GPT Image 2 is OpenAI’s model for image generation and editing from text and visual inputs. It creates a new image from a written brief and can use source images for edits or reference-led work. Practical tasks include illustrations, product concepts, visual compositions and changes to an existing asset. It is a separate edition from the GPT Image 2.5 Sunburst and Flare models, with its own quality range and input-fidelity behaviour.
For generation, describe the subject, scene, composition, light and intended style. For an edit, name what should change and what should keep its appearance. A product brief can request a ceramic lamp on a pale surface with a centred silhouette and room for a caption; a follow-up edit can change the background while retaining the lamp’s shape and viewing angle. The documented direct generation and edit workflows accept prompts up to 32,000 characters and can return one to ten images.
Reference editing accepts up to sixteen input images. Specify the purpose of each reference so a subject, background and visual treatment are not confused. GPT Image 2 processes every image input at high fidelity automatically; input_fidelity should be omitted because it is not adjustable for this edition. This differs from the high-or-low choice on GPT Image 1 and the low-only input-fidelity mode of GPT Image 1 Mini. High-fidelity input processing supports source detail without guaranteeing that every detail is reproduced unchanged.
A mask can identify the region to edit. The source image and mask must have the same format and dimensions and be below 50 MB in the guide’s preparation requirements; the mask also needs an alpha channel. If several input images are provided, masking applies to the first. The model treats the mask as prompt-based guidance rather than a strict geometric boundary. Describe the local change and preservation requirements, then examine the surrounding area for unintended differences.
GPT Image 2 supports low, medium, high and auto quality, with auto as the default. The 2.5 family’s xhigh and max settings are not part of this edition’s quality range. Size can be square, landscape, portrait, automatic or a valid custom width and height. The producer examples include 1024 × 1024, 1536 × 1024, 1024 × 1536, 2048 × 2048, 2048 × 1152, 3840 × 2160 and 2160 × 3840 pixels. Choose the orientation and detail level for the actual layout rather than treating quality and dimensions as the same control.
Custom dimensions must be multiples of sixteen pixels, with a maximum edge of 3840 pixels, a long-to-short-edge ratio no greater than 3:1 and an area from 655,360 to 8,294,400 pixels. These conditions hold simultaneously. Resolutions above 2560 × 1440 are marked experimental. A frame that satisfies one rule can still fail another, so select a supported pair of dimensions and describe the crop-sensitive elements in the brief.
Output is PNG by default, with JPEG or WebP also available. Compression from 0 to 100 is supported for JPEG and WebP. The background can be opaque or automatic; the exact current reference describes transparency for GPT Image 2 as a preview capability. When requesting transparency, use PNG or WebP so an alpha channel can be retained. The documented streaming workflow permits up to three partial images before the finished image; save the final asset rather than a progress preview. The manufacturer interface also supports batch processing.
Evaluate text clarity, the position of objects and preservation of source details in the actual result. GPT Image can struggle with precise lettering, layout-sensitive compositions and recurring visual identity across separate generations. For a sequence of edits, use the chosen result as the next source and give a concrete change tied to a visible issue. GPT Image 2’s useful output is an image connected to a clear generation or edit brief, with its high-fidelity inputs, dimensions and quality chosen for that specific task.
", "aboutText": "GPT Image 2 is OpenAI’s model for image generation and editing from text and visual inputs. It creates a new image from a written brief and can use source images for edits or reference-led work. Practical tasks include illustrations, product concepts, visual compositions and changes to an existing asset. It is a separate edition from the GPT Image 2.5 Sunburst and Flare models, with its own quality range and input-fidelity behaviour.\n\nFor generation, describe the subject, scene, composition, light and intended style. For an edit, name what should change and what should keep its appearance. A product brief can request a ceramic lamp on a pale surface with a centred silhouette and room for a caption; a follow-up edit can change the background while retaining the lamp’s shape and viewing angle. The documented direct generation and edit workflows accept prompts up to 32,000 characters and can return one to ten images.\n\nReference editing accepts up to sixteen input images. Specify the purpose of each reference so a subject, background and visual treatment are not confused. GPT Image 2 processes every image input at high fidelity automatically; input_fidelity should be omitted because it is not adjustable for this edition. This differs from the high-or-low choice on GPT Image 1 and the low-only input-fidelity mode of GPT Image 1 Mini. High-fidelity input processing supports source detail without guaranteeing that every detail is reproduced unchanged.