Recraft V3 is an image-generation model built for graphic design as well as photographic and illustrated scenes. A written brief describes the subject, setting and composition; the result is an image. V3 develops Recraft's text rendering and photorealism while retaining style consistency from example images without retraining.
V3 works with text inside the image, including longer copy and mid-size lettering. Recraft describes a layout stage that establishes words and their positions before image generation. The layout can be produced automatically from the brief or arranged manually in Recraft's design environment. This helps connect a headline, illustration and supporting text within one composition. The manufacturer also documents explicit text-layout coordinates, expressed relative to the image rather than as a fixed pixel grid. Each text element contains a single word and four corner points in normalized coordinates: (0, 0) is the top-left and (1, 1) the bottom-right. Coordinates may extend beyond that range, in which case the shape is cropped. Explicit text-layout words must follow the documented character restrictions.
For a poster or cover, supply the exact wording and describe its hierarchy: which line leads, where it sits and how the picture supports it. Check the rendered spelling and spacing when selecting a result.
V3 includes curated photographic, illustration and emblem styles, plus a separate vector-style library. Recraft V3 Raw is the raster model's default style; Vector art is the default for the vector variant. Photorealism aims at a photographic appearance, while Illustration accommodates stylised textures, shading and more complex colour transitions. Vector styles favour shapes, limited palettes and flat fills or simple gradients.
Custom styles can be built from reference images, existing compatible styles or a combination. They provide a reusable visual direction across an image series. The documented mixing controls let references and source styles carry separate weights; the weight counts match the sources. PaletteMatch and MaxWeight are the two listed mixing policies. The manufacturer allows up to 10 style-reference images and uses the regular style-match mode for V3. A stored custom style and direct style references are alternative inputs, and a custom style must match the model used for generation.
Preferred colours and a background colour guide the palette. Up to 10 RGB colours are documented, with each component from 0 to 255. Optional relative weights range from 0 to 1; they must be supplied for every colour or for none, and their total cannot exceed 1. Artistic level ranges from 0 for a static, clean treatment to 5 for more dynamic, eccentric compositions. A negative prompt describes unwanted elements; a separate no-text control disables embedded text layouts. A random seed is available for reproducibility. These controls give different levers for the scene, its styling and its visual layout.
Recraft documents two V3 variants. The raster model produces lossless WebP or PNG and is suitable for photographic detail, shading and textured illustration. Recraft V3 Vector produces SVG: paths and shapes that can scale without a fixed pixel resolution. It suits pictograms, logo concepts, badges and detailed vector artwork. Raster-to-vector conversion is a separate operation from generating vector artwork directly.
Both variants have their own identity. An image with a vector-like appearance and an actual SVG output are different choices. Select the intended output when preparing a design workflow, rather than treating the shared V3 name as proof that every operation returns the same file type.
Recraft's V3 documentation lists image-to-image generation, inpainting, outpainting and background replacement or generation. Image-to-image work combines an existing image with a new brief. Inpainting regenerates the selected region using an image and a matching mask; outpainting adds content beyond the original frame. Background operations address the surroundings of a subject.
The accompanying toolset also includes erasing, background removal, vectorization and two upscaling approaches. Creative upscaling can introduce new detail; crisp upscaling targets a sharper larger rendition of existing content. These are distinct operations with their own inputs and results, rather than additional meanings of the raster or vector model name.
The manufacturer's V3 generation specification accepts a prompt of up to 1000 characters and 1–6 images per request. It supports 14 aspect ratios: 1:1, 2:1, 1:2, 3:2, 2:3, 4:3, 3:4, 5:4, 4:5, 6:10, 14:10, 10:14, 16:9 and 9:16. Documented raster examples include 1024x1024, 1820x1024 and 1024x1820. Exact raster dimensions must be from the supported list; SVG uses aspect ratios without a fixed pixel size. When size is omitted, the manufacturer's system selects it from the prompt.
For image-input operations, the manufacturer lists PNG, JPG and WebP, with SVG where the particular operation allows it. Files must be under 20 MB, no larger than 16 MP, with a longest side of at most 4096 pixels. The shortest side is at least 256 pixels, with a 32-pixel exception for crisp upscaling. Masks match the image size and use pure black and white; style references have a combined 64 MB limit.
