--- title: "GPT Image 2.5" description: "GPT Image 2.5 makes detailed still images with exact rendered typography. It is the roasOS image model for statics that carry text: headlines, body copy, wordmarks and UI mockups. This endpoint runs fal's flare model: fast, and the default." url: https://docs.roasos.com/models/image/gpt-image-2.5 --- # GPT Image 2.5 Family `image` · model `gpt-image-2.5` · catalog `model-catalog@2026-10-06.v5` · pricing `customer-pricing@2026-11-05.v15` . ## Endpoint ```http POST https://api.roasos.com/v1/image/gpt-image-2.5 ``` Send your API key as a bearer token. The key needs the scope `api:write`. Every paid request also needs an `Idempotency-Key` header. The envelope fields `quote_only`, `quote_id`, `webhook_url` and `wait_timeout_seconds` behave the same on each model endpoint. Refer to [Jobs](/concepts/jobs) and [Quotes and credits](/concepts/quotes-and-credits). ## Good at GPT Image 2.5 is OpenAI's image model on fal. fal describes the flare model as "OpenAI's default image model for most applications. Fast, high-quality generation with natural lighting, rich textures, and support for complex layouts including transparent backgrounds". Use it for headline typography, dense body copy, wordmarks, and UI mockups such as chat threads and dialogs. 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`. Set `background` to `transparent` for a PNG cutout with alpha, or to `opaque` for a filled canvas; the price does not change. Do not use it for photoreal handheld product shots. Do not use it for subject continuity across many references; it blends multiple references less smoothly than Nano Banana Pro. Likeness quality on GPT Image 2.5 is not yet measured; Nano Banana Pro remains the measured identity lane. For fine detail with a longer wait use /v1/image/gpt-image-2.5-sunburst at the same price. For a masked, positional edit use /v1/image-edit/gpt-image-2.5. ## Pricing The unit is one **image**. Pricing keys: `gpt-image-2.5-high`, `gpt-image-2.5-low`, `gpt-image-2.5-medium`. The catalog has no credit example for this model. Send `quote_only: true` to get the price. ## Modes * `text-to-image` * `image-edit` roasOS selects the mode from the media fields of your request. You do not send a mode. Provider endpoints: `openai/gpt-image-2.5/flare/edit` · `openai/gpt-image-2.5/flare/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 gets `400 unsupported_option`. The field names are the roasOS role names. One role has one name in every family. ## Media This endpoint accepts these media roles: * `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 | Maximum 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` | — | Every other role is 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 gets `400 unsupported_option`. Each media URL must be an immutable object on `https://cdn.roasos.com` that your workspace owns. Any other URL gets `400 reference_media_not_workspace_owned` . Refer to [Reference media and uploads](/concepts/reference-media) to learn how to put a file there. ## 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. * For a cutout, say "isolated on a transparent background" and set `background: "transparent"`. * 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 These catalog entries describe omitted inputs, pinned values and source constraints. They do not imply that the provider accepts every listed field. * `quality` — these values are not available: `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 The result kind is `image`. Always present: nothing. Present when the run makes 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", "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" } } } ``` The files are immutable objects on `https://cdn.roasos.com`. A result URL is a valid media input for your next request. ## Example The three steps are always the same: quote, run, poll. cURL JavaScript Python ```bash # 1. Quote. Nothing is spent. curl -X POST https://api.roasos.com/v1/image/gpt-image-2.5 \ -H "Authorization: Bearer roasos_sk_live_..." \ -H "Idempotency-Key: 0f1c9e2a-gpt-image-2.5-0001" \ -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" } } } # 2. Run. Same body, same Idempotency-Key, quote_id in place of quote_only. curl -X POST https://api.roasos.com/v1/image/gpt-image-2.5 \ -H "Authorization: Bearer roasos_sk_live_..." \ -H "Idempotency-Key: 0f1c9e2a-gpt-image-2.5-0001" \ -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_...", "status": "queued", "credits_reserved": ... } } # 3. Poll, then read the result. 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_..." ``` ```javascript const key = process.env.ROASOS_API_KEY; const url = "https://api.roasos.com/v1/image/gpt-image-2.5"; const idempotencyKey = "0f1c9e2a-gpt-image-2.5-0001"; const input = { "prompt": "A woman holds the bottle at eye level in a bright kitchen, morning light, static camera." }; const post = (payload) => fetch(url, { method: "POST", headers: { Authorization: `Bearer ${key}`, "Idempotency-Key": idempotencyKey, "Content-Type": "application/json", }, body: JSON.stringify(payload), }).then((response) => response.json()); // 1. Quote. Nothing is spent. const quote = await post({ quote_only: true, ...input }); console.log(quote.data.credits); // 2. Run. const job = await post({ quote_id: quote.data.quote_id, ...input }); // 3. Poll, then read the result. let status = "queued"; while (status !== "completed" && status !== "failed" && status !== "canceled") { await new Promise((done) => setTimeout(done, 3000)); const poll = await fetch(`${url.split("/v1")[0]}/v1/jobs/${job.data.id}/status`, { headers: { Authorization: `Bearer ${key}` }, }).then((response) => response.json()); status = poll.data.status; } const result = await fetch(`${url.split("/v1")[0]}/v1/jobs/${job.data.id}/result`, { headers: { Authorization: `Bearer ${key}` }, }).then((response) => response.json()); console.log(result.data.result); ``` ```python import os, time, requests key = os.environ["ROASOS_API_KEY"] url = "https://api.roasos.com/v1/image/gpt-image-2.5" headers = { "Authorization": f"Bearer {key}", "Idempotency-Key": "0f1c9e2a-gpt-image-2.5-0001", } payload = { "prompt": "A woman holds the bottle at eye level in a bright kitchen, morning light, static camera." } # 1. Quote. Nothing is spent. quote = requests.post(url, headers=headers, json={"quote_only": True, **payload}).json() print(quote["data"]["credits"]) # 2. Run. job = requests.post(url, headers=headers, json={"quote_id": quote["data"]["quote_id"], **payload}).json() job_id = job["data"]["id"] # 3. Poll, then read the result. jobs = "https://api.roasos.com/v1/jobs" status = "queued" while status not in ("completed", "failed", "canceled"): time.sleep(3) status = requests.get(f"{jobs}/{job_id}/status", headers=headers).json()["data"]["status"] result = requests.get(f"{jobs}/{job_id}/result", headers=headers).json() print(result["data"]["result"]) ``` ## The deprecated path `POST /v1/generations` still reaches this model for one minor version. It is deprecated. This is how it maps: `POST /v1/image/gpt-image-2.5` 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"` still reaches the text-to-image mode for one minor version; there `resolution` carries the quality tier. The retired `/v1/image/gpt-image-2` answers 404. The roasOS agent uses this model for the transparent-cutout role. ## See also * [`llms.txt` for this model](https://docs.roasos.com/models/image/gpt-image-2.5/llms.txt) — the same facts as one plain-text file for an agent. * `GET https://api.roasos.com/v1/catalog/gpt-image-2.5` — the machine-readable form: enums, defaults, limits and prices. Refer to the [API reference](/api-reference/overview). * [Jobs](/concepts/jobs) — how to poll a job and read its result. * Provider endpoints: `openai/gpt-image-2.5/flare/edit` · `openai/gpt-image-2.5/flare/text-to-image`.