\n\nA mask can identify the region to edit. The source image and mask must have the same format and dimensions and be below 50 MB in the guide’s preparation requirements; the mask also needs an alpha channel. If several input images are provided, masking applies to the first. The model treats the mask as prompt-based guidance rather than a strict geometric boundary. Describe the local change and preservation requirements, then examine the surrounding area for unintended differences.\n\nGPT Image 2 supports low, medium, high and auto quality, with auto as the default. The 2.5 family’s xhigh and max settings are not part of this edition’s quality range. Size can be square, landscape, portrait, automatic or a valid custom width and height. The producer examples include 1024 × 1024, 1536 × 1024, 1024 × 1536, 2048 × 2048, 2048 × 1152, 3840 × 2160 and 2160 × 3840 pixels. Choose the orientation and detail level for the actual layout rather than treating quality and dimensions as the same control.\n\nCustom dimensions must be multiples of sixteen pixels, with a maximum edge of 3840 pixels, a long-to-short-edge ratio no greater than 3:1 and an area from 655,360 to 8,294,400 pixels. These conditions hold simultaneously. Resolutions above 2560 × 1440 are marked experimental. A frame that satisfies one rule can still fail another, so select a supported pair of dimensions and describe the crop-sensitive elements in the brief.\n\nOutput is PNG by default, with JPEG or WebP also available. Compression from 0 to 100 is supported for JPEG and WebP. The background can be opaque or automatic; the exact current reference describes transparency for GPT Image 2 as a preview capability. When requesting transparency, use PNG or WebP so an alpha channel can be retained. The documented streaming workflow permits up to three partial images before the finished image; save the final asset rather than a progress preview. The manufacturer interface also supports batch processing.\n\nEvaluate text clarity, the position of objects and preservation of source details in the actual result. GPT Image can struggle with precise lettering, layout-sensitive compositions and recurring visual identity across separate generations. For a sequence of edits, use the chosen result as the next source and give a concrete change tied to a visible issue. GPT Image 2’s useful output is an image connected to a clear generation or edit brief, with its high-fidelity inputs, dimensions and quality chosen for that specific task.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "6c4ff8266363821b1a8720f008506594d8e1ba59a913bf24adc71e958111e7be", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "gpt-image-2GPT Image 2 generates and edits images from text and visual references. It supports flexible frame dimensions and automatically processes image inputs at high fidelity, with separate quality, format and background controls for the finished asset.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
GPT Image 2 is OpenAI’s model for image generation and editing from text and visual inputs. It creates a new image from a written brief and can use source images for edits or reference-led work. Practical tasks include illustrations, product concepts, visual compositions and changes to an existing asset. It is a separate edition from the GPT Image 2.5 Sunburst and Flare models, with its own quality range and input-fidelity behaviour.
For generation, describe the subject, scene, composition, light and intended style. For an edit, name what should change and what should keep its appearance. A product brief can request a ceramic lamp on a pale surface with a centred silhouette and room for a caption; a follow-up edit can change the background while retaining the lamp’s shape and viewing angle. The documented direct generation and edit workflows accept prompts up to 32,000 characters and can return one to ten images.
Reference editing accepts up to sixteen input images. Specify the purpose of each reference so a subject, background and visual treatment are not confused. GPT Image 2 processes every image input at high fidelity automatically; input_fidelity should be omitted because it is not adjustable for this edition. This differs from the high-or-low choice on GPT Image 1 and the low-only input-fidelity mode of GPT Image 1 Mini. High-fidelity input processing supports source detail without guaranteeing that every detail is reproduced unchanged.
A mask can identify the region to edit. The source image and mask must have the same format and dimensions and be below 50 MB in the guide’s preparation requirements; the mask also needs an alpha channel. If several input images are provided, masking applies to the first. The model treats the mask as prompt-based guidance rather than a strict geometric boundary. Describe the local change and preservation requirements, then examine the surrounding area for unintended differences.
GPT Image 2 supports low, medium, high and auto quality, with auto as the default. The 2.5 family’s xhigh and max settings are not part of this edition’s quality range. Size can be square, landscape, portrait, automatic or a valid custom width and height. The producer examples include 1024 × 1024, 1536 × 1024, 1024 × 1536, 2048 × 2048, 2048 × 1152, 3840 × 2160 and 2160 × 3840 pixels. Choose the orientation and detail level for the actual layout rather than treating quality and dimensions as the same control.
Custom dimensions must be multiples of sixteen pixels, with a maximum edge of 3840 pixels, a long-to-short-edge ratio no greater than 3:1 and an area from 655,360 to 8,294,400 pixels. These conditions hold simultaneously. Resolutions above 2560 × 1440 are marked experimental. A frame that satisfies one rule can still fail another, so select a supported pair of dimensions and describe the crop-sensitive elements in the brief.