For an Ailoot API project, turn the task into a focused image brief: the exact copy, object arrangement, visual style and desired composition. A poster, a product scene and an icon series call for different briefs; preserve the relevant V3 variant and operation distinctions when deciding how each result will be used.
", "aboutText": "Recraft V3 is an image-generation model built for graphic design as well as photographic and illustrated scenes. A written brief describes the subject, setting and composition; the result is an image. V3 develops Recraft's text rendering and photorealism while retaining style consistency from example images without retraining.\n\n### Text as part of the composition\n\nV3 works with text inside the image, including longer copy and mid-size lettering. Recraft describes a layout stage that establishes words and their positions before image generation. The layout can be produced automatically from the brief or arranged manually in Recraft's design environment. This helps connect a headline, illustration and supporting text within one composition. The manufacturer also documents explicit text-layout coordinates, expressed relative to the image rather than as a fixed pixel grid. Each text element contains a single word and four corner points in normalized coordinates: (0, 0) is the top-left and (1, 1) the bottom-right. Coordinates may extend beyond that range, in which case the shape is cropped. Explicit text-layout words must follow the documented character restrictions.\n\nFor a poster or cover, supply the exact wording and describe its hierarchy: which line leads, where it sits and how the picture supports it. Check the rendered spelling and spacing when selecting a result.\n\n### Style, palette and artistic direction\n\nV3 includes curated photographic, illustration and emblem styles, plus a separate vector-style library. Recraft V3 Raw is the raster model's default style; Vector art is the default for the vector variant. Photorealism aims at a photographic appearance, while Illustration accommodates stylised textures, shading and more complex colour transitions. Vector styles favour shapes, limited palettes and flat fills or simple gradients.\n\nCustom styles can be built from reference images, existing compatible styles or a combination. They provide a reusable visual direction across an image series. The documented mixing controls let references and source styles carry separate weights; the weight counts match the sources. PaletteMatch and MaxWeight are the two listed mixing policies. The manufacturer allows up to 10 style-reference images and uses the regular style-match mode for V3. A stored custom style and direct style references are alternative inputs, and a custom style must match the model used for generation.\n\nPreferred colours and a background colour guide the palette. Up to 10 RGB colours are documented, with each component from 0 to 255. Optional relative weights range from 0 to 1; they must be supplied for every colour or for none, and their total cannot exceed 1. Artistic level ranges from 0 for a static, clean treatment to 5 for more dynamic, eccentric compositions. A negative prompt describes unwanted elements; a separate no-text control disables embedded text layouts. A random seed is available for reproducibility. These controls give different levers for the scene, its styling and its visual layout.\n\n### Raster images and a separate SVG variant\n\nRecraft documents two V3 variants. The raster model produces lossless WebP or PNG and is suitable for photographic detail, shading and textured illustration. Recraft V3 Vector produces SVG: paths and shapes that can scale without a fixed pixel resolution. It suits pictograms, logo concepts, badges and detailed vector artwork. Raster-to-vector conversion is a separate operation from generating vector artwork directly.\n\nBoth variants have their own identity. An image with a vector-like appearance and an actual SVG output are different choices. Select the intended output when preparing a design workflow, rather than treating the shared V3 name as proof that every operation returns the same file type.\n\n### Editing and finishing existing artwork\n\nRecraft's V3 documentation lists image-to-image generation, inpainting, outpainting and background replacement or generation. Image-to-image work combines an existing image with a new brief. Inpainting regenerates the selected region using an image and a matching mask; outpainting adds content beyond the original frame. Background operations address the surroundings of a subject.\n\nThe accompanying toolset also includes erasing, background removal, vectorization and two upscaling approaches. Creative upscaling can introduce new detail; crisp upscaling targets a sharper larger rendition of existing content. These are distinct operations with their own inputs and results, rather than additional meanings of the raster or vector model name.\n\n### Prompt, size and source-image limits\n\nThe manufacturer's V3 generation specification accepts a prompt of up to 1000 characters and 1–6 images per request. It supports 14 aspect ratios: 1:1, 2:1, 1:2, 3:2, 2:3, 4:3, 3:4, 5:4, 4:5, 6:10, 14:10, 10:14, 16:9 and 9:16. Documented raster examples include 1024x1024, 1820x1024 and 1024x1820. Exact raster dimensions must be from the supported list; SVG uses aspect ratios without a fixed pixel size. When size is omitted, the manufacturer's system selects it from the prompt.