API: [models and pricing](https://api2.laozhang.ai/account/pricing), [token management](https://api2.laozhang.ai/token), and [call logs](https://api2.laozhang.ai/log).
* [GPT Image 2.5 integration guide](/en/api-capabilities/gpt-image-2-5), [Images API reference](/en/api-reference/images), [model and pricing catalog](/en/models), and [service and billing terms](https://www.laozhang.ai/terms).