Output is PNG by default, with JPEG or WebP also available. Compression from 0 to 100 is supported for JPEG and WebP. The background can be opaque or automatic; the exact current reference describes transparency for GPT Image 2 as a preview capability. When requesting transparency, use PNG or WebP so an alpha channel can be retained. The documented streaming workflow permits up to three partial images before the finished image; save the final asset rather than a progress preview. The manufacturer interface also supports batch processing.
Evaluate text clarity, the position of objects and preservation of source details in the actual result. GPT Image can struggle with precise lettering, layout-sensitive compositions and recurring visual identity across separate generations. For a sequence of edits, use the chosen result as the next source and give a concrete change tied to a visible issue. GPT Image 2’s useful output is an image connected to a clear generation or edit brief, with its high-fidelity inputs, dimensions and quality chosen for that specific task.
POST /v1/images/generationstextimage| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits gpt-image-2 | Default— |
Fieldprompt | Typestring | RequirementRequired | Values & limits Minimum length: 1 | Default— |
Fieldn | Typeinteger | RequirementOptional | Values & limits Minimum: 1 | Default1 |
Fieldresponse_format | Typestring | RequirementOptional | Values & limits url, b64_json | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Fieldsize | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldquality | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldbackground | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldoutput_format | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldoutput_compression | Typeinteger | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmoderation | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldinput_fidelity | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldstyle | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldpartial_images | Typeinteger | RequirementOptional | Values & limits Model-specific | Default— |
Text to image · Required: prompt
| Parameter | Contract |
|---|---|
Parametermaterial_types | Contracttext |
Parameterrequired | Contractmodel, prompt |
Parameteroptional_controls | Contractnull |
Parametercontent_type | Contractapplication/json |
Lifecycle: synchronous_result_then_owned_library
GET /v1/media/tasks/{task_id} · actual returned task_id or media library record
GET /v1/media/assets/{asset_id}/content
GET /v1/media/assets
GET /v1/media/assets/{asset_id}
Method shapes and IDs are exact; supplier capability is separate from admission.
POST /v1/images/generationsAiloot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\nexport AILOOT_API_KEY\nexport AILOOT_API_KEY\n: "${AILOOT_PROMPT_FILE:?Set your actual UTF-8 image brief}"\nexport AILOOT_PROMPT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "gpt-image-2", "prompt": ""}')\nf=Path(os.environ["AILOOT_PROMPT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 brief")\np['prompt']=f.read_text(encoding="utf-8")\nif not p['prompt'].strip():raise SystemExit("Brief must contain text")\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/images/generations \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json, os, subprocess\nfrom pathlib import Path\nfrom urllib.parse import urlsplit, urljoin\n\ndef save_images(items):\n if not items: raise SystemExit("No completed images; retain the full response")\n for index, item in enumerate(items):\n encoded=item.get("b64_json")\n uri=item.get("url", "")\n if not encoded and uri.startswith("data:image/"):\n header, separator, encoded=uri.partition(",")\n if not separator or ";base64" not in header: raise SystemExit("Unsupported image data URI")\n if encoded:\n raw=base64.b64decode(encoded,validate=True)\n elif uri:\n uri=urljoin("https://api.ailoot.ai",uri)\n parsed=urlsplit(uri)\n if parsed.scheme!="https" or not parsed.netloc or parsed.username or parsed.password:\n raise SystemExit("Invalid returned image URL")\n owned=parsed.netloc=="api.ailoot.ai" and parsed.path.startswith("/v1/media/assets/") and parsed.path.endswith("/content")\n args=["curl","--fail-with-body","--silent","--show-error",uri]\n if owned: args += ["-H","Authorization: Bearer "+os.environ["AILOOT_API_KEY"]]\n temporary=Path(f"image-{index}.bin")\n subprocess.run(args+["-o",str(temporary)],check=True)\n raw=temporary.read_bytes()\n temporary.unlink()\n else: raise SystemExit("Image has neither bytes nor URL")\n if not raw: raise SystemExit("Empty image result")\n ext="png" if raw.startswith(b"\\x89PNG") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else "svg" if raw.lstrip().startswith((b"<svg",b"<?xml")) else "bin"\n Path(f"image-{index}.