# GPT Image 2.5 Sunburst (image)

> GPT Image 2.5 Sunburst makes detailed still images with exact rendered typography and extra fidelity on fine detail. It is the roasOS precision lane for statics that carry text. It runs fal's sunburst model: slower than GPT Image 2.5, same price.

Status: roasOS API v1.1. Catalog `model-catalog@2026-10-06.v5`, pricing `customer-pricing@2026-11-05.v15`. The endpoint `POST /v1/image/gpt-image-2.5-sunburst` is live. `POST /v1/generations` stays for one minor version as a deprecated alias (see "Today").

## Endpoint
POST https://api.roasos.com/v1/image/gpt-image-2.5-sunburst
Auth: Authorization: Bearer roasos_sk_… (scope api:write). Idempotency-Key required. quote_only / quote_id / webhook_url as in https://docs.roasos.com/llms.txt.

## Good at
GPT Image 2.5 Sunburst is OpenAI's precision image model on fal. fal describes it as "built for premium visual work, extra fidelity on intricate detail, in exchange for longer generation times". Use it when a headline, a wordmark or a UI mockup must be exact and a longer wait is acceptable. Use it with up to 8 references for a maskless edit; fal permits 16, roasOS caps at 8. It accepts `avatar_id`: the saved avatar's front and full-body shots lead the reference list and count as 2 of the 8. `avatar_outfit` requires `avatar_id`. fal describes the sunburst edit as "edits scoped precisely to the instruction, with subject and composition preserved across many rounds of revision". Set `background` to `transparent` for a PNG cutout with alpha. The request fields, the reference cap and the price table are the same as /v1/image/gpt-image-2.5. Do not use it for photoreal handheld product shots. Do not use it for subject continuity across many references. Likeness quality on GPT Image 2.5 Sunburst is not yet measured; Nano Banana Pro remains the measured identity lane. Use /v1/image/gpt-image-2.5 when speed matters more than detail. For a masked, positional edit use /v1/image-edit/gpt-image-2.5, which already runs the sunburst editor.

## Pricing
Unit: image. Pricing keys: `gpt-image-2.5-high`, `gpt-image-2.5-low`, `gpt-image-2.5-medium`.
The catalog publishes no credit example for this model: the pricing table has no key for it, and roasOS never states a guessed price.

## Modes
- `text-to-image`
- `image-edit`

The worker derives the mode from the media fields of the request.
Provider endpoints: `openai/gpt-image-2.5/sunburst/edit` · `openai/gpt-image-2.5/sunburst/text-to-image`.

## Request fields
| field | type | required | default | rule |
|---|---|---|---|---|
| `ad_look` | enum | no | — | `designed`, `native`, `ui` |
| `ad_set` | object | no | — | `{ id, index, total }` |
| `aspect_ratio` | enum | no | `1:1` | `9:16`, `1:1`, `2:3`, `3:4`, `4:5`, `4:3`, `3:2`, `16:9` |
| `avatar_id` | string | no | — | UUID |
| `avatar_outfit` | string | no | — | ≤ 500 characters |
| `background` | enum | no | `auto` | `auto`, `transparent`, `opaque` |
| `num_images` | integer | no | `1` | 1–4 |
| `product_id` | string | no | — | UUID |
| `product_images` | string[] | no | — | ≤ 8 items; only in `image-edit` |
| `prompt` | string | yes | — | ≥ 1 character; ≤ 10,000 characters |
| `prompt_mode` | enum | no | — | `wrapped`, `exact` |
| `quality_tier` | enum | no | `high` | `low`, `medium`, `high` |
| `quote_id` | string | no | — | UUID |
| `quote_only` | boolean | no | `false` | — |
| `references` | string[] | no | — | ≤ 8 items; only in `image-edit` |
| `source_image` | string | no | — | https URL; ≤ 4,096 characters |
| `wait_timeout_seconds` | integer | no | `0` | 0–60 |
| `webhook_url` | string | no | — | https URL; ≤ 4,096 characters |

The schema is strict: a field that is not in this table returns `400 unsupported_option`. Field names are the roasOS role names, one name per role across every family.

## Media
- `avatar_id` — identity; the saved character reference sheet, with a derived portrait only where the model requires a single face or source frame
- `product_id` — product; resolves to the product image list
- `product_images` — product reference images
- `references` — style and appearance references

| role | items | max size | content types | duration |
|---|---|---|---|---|
| `product_images` | ≤ 8 | 10 MB | `image/jpeg`, `image/png`, `image/webp` | — |
| `references` | ≤ 8 | 10 MB | `image/jpeg`, `image/png`, `image/webp` | — |

- Refused: `elements`, `reference_images`, `image_url`, `end_image_url`, `scene_id`, `scene_image`, `video_urls`, `video_url`, `audio_urls`, `audio_url`, `voice_id`. A refused role returns `400 unsupported_option`.
- Every URL must be an immutable object on `https://cdn.roasos.com/…` that your workspace owns; any other URL is `400 reference_media_not_workspace_owned`. Upload with `POST /v1/uploads` (direct POST of the bytes to `put_url`, or a `source_url` import), then use the returned CDN URL.