\n\nFor image-input operations, the manufacturer lists PNG, JPG and WebP, with SVG where the particular operation allows it. Files must be under 20 MB, no larger than 16 MP, with a longest side of at most 4096 pixels. The shortest side is at least 256 pixels, with a 32-pixel exception for crisp upscaling. Masks match the image size and use pure black and white; style references have a combined 64 MB limit.\n\nFor an Ailoot API project, turn the task into a focused image brief: the exact copy, object arrangement, visual style and desired composition. A poster, a product scene and an icon series call for different briefs; preserve the relevant V3 variant and operation distinctions when deciding how each result will be used.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "e022aec8d098a9f6fcfa117d4935f3eea8b7244cc4a6e4f2c28aed1e9f37d9f5", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "recraft/recraft-v3Recraft V3 creates photographs, illustrations and graphic layouts with text-aware composition and style controls. Its distinct raster and SVG variants suit posters, branded image sets, icons and designs where wording and visual structure need to work together.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Recraft V3 is an image-generation model built for graphic design as well as photographic and illustrated scenes. A written brief describes the subject, setting and composition; the result is an image. V3 develops Recraft's text rendering and photorealism while retaining style consistency from example images without retraining.
V3 works with text inside the image, including longer copy and mid-size lettering. Recraft describes a layout stage that establishes words and their positions before image generation. The layout can be produced automatically from the brief or arranged manually in Recraft's design environment. This helps connect a headline, illustration and supporting text within one composition. The manufacturer also documents explicit text-layout coordinates, expressed relative to the image rather than as a fixed pixel grid. Each text element contains a single word and four corner points in normalized coordinates: (0, 0) is the top-left and (1, 1) the bottom-right. Coordinates may extend beyond that range, in which case the shape is cropped. Explicit text-layout words must follow the documented character restrictions.
For a poster or cover, supply the exact wording and describe its hierarchy: which line leads, where it sits and how the picture supports it. Check the rendered spelling and spacing when selecting a result.
V3 includes curated photographic, illustration and emblem styles, plus a separate vector-style library. Recraft V3 Raw is the raster model's default style; Vector art is the default for the vector variant. Photorealism aims at a photographic appearance, while Illustration accommodates stylised textures, shading and more complex colour transitions. Vector styles favour shapes, limited palettes and flat fills or simple gradients.
Custom styles can be built from reference images, existing compatible styles or a combination. They provide a reusable visual direction across an image series. The documented mixing controls let references and source styles carry separate weights; the weight counts match the sources. PaletteMatch and MaxWeight are the two listed mixing policies. The manufacturer allows up to 10 style-reference images and uses the regular style-match mode for V3. A stored custom style and direct style references are alternative inputs, and a custom style must match the model used for generation.
Preferred colours and a background colour guide the palette. Up to 10 RGB colours are documented, with each component from 0 to 255. Optional relative weights range from 0 to 1; they must be supplied for every colour or for none, and their total cannot exceed 1. Artistic level ranges from 0 for a static, clean treatment to 5 for more dynamic, eccentric compositions. A negative prompt describes unwanted elements; a separate no-text control disables embedded text layouts. A random seed is available for reproducibility. These controls give different levers for the scene, its styling and its visual layout.
Recraft documents two V3 variants. The raster model produces lossless WebP or PNG and is suitable for photographic detail, shading and textured illustration. Recraft V3 Vector produces SVG: paths and shapes that can scale without a fixed pixel resolution. It suits pictograms, logo concepts, badges and detailed vector artwork. Raster-to-vector conversion is a separate operation from generating vector artwork directly.
Both variants have their own identity. An image with a vector-like appearance and an actual SVG output are different choices. Select the intended output when preparing a design workflow, rather than treating the shared V3 name as proof that every operation returns the same file type.
Recraft's V3 documentation lists image-to-image generation, inpainting, outpainting and