{ext}").write_bytes(raw)\n print("Every returned image saved; complete response metadata retained")\nsave_images(json.loads(Path("result.json").read_text())["data"])\nPY_RESULT\nfrom openai import OpenAI\nimport base64, json, os, subprocess\nfrom pathlib import Path\nfrom urllib.parse import urlsplit, urljoin\n\ndef save_images(items):\n if not items: raise SystemExit("No completed images; retain the full response")\n for index, item in enumerate(items):\n encoded=item.get("b64_json")\n uri=item.get("url", "")\n if not encoded and uri.startswith("data:image/"):\n header, separator, encoded=uri.partition(",")\n if not separator or ";base64" not in header: raise SystemExit("Unsupported image data URI")\n if encoded:\n raw=base64.b64decode(encoded,validate=True)\n elif uri:\n uri=urljoin("https://api.ailoot.ai",uri)\n parsed=urlsplit(uri)\n if parsed.scheme!="https" or not parsed.netloc or parsed.username or parsed.password:\n raise SystemExit("Invalid returned image URL")\n owned=parsed.netloc=="api.ailoot.ai" and parsed.path.startswith("/v1/media/assets/") and parsed.path.endswith("/content")\n args=["curl","--fail-with-body","--silent","--show-error",uri]\n if owned: args += ["-H","Authorization: Bearer "+os.environ["AILOOT_API_KEY"]]\n temporary=Path(f"image-{index}.bin")\n subprocess.run(args+["-o",str(temporary)],check=True)\n raw=temporary.read_bytes()\n temporary.unlink()\n else: raise SystemExit("Image has neither bytes nor URL")\n if not raw: raise SystemExit("Empty image result")\n ext="png" if raw.startswith(b"\\x89PNG") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else "svg" if raw.lstrip().startswith((b"<svg",b"<?xml")) else "bin"\n Path(f"image-{index}.{ext}").write_bytes(raw)\n print("Every returned image saved; complete response metadata retained")\n\nf=Path(os.environ["AILOOT_PROMPT_FILE"])\nif not f.is_file():raise SystemExit("Set your actual UTF-8 image brief file")\nrequest={'model': 'gpt-image-2', 'prompt': ''}\nrequest["prompt"]=f.read_text(encoding="utf-8")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nresult=client.images.generate(**request)\nPath("sdk-result.txt").write_text(str(result),encoding="utf-8")\nsave_images([{"b64_json":getattr(item,"b64_json",None),"url":getattr(item,"url",None)} for item in result.data])\nimport OpenAI from "openai";\nimport { readFileSync, writeFileSync } from "node:fs";\nconst key=process.env.AILOOT_API_KEY;\nif(!key) throw new Error("Set your actual Ailoot API key");\nconst client=new OpenAI({baseURL:"https://api.ailoot.ai/v1",apiKey:key,maxRetries:0});\nconst request={"model": "gpt-image-2", "prompt": ""};\nif(!process.env.AILOOT_PROMPT_FILE)throw new Error("Set your actual UTF-8 image brief file");\nrequest.prompt=readFileSync(process.env.AILOOT_PROMPT_FILE,"utf8");\nconst result=await client.images.generate(request);\nwriteFileSync("sdk-result.json",JSON.stringify(result,null,2));\nif(!result.data?.length) throw new Error("No completed images");\nfor(let index=0;index<result.data.length;index++) {\n const item=result.data[index];let encoded=item.b64_json,uri=item.url||"",raw;\n if(!encoded && uri.startsWith("data:image/")) {\n const comma=uri.indexOf(",");if(comma<0 || !uri.slice(0,comma).includes(";base64")) throw new Error("Unsupported image data URI");\n encoded=uri.slice(comma+1);\n }\n if(encoded) {\n if(encoded.length%4!==0 || !/^[A-Za-z0-9+/]*={0,2}$/.test(encoded)) throw new Error("Invalid Base64");\n raw=Buffer.from(encoded,"base64");\n } else if(uri) {\n const u=new URL(uri,"https://api.ailoot.ai");\n if(u.protocol!=="https:" || u.username || u.password) throw new Error("Invalid returned URL");\n const owned=u.origin==="https://api.ailoot.ai" && u.pathname.startsWith("/v1/media/assets/") && u.pathname.endsWith("/content");\n const response=await fetch(u,{headers:owned?{Authorization:"Bearer "+key}:{},redirect:"manual"});\n if(!response.ok) throw new Error("Image content download failed: "+response.status);\n raw=Buffer.from(await response.arrayBuffer());\n } else throw new Error("Image has neither bytes nor URL");\n if(!raw.length) throw new Error("Empty image result");\n const ext=raw.subarray(0,4).equals(Buffer.from([137,80,78,71]))?"png":raw[0]===255&&raw[1]===216?"jpg":raw.toString("ascii",0,4)==="RIFF"&&raw.toString("ascii",8,12)==="WEBP"?"webp":raw.toString("utf8").trimStart().startsWith("<svg")||raw.toString("utf8").trimStart().startsWith("<?xml")?"svg":"bin";\n writeFileSync(`image-${index}.${ext}`,raw);\n}\nconsole.log("Every returned image saved; sdk-result.json retains complete metadata");\nDownload each returned image or save its Base64 contents
GET /v1/media/tasks/{task_id}GET /v1/media/assets/{asset_id}/contentGET /v1/media/assetsGET /v1/media/assets/{asset_id}Save every completed image; retrieve each returned URL or decode its Base64 contents.