## Prompt
Limit: 10,000 characters including the wrapper (the wrapper is added only with product media). fal accepts 32,000. No tag syntax.
- Treat body-text lines as exact strings. Put each rendered string in quotation marks.
- Render critical text at 25 % or more of the canvas height.
- State exact element counts ("EXACTLY THREE message rows").
- Keep all text and focal subjects inside the central 84 % of the canvas.
- Name the layout, the type style and the color of each text block.
- Describe the fine detail you pay the extra time for: material, texture, edge, letterform.
- On a bad result, write a new prompt that names the fix; do not send the same payload again. Stop after two retries.

## Not exposed
- `quality`: values not exposed — `auto`, `xhigh`, `max`.
- `output_compression`: not accepted by this public endpoint.
- `image_size`: pinned to `seven fixed sizes in text-to-image, auto in an edit`.
- `output_format`: pinned to `png`.
- `sync_mode`: pinned to `false`.
- `mask_url`: pinned to `reachable only through the inpaint endpoint`.
- `references`: pinned to `8 images including the avatar's two shots; fal permits 16`.
- `prompt`: pinned to `characters 10,001–32,000`.
- `seed`: not accepted by this public endpoint.
- `negative_prompt`: not accepted by this public endpoint.

## Result
Result kind `image`. Always present: nothing. Present when the run produces it: `avatar_id`, `full_body_url`, `images`, `portrait_url`, `provider_seed`, `reference_sheet`, `url`.
```json
{ "data": { "id": "gen_…", "kind": "image", "model": "gpt-image-2.5-sunburst", "status": "completed", "result": {"avatar_id":"00000000-0000-4000-8000-000000000000","full_body_url":"https://cdn.roasos.com/workspaces/ws_01/full_body_url","images":["https://cdn.roasos.com/workspaces/ws_01/images-1.png"],"portrait_url":"https://cdn.roasos.com/workspaces/ws_01/portrait_url","provider_seed":0,"reference_sheet":"https://cdn.roasos.com/workspaces/ws_01/reference_sheet","url":"https://cdn.roasos.com/workspaces/ws_01/result"} } }
```
Files live on `https://cdn.roasos.com` and are immutable; a result URL can be a media input to the next call. Poll `GET /v1/jobs/{id}/status` → `{ id, status, updated_at }`, then `GET /v1/jobs/{id}/result` (`409 run_not_completed` until the job is `completed`, `failed` or `canceled`). Statuses: `queued → processing → completed | failed | canceled`.

## Example
```bash
# 1. quote — nothing is spent
curl -X POST https://api.roasos.com/v1/image/gpt-image-2.5-sunburst \
  -H "Authorization: Bearer roasos_sk_live_…" \
  -H "Idempotency-Key: 0f1c9e2a-gpt-image-2.5-sunburst-0001" \
  -H "Content-Type: application/json" \
  -d '{"quote_only":true,"prompt":"A woman holds the bottle at eye level in a bright kitchen, morning light, static camera."}'
# → 200 { "data": { "kind": "quote", "quote_id": "q_7Hk…", "credits": …, "expires_at": "…", "confirmation": { "model": "gpt-image-2.5-sunburst" } } }

# 2. run — the same body and the same Idempotency-Key, quote_id instead of quote_only
curl -X POST https://api.roasos.com/v1/image/gpt-image-2.5-sunburst \
  -H "Authorization: Bearer roasos_sk_live_…" \
  -H "Idempotency-Key: 0f1c9e2a-gpt-image-2.5-sunburst-0001" \
  -H "Content-Type: application/json" \
  -d '{"quote_id":"q_7Hk…","prompt":"A woman holds the bottle at eye level in a bright kitchen, morning light, static camera."}'
# → 201 { "data": { "id": "gen_…", "kind": "image", "model": "gpt-image-2.5-sunburst", "status": "queued", "credits_reserved": …, "links": { "status": "/v1/jobs/gen_…/status", "result": "/v1/jobs/gen_…/result" } } }

# 3. poll
curl https://api.roasos.com/v1/jobs/gen_…/status -H "Authorization: Bearer roasos_sk_live_…"
curl https://api.roasos.com/v1/jobs/gen_…/result -H "Authorization: Bearer roasos_sk_live_…"
```

## Today
`POST /v1/image/gpt-image-2.5-sunburst` is live. `quality_tier` (`low`, `medium`, `high`, default `high`) selects the price; fal's `auto`, `xhigh` and `max` are not exposed, because fal publishes no price for them. `aspect_ratio` is refused in an edit; the output follows the source image. `POST /v1/generations` with `model: "gpt-image-2.5-sunburst"` reaches the text-to-image mode for one minor version; there `resolution` carries the quality tier. Expect a longer generation time than GPT Image 2.5. Not reachable from the agent today.

## See also
https://docs.roasos.com/models/image/gpt-image-2.5-sunburst · https://api.roasos.com/v1/catalog/image/gpt-image-2.5-sunburst · openai/gpt-image-2.5/sunburst/edit · openai/gpt-image-2.5/sunburst/text-to-image