GPT Image 2.5 Edit

Unganisha

Kitambulisho cha modeli openai/gpt-image-2.5/flare/edit

# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.ru/v1/run/openai/gpt-image-2.5/flare/edit?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Same sneaker, but on a snowy mountain trail in daylight",
    "images": [
      "https://content.doitong.com/images/showcase/v3/gen_sneaker_ad.jpg"
    ],
    "quality": "medium"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

const API = "https://api.doitong.ru/v1";
const headers = {
  "Authorization": "Bearer " + process.env.DOITONG_API_KEY,
  "Content-Type": "application/json",
};

// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/openai/gpt-image-2.5/flare/edit?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "prompt": "Same sneaker, but on a snowy mountain trail in daylight",
    "images": [
      "https://content.doitong.com/images/showcase/v3/gen_sneaker_ad.jpg"
    ],
    "quality": "medium"
  }),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);

// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
  res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
  request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");

import os
import requests

API = "https://api.doitong.ru/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "prompt": "Same sneaker, but on a snowy mountain trail in daylight",
    "images": [
        "https://content.doitong.com/images/showcase/v3/gen_sneaker_ad.jpg",
    ],
    "quality": "medium",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/openai/gpt-image-2.5/flare/edit", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
    raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])

# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
    request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
    raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])

# 1. Connect once (Claude Code; Cursor, VS Code, Claude Desktop: https://doitong.com/sw/developers/docs/mcp)
claude mcp add --transport http doitong-models https://api.doitong.ru/v1/mcp \
  --header "Authorization: Bearer $DOITONG_API_KEY"

# 2. Your agent calls the "run" tool with:
{
  "model_id": "openai/gpt-image-2.5/flare/edit",
  "input": {
    "prompt": "Same sneaker, but on a snowy mountain trail in daylight",
    "images": [
      "https://content.doitong.com/images/showcase/v3/gen_sneaker_ad.jpg"
    ],
    "quality": "medium"
  }
}

Piga modeli ya GPT Image 2.5 Edit (openai/gpt-image-2.5/flare/edit) kupitia Doitong API. Nyaraka za mawakala: https://doitong.com/sw/developers/models/openai/gpt-image-2.5/flare/edit.md

POST https://api.doitong.ru/v1/run/openai/gpt-image-2.5/flare/edit?wait=20
Authorization: Bearer $DOITONG_API_KEY
Content-Type: application/json

{
  "prompt": "Same sneaker, but on a snowy mountain trail in daylight",
  "images": [
    "https://content.doitong.com/images/showcase/v3/gen_sneaker_ad.jpg"
  ],
  "quality": "medium"
}

Ikiwa hali ya jibu ni "queued" au "running", piga GET https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20 mara kwa mara hadi iwe "succeeded"; faili ziko kwenye outputs[].url. POST https://api.doitong.ru/v1/quote/openai/gpt-image-2.5/flare/edit yenye mwili uleule hurejesha bei kamili kabla ya kuendesha.

Ombi hili: ≈$ 0.12 salio za API 120 · ≈ ₽ 12.91 Iendeshe kwenye ukurasa huu

Pata ufunguo wa API

OpenAI Uhariri wa Picha #editing#mask#transparent

Hariri au unganisha hadi picha 16 za marejeleo kwa modeli ya picha ya OpenAI, ikiwa na maski na uwazi wa hiari.

OpenAPI Markdown

Imetengenezwa kwenye Doitong

Kazi za umma zilizotengenezwa kwa GPT Image 2.5 na jumuiya ya Doitong. Tumia tena kidokezo kwa kubofya mara moja.

Kazi za umma zilizoonyeshwa: 16

Art style: Кинематографичный, реалистичный стиль. Она отнимает полотенце от лица. В зеркале — ее ... — Art style: Кинематографичный, реалистичный стиль. Она отнимает полотенце от лица. В зеркале — ее обычное, симпатичное лицо. Она смотрит с недоверием, затем на ее лице появляется огромное облегчение и легкая, искренняя улыбка. Свет снова становится теплым. ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━...

Grungy analog photo of Daphne Blake (from Serial scooby doo) watching her own movie on a 90s CRT ... — Grungy analog photo of Daphne Blake (from Serial scooby doo) watching her own movie on a 90s CRT TV in a dimly lit bedroom. The TV clearly shows animated scene from scooby doo, with a cartoon-style Daphne in her classic clothes on screen, smiling. Daphne Blake is sitting cross-legged on the floor...

Strong rule: style --- Cinematic Realistic ---. Энергичная девушка 27 лет с широкой лучезарной ул... — Strong rule: style --- Cinematic Realistic ---. Энергичная девушка 27 лет с широкой лучезарной улыбкой и задорными искорками в темных глазах. Короткая стильная стрижка пикси, волосы выкрашены в модный пепельный блонд. Одета в яркую джинсовую куртку с цветными нашивками и белую футболку. Образ...