Save every data item. Decode each b64_json or fetch every returned signed URL. Select a filename extension from the actual MIME/bytes.
If an image generation or edit result requires a check, keep the original operation_id/X-Client-Request-ID and returned result information. Recover existing owned results through the media library using actual task_id or asset_id values. Do not resubmit the generation/edit request or construct a polling URL from operation_id.
| Field | Type |
|---|---|
Fieldcreated | Typeinteger |
Fielddata[].url | Typestring |
Fielddata[].b64_json | Typebase64 string |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Responseserver_error | ConditionThe returned response says the operation or result requires a check | Next stepKeep the original returned operation/task ID, request headers and response; continue supported reads of that original operation. Do not resubmit the creation request. |
Ailoot gpt-image-2
Ailoot Ultra gpt-image-2, openai/gpt-image-2
/v1/images
gpt-image-2GPT Image 2 generates and edits images from text and visual references. It supports flexible frame dimensions and automatically processes image inputs at high fidelity, with separate quality, format and background controls for the finished asset.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
GPT Image 2 is OpenAI’s model for image generation and editing from text and visual inputs. It creates a new image from a written brief and can use source images for edits or reference-led work. Practical tasks include illustrations, product concepts, visual compositions and changes to an existing asset. It is a separate edition from the GPT Image 2.5 Sunburst and Flare models, with its own quality range and input-fidelity behaviour.
For generation, describe the subject, scene, composition, light and intended style. For an edit, name what should change and what should keep its appearance. A product brief can request a ceramic lamp on a pale surface with a centred silhouette and room for a caption; a follow-up edit can change the background while retaining the lamp’s shape and viewing angle. The documented direct generation and edit workflows accept prompts up to 32,000 characters and can return one to ten images.
Reference editing accepts up to sixteen input images. Specify the purpose of each reference so a subject, background and visual treatment are not confused. GPT Image 2 processes every image input at high fidelity automatically; input_fidelity should be omitted because it is not adjustable for this edition. This differs from the high-or-low choice on GPT Image 1 and the low-only input-fidelity mode of GPT Image 1 Mini. High-fidelity input processing supports source detail without guaranteeing that every detail is reproduced unchanged.
A mask can identify the region to edit. The source image and mask must have the same format and dimensions and be below 50 MB in the guide’s preparation requirements; the mask also needs an alpha channel. If several input images are provided, masking applies to the first. The model treats the mask as prompt-based guidance rather than a strict geometric boundary. Describe the local change and preservation requirements, then examine the surrounding area for unintended differences.
GPT Image 2 supports low, medium, high and auto quality, with auto as the default. The 2.5 family’s xhigh and max settings are not part of this edition’s quality range. Size can be square, landscape, portrait, automatic or a valid custom width and height. The producer examples include 1024 × 1024, 1536 × 1024, 1024 × 1536, 2048 × 2048, 2048 × 1152, 3840 × 2160 and 2160 × 3840 pixels. Choose the orientation and detail level for the actual layout rather than treating quality and dimensions as the same control.
Custom dimensions must be multiples of sixteen pixels, with a maximum edge of 3840 pixels, a long-to-short-edge ratio no greater than 3:1 and an area from 655,360 to 8,294,400 pixels. These conditions hold simultaneously. Resolutions above 2560 × 1440 are marked experimental. A frame that satisfies one rule can still fail another, so select a supported pair of dimensions and describe the crop-sensitive elements in the brief.
Output is PNG by default, with JPEG or WebP also available. Compression from 0 to 100 is supported for JPEG and WebP. The background can be opaque or automatic; the exact current reference describes transparency for GPT Image 2 as a preview capability. When requesting transparency, use PNG or WebP so an alpha channel can be retained. The documented streaming workflow permits up to three partial images before the finished image; save the final asset rather than a progress preview. The manufacturer interface also supports batch processing.
Evaluate text clarity, the position of objects and preservation of source details in the actual result. GPT Image can struggle with precise lettering, layout-sensitive compositions and recurring visual identity across separate generations. For a sequence of edits, use the chosen result as the next source and give a concrete change tied to a visible issue. GPT Image 2’s useful output is an image connected to a clear generation or edit brief, with its high-fidelity inputs, dimensions and quality chosen for that specific task.
POST /v1/images/generationstextimage| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits gpt-image-2 | Default— |
Fieldprompt | Typestring | RequirementRequired | Values & limits Maximum length: 32,000 | Default— |
Fieldsize | Typestring | RequirementOptional | Values & limits Conditions: Use auto or WIDTHxHEIGHT with both dimensions divisible by 16. The longest side is at most 3,840 pixels and total size at most 8,300,000 pixels. | Defaultauto |
Fieldbackground | Typestring | RequirementOptional | Values & limits transparent, opaque, auto | Defaultauto |
Fieldmoderation | Typestring | RequirementOptional | Values & limits low, auto Conditions: Use auto for standard content moderation. | Default— |
Fieldn | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Maximum: 10 | Default1 |
Fieldquality | Typestring | RequirementOptional | Values & limits auto, high, medium, low | Defaultauto |
Fieldoutput_compression | Typeinteger | RequirementOptional | Values & limits Minimum: 0 Maximum: 100 Conditions: Applies to JPEG and WebP output; send the documented integer value. | Default100 |
Fieldoutput_format | Typestring | RequirementOptional | Values & limits webp, png, jpeg | Defaultpng |
Fieldstream | Typeboolean | RequirementOptional | Values & limits false Conditions: This route returns one completed JSON response. | Defaultfalse |
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractprompt, model |
Parametermaterial_types | Contracttext |
Parameteroptional | Contractsize, background, moderation, n, quality, output_compression, output_format, stream |
Parameterconditions | ContractA transparent background requires PNG or WebP., Output compression applies to JPEG or WebP., The selected method generates from text. Editing and streaming controls described for the manufacturer are separate capabilities. |
Lifecycle: synchronous_result_then_owned_library
GET /v1/media/tasks/{task_id} · actual returned task_id or media library record
GET /v1/media/assets/{asset_id}/content
GET /v1/media/assets
GET /v1/media/assets/{asset_id}
The displayed rates estimate the cost before generation. The final charge is calculated from the cost recorded for the original generation. Measured output duration and forecast quantities are not the final billable quantity.
Tariff references do not add request options. Supported parameters are listed for the selected method.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Forecast quantity | Charge |
|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Forecast quantity— | Charge Input · Input tokens · Estimate for comparison only — / 1K tokens Output · Output tokens · Estimate for comparison only — / 1K tokens Input · Cache read · Estimate for comparison only — / 1K tokens Input · Cache write · Estimate for comparison only — / 1K tokens Input · Cache write, 1 hour · Estimate for comparison only — / 1K tokens |
| ConfigurationEstimated generation cost | Rate schedule— | Forecast quantityone generation estimate | Charge Output · Estimated generation cost · Estimate for comparison only $0.24576 estimate before generation This estimate is not an additional charge or a fixed rate for the completed generation. |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\nexport AILOOT_API_KEY\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np={'prompt': 'A cute baby sea otter', 'model': 'gpt-image-2', 'size': '1024x1024', 'n': 1, 'background': 'auto', 'moderation': 'auto', 'output_format': 'png'}\n\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/images/generations \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json, os, subprocess\nfrom pathlib import Path\nfrom urllib.parse import urlsplit, urljoin\n\ndef save_images(items):\n if not items: raise SystemExit("No completed images; retain the full response")\n for index, item in enumerate(items):\n encoded=item.get("b64_json")\n uri=item.get("url", "")\n if not encoded and uri.startswith("data:image/"):\n header, separator, encoded=uri.partition(",")\n if not separator or ";base64" not in header: raise SystemExit("Unsupported image data URI")\n if encoded:\n raw=base64.b64decode(encoded,validate=True)\n elif uri:\n uri=urljoin("https://api.ailoot.ai",uri)\n parsed=urlsplit(uri)\n if parsed.scheme!="https" or not parsed.netloc or parsed.username or parsed.password:\n raise SystemExit("Invalid returned image URL")\n owned=parsed.netloc=="api.ailoot.ai" and parsed.path.startswith("/v1/media/assets/") and parsed.path.endswith("/content")\n args=["curl","--fail-with-body","--silent","--show-error",uri]\n if owned: args += ["-H","Authorization: Bearer "+os.environ["AILOOT_API_KEY"]]\n temporary=Path(f"image-{index}.bin")\n subprocess.run(args+["-o",str(temporary)],check=True)\n raw=temporary.read_bytes()\n temporary.unlink()\n else: raise SystemExit("Image has neither bytes nor URL")\n if not raw: raise SystemExit("Empty image result")\n ext="png" if raw.startswith(b"\\x89PNG") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else "svg" if raw.lstrip().startswith((b"<svg",b"<?xml")) else "bin"\n Path(f"image-{index}.{ext}").write_bytes(raw)\n print("Every returned image saved; complete response metadata retained")\nsave_images(json.loads(Path("result.json").read_text())["data"])\nPY_RESULT\nDownload each returned image or save its Base64 contents
GET /v1/media/tasks/{task_id}GET /v1/media/assets/{asset_id}/contentGET /v1/media/assetsGET /v1/media/assets/{asset_id}set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/media/assets \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -o owned-assets.json\n# Preserve every returned asset and follow its exact signed content URL. Do not construct a signed token.\nSave every completed image; retrieve each returned URL or decode its Base64 contents.