Strong rule: style --- Cinematic Realistic ---. Молодая женщина около 30 лет, утонченные черты ли... — Strong rule: style --- Cinematic Realistic ---. Молодая женщина около 30 лет, утонченные черты лица, высокие скулы, пронзительные зеленые глаза. Волосы уложены в безупречное каре каштанового цвета. Одета в дорогой шелковый бежевый блейзер и изящные золотые украшения. Образ излучает уверенность,...

Use facial feature of attached photo. A realistic portrait of a woman with black hair loosely tie... — Use facial feature of attached photo. A realistic portrait of a woman with black hair loosely tied back, sitting outside a whitewashed stone house with a conical roof in a quiet Italian village. She wears a soft yellow floral summer dress with puff sleeves and white strappy heels. A wicker basket...

Фотореалистичная рекламная композиция в вертикальном формате 9:16. На переднем плане большая ярка... — Фотореалистичная рекламная композиция в вертикальном формате 9:16. На переднем плане большая яркая глянцевая фольгированная розово-синяя упаковка чипсов в современном стильном дизайне, с глянцевой поверхностью, бликами и складками, как у реального продукта. В левом углу упаковки средний логотип...

Art style: Кинематографичный, реалистичный стиль. Резкая смена кадра. Девушка с ужасом смотрит на... — Art style: Кинематографичный, реалистичный стиль. Резкая смена кадра. Девушка с ужасом смотрит на себя в зеркало. Маска снята, но ее лицо гротескно искажено: глаза слишком большие, улыбка растянута неестественно. Освещение стало холодным и резким. ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ FINAL...

Bei iliyokadiriwa kwa utekelezaji

Bei iliyokadiriwa

$ 0.12kwa utekelezaji

salio za API 120 · ≈ ₽ 12.91

Bei: ≈ kuanzia $ 0.12

Bei maalum kwa utekelezaji, hutozwa tu ikifanikiwa.

Endesha · $ 0.12

Hutozwa tu ikifanikiwa, na kurejeshewa kiotomatiki ikishindwa.

quality

num_outputs chaguomsingi 1

Sheria za bei

Wakati quality = xhigh: bei ya msingi × 1.8
Wakati quality = max: bei ya msingi × 3

Imekadiriwa kutokana na gharama ya kawaida ya utekelezaji mmoja. Nukuu ni sawa kabisa na kiasi kinachotozwa kwa utekelezaji.

Endpoint ya makadirio: POST /quote/{id}

Unda ombi

Vidhibiti vinazalishwa kutoka kwenye schema ya modeli. Msimbo na bei husasishwa unapovibadilisha.

prompt •inahitajika 55 / 32000

Kidokezo kilichotumika kuzalisha picha.

images •inahitajika image_urls

Dondosha faili, au · hadi 16

URL za picha za marejeleo kwa uzalishaji, zikiwa na kikomo cha picha 16.

image_size chaguomsingi auto

Vipimo vya tokeo, vinavyokadiriwa kutoka picha zilizotolewa vinapowekwa kuwa 'auto'.

quality

Uteuzi wa ubora wa picha, ambapo 'auto' hukabidhi uamuzi kwa modeli. Maelezo ya ziada katika mipangilio ya juu huleta ucheleweshaji mrefu na matumizi makubwa ya tokeni.

num_outputs num_images chaguomsingi 1

Idadi ya picha za kuzalisha.

Ya kina mask · background · output_format · output_compression

mask mask_url

Dondosha faili, au

URL ya picha ya maski inayotambua eneo la kuhariri wakati wa uzalishaji.

background chaguomsingi auto

Mandharinyuma ya picha inayotokana.

output_format chaguomsingi png

Umbizo la faili la picha za tokeo.

output_compression

Mpangilio wa ukandamizaji unaopatikana tu kwa 'jpeg' au 'webp' katika output_format; masafa yake yanayoruhusiwa ni 0–100.

POST /run/openai/gpt-image-2.5/flare/edit?wait=20 makadirio → $ 0.12

# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.ru/v1/run/openai/gpt-image-2.5/flare/edit?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Same sneaker, but on a snowy mountain trail in daylight",
    "images": [
      "https://content.doitong.com/images/showcase/v3/gen_sneaker_ad.jpg"
    ],
    "quality": "medium"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

const API = "https://api.doitong.ru/v1";
const headers = {
  "Authorization": "Bearer " + process.env.DOITONG_API_KEY,
  "Content-Type": "application/json",
};

// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/openai/gpt-image-2.5/flare/edit?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "prompt": "Same sneaker, but on a snowy mountain trail in daylight",
    "images": [
      "https://content.doitong.com/images/showcase/v3/gen_sneaker_ad.jpg"
    ],
    "quality": "medium"
  }),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);

// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
  res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
  request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");

import os
import requests

API = "https://api.doitong.ru/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "prompt": "Same sneaker, but on a snowy mountain trail in daylight",
    "images": [
        "https://content.doitong.com/images/showcase/v3/gen_sneaker_ad.jpg",
    ],
    "quality": "medium",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/openai/gpt-image-2.5/flare/edit", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
    raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])

# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
    request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
    raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "run",
    "arguments": {
      "model_id": "openai/gpt-image-2.5/flare/edit",
      "input": {
        "prompt": "Same sneaker, but on a snowy mountain trail in daylight",
        "images": [
          "https://content.doitong.com/images/showcase/v3/gen_sneaker_ad.jpg"
        ],
        "quality": "medium"
      },
      "wait_seconds": 20
    }
  }
}

Endesha ombi hili

Ufunguo wa API

Key yako inabaki kwenye kivinjari hiki: inatumwa kwa Doitong API pekee na kuhifadhiwa (localStorage) tu ukiweka tiki kwenye Kumbuka. Kumbuka katika kivinjari hiki Pata ufunguo wa API

Kuhusu GPT Image 2.5 Edit

Hali ya kuhariri ya GPT Image 2.5: eleza mabadiliko na tuma hadi picha 16 za marejeo, kwa hiari ukiambatanisha mask inayoweka kikomo eneo ambalo modeli inaweza kupaka rangi. Inaauni mandharinyuma yenye uwazi, viwango vitano vya ubora na hadi matokeo kumi kwa kila ombi.

Vigezo

Tuma jina rasmi au jina asilia, si yote mawili. Majina rasmi

JinaAina ChaguomsingiInaruhusiwa Maelezo

promptinahitajika

Ainastring

≤ herufi 32,000

Kidokezo kilichotumika kuzalisha picha.

image_urlsinahitajika images

Ainaurl[] · image

≤ vipengee 16

URL za picha za marejeleo kwa uzalishaji, zikiwa na kikomo cha picha 16.

mask_urlsi lazima mask

Ainaurl · image

URL ya picha ya maski inayotambua eneo la kuhariri wakati wa uzalishaji.

image_sizesi lazima

Ainaobject

Chaguomsingiauto

square_hdsquareportrait_4_3portrait_16_9landscape_4_3landscape_16_9auto

Vipimo vya tokeo, vinavyokadiriwa kutoka picha zilizotolewa vinapowekwa kuwa 'auto'.

backgroundsi lazima

Ainaenum

Chaguomsingiauto

autotransparentopaque

Mandharinyuma ya picha inayotokana.

qualitysi lazima

Ainaenum

Chaguomsingihigh

autolowmediumhighxhighmax

Uteuzi wa ubora wa picha, ambapo 'auto' hukabidhi uamuzi kwa modeli. Maelezo ya ziada katika mipangilio ya juu huleta ucheleweshaji mrefu na matumizi makubwa ya tokeni.

num_imagessi lazima num_outputs

Ainainteger

Chaguomsingi1

1 – 10

Idadi ya picha za kuzalisha.

output_formatsi lazima

Ainaenum

Chaguomsingipng

jpegpngwebp

Umbizo la faili la picha za tokeo.

output_compressionsi lazima

Ainainteger | null

0 – 100

Mpangilio wa ukandamizaji unaopatikana tu kwa 'jpeg' au 'webp' katika output_format; masafa yake yanayoruhusiwa ni 0–100.

inahitajika Jina rasmi, pia linakubalika

Vigezo vya faili vinakubali URL ya umma ya https://, data: URI ya hadi 10 MB, au file_url ya upakiaji. Faili

Tokeo

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t

{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "openai/gpt-image-2.5/flare/edit",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 120,
    "usd": "0.12",
    "charged": 120,
    "refunded": 0
  },
  "input": {
    "prompt": "Same sneaker, but on a snowy mountain trail in daylight",
    "images": [
      "https://content.doitong.com/images/showcase/v3/gen_sneaker_ad.jpg"
    ],
    "quality": "medium"
  },
  "output": {
    "images": [
      {
        "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
        "content_type": "image/jpeg",
        "file_name": "0-output.jpeg",
        "file_size": 1843200,
        "width": 1024,
        "height": 768
      }
    ]
  },
  "outputs": [
    {
      "type": "image",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "width": 1024,
      "height": 768,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}

Faili zako, chaguo lakoKila outputs[].url ni nakala kwenye hifadhi yetu: huhifadhiwa milele (hutozwa kwa GB kwa mwezi) au 7 siku bila malipo, kulingana na mpangilio wa akaunti yako au ?storage=.

Muundo uleule kwenye kila modelitype, url, content_type, width, height na duration, kwa picha, video na sauti. output ni kitu cha matokeo cha modeli yenyewe.

Sehemu za tokeo