Retain the complete response and headers, every actual output, original returned identifiers and all usage fields. Recover the original operation without submitting creation again.
Keep the returned X-Client-Request-ID for reconciliation. Read only actual returned task_id/asset_id values or the owned media library; never build a task URL from the operation ID and never resubmit creation.
| Field | Type |
|---|---|
Fieldcreated | Type |
Fielddata[].url | Type |
Fielddata[].b64_json | Type |
Fieldusage | Type |
Ailoot gpt-image-2
Ailoot Ultra gpt-image-2, openai/gpt-image-2
/v1/images
openai/gpt-image-2GPT Image 2 generates and edits images from text and visual references. It supports flexible frame dimensions and automatically processes image inputs at high fidelity, with separate quality, format and background controls for the finished asset.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
GPT Image 2 is OpenAI’s model for image generation and editing from text and visual inputs. It creates a new image from a written brief and can use source images for edits or reference-led work. Practical tasks include illustrations, product concepts, visual compositions and changes to an existing asset. It is a separate edition from the GPT Image 2.5 Sunburst and Flare models, with its own quality range and input-fidelity behaviour.
For generation, describe the subject, scene, composition, light and intended style. For an edit, name what should change and what should keep its appearance. A product brief can request a ceramic lamp on a pale surface with a centred silhouette and room for a caption; a follow-up edit can change the background while retaining the lamp’s shape and viewing angle. The documented direct generation and edit workflows accept prompts up to 32,000 characters and can return one to ten images.
Reference editing accepts up to sixteen input images. Specify the purpose of each reference so a subject, background and visual treatment are not confused. GPT Image 2 processes every image input at high fidelity automatically; input_fidelity should be omitted because it is not adjustable for this edition. This differs from the high-or-low choice on GPT Image 1 and the low-only input-fidelity mode of GPT Image 1 Mini. High-fidelity input processing supports source detail without guaranteeing that every detail is reproduced unchanged.
A mask can identify the region to edit. The source image and mask must have the same format and dimensions and be below 50 MB in the guide’s preparation requirements; the mask also needs an alpha channel. If several input images are provided, masking applies to the first. The model treats the mask as prompt-based guidance rather than a strict geometric boundary. Describe the local change and preservation requirements, then examine the surrounding area for unintended differences.
GPT Image 2 supports low, medium, high and auto quality, with auto as the default. The 2.5 family’s xhigh and max settings are not part of this edition’s quality range. Size can be square, landscape, portrait, automatic or a valid custom width and height. The producer examples include 1024 × 1024, 1536 × 1024, 1024 × 1536, 2048 × 2048, 2048 × 1152, 3840 × 2160 and 2160 × 3840 pixels. Choose the orientation and detail level for the actual layout rather than treating quality and dimensions as the same control.
Custom dimensions must be multiples of sixteen pixels, with a maximum edge of 3840 pixels, a long-to-short-edge ratio no greater than 3:1 and an area from 655,360 to 8,294,400 pixels. These conditions hold simultaneously. Resolutions above 2560 × 1440 are marked experimental. A frame that satisfies one rule can still fail another, so select a supported pair of dimensions and describe the crop-sensitive elements in the brief.
Output is PNG by default, with JPEG or WebP also available. Compression from 0 to 100 is supported for JPEG and WebP. The background can be opaque or automatic; the exact current reference describes transparency for GPT Image 2 as a preview capability. When requesting transparency, use PNG or WebP so an alpha channel can be retained. The documented streaming workflow permits up to three partial images before the finished image; save the final asset rather than a progress preview. The manufacturer interface also supports batch processing.
Evaluate text clarity, the position of objects and preservation of source details in the actual result. GPT Image can struggle with precise lettering, layout-sensitive compositions and recurring visual identity across separate generations. For a sequence of edits, use the chosen result as the next source and give a concrete change tied to a visible issue. GPT Image 2’s useful output is an image connected to a clear generation or edit brief, with its high-fidelity inputs, dimensions and quality chosen for that specific task.
POST /v1/images/generationstext, imageimage| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits openai/gpt-image-2 | Default— |
Fieldprompt | Typestring | RequirementRequired | Values & limits Minimum length: 1 | Default— |
Fieldaspect_ratio | Typestring | RequirementOptional | Values & limits 1:1, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, 21:9, auto | Default— |
Fieldquality | Typestring | RequirementOptional | Values & limits auto, low, medium, high | Default— |
Fieldbackground | Typestring | RequirementOptional | Values & limits auto, opaque | Default— |
Fieldn | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Maximum: 10 | Default— |
Fieldinput_references | Typearray | RequirementOptional | Values & limits Minimum items: 0 Maximum items: 16 | Default— |
Fieldoutput_compression | Typeinteger | RequirementOptional | Values & limits Minimum: 0 Maximum: 100 | Default— |
Fieldprovider | Typeobject | RequirementOptional | Values & limits | Default— |
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, prompt |
Parametermaterial_types | Contracttext, image |
Lifecycle: synchronous_result_then_owned_library
GET /v1/media/tasks/{task_id} · actual returned task_id or media library record
GET /v1/media/assets/{asset_id}/content
GET /v1/media/assets
GET /v1/media/assets/{asset_id}
The displayed rates estimate the cost before generation. The final charge is calculated from the cost recorded for the original generation. Measured output duration and forecast quantities are not the final billable quantity.
Tariff references do not add request options. Supported parameters are listed for the selected method.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Forecast quantity | Charge |
|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Forecast quantity— | Charge Input · Input tokens · Estimate for comparison only — / 1K tokens Output · Output tokens · Estimate for comparison only — / 1K tokens Input · Cache read · Estimate for comparison only — / 1K tokens Input · Cache write · Estimate for comparison only — / 1K tokens Input · Cache write, 1 hour · Estimate for comparison only — / 1K tokens |
| ConfigurationEstimated generation cost | Rate schedule— | Forecast quantityone generation estimate | Charge Output · Estimated generation cost · Estimate for comparison only $0.24576 estimate before generation This estimate is not an additional charge or a fixed rate for the completed generation. |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\nexport AILOOT_API_KEY\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np={'model': 'openai/gpt-image-2', 'prompt': 'a red panda astronaut floating in space, studio lighting'}\n\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/images/generations \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json, os, subprocess\nfrom pathlib import Path\nfrom urllib.parse import urlsplit, urljoin\n\ndef save_images(items):\n if not items: raise SystemExit("No completed images; retain the full response")\n for index, item in enumerate(items):\n encoded=item.get("b64_json")\n uri=item.get("url", "")\n if not encoded and uri.startswith("data:image/"):\n header, separator, encoded=uri.partition(",")\n if not separator or ";base64" not in header: raise SystemExit("Unsupported image data URI")\n if encoded:\n raw=base64.b64decode(encoded,validate=True)\n elif uri:\n uri=urljoin("https://api.ailoot.ai",uri)\n parsed=urlsplit(uri)\n if parsed.scheme!="https" or not parsed.netloc or parsed.username or parsed.password:\n raise SystemExit("Invalid returned image URL")\n owned=parsed.netloc=="api.ailoot.ai" and parsed.path.startswith("/v1/media/assets/") and parsed.path.endswith("/content")\n args=["curl","--fail-with-body","--silent","--show-error",uri]\n if owned: args += ["-H","Authorization: Bearer "+os.environ["AILOOT_API_KEY"]]\n temporary=Path(f"image-{index}.bin")\n subprocess.run(args+["-o",str(temporary)],check=True)\n raw=temporary.read_bytes()\n temporary.unlink()\n else: raise SystemExit("Image has neither bytes nor URL")\n if not raw: raise SystemExit("Empty image result")\n ext="png" if raw.startswith(b"\\x89PNG") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else "svg" if raw.lstrip().startswith((b"<svg",b"<?xml")) else "bin"\n Path(f"image-{index}.{ext}").write_bytes(raw)\n print("Every returned image saved; complete response metadata retained")\nsave_images(json.loads(Path("result.json").read_text())["data"])\nPY_RESULT\nDownload each returned image or save its Base64 contents
GET /v1/media/tasks/{task_id}GET /v1/media/assets/{asset_id}/contentGET /v1/media/assetsGET /v1/media/assets/{asset_id}set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/media/assets \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -o owned-assets.json\n# Preserve every returned asset and follow its exact signed content URL. Do not construct a signed token.\nSave every completed image; retrieve each returned URL or decode its Base64 contents.
Retain the complete response and headers, every actual output, original returned identifiers and all usage fields. Recover the original operation without submitting creation again.
Keep the returned X-Client-Request-ID for reconciliation. Read only actual returned task_id/asset_id values or the owned media library; never build a task URL from the operation ID and never resubmit creation.
| Field | Type |
|---|---|
Fieldcreated | Type |
Fielddata[].url | Type |
Fielddata[].b64_json | Type |
Fieldusage | Type |
Ailoot gpt-image-2
Ailoot Ultra gpt-image-2, openai/gpt-image-2
/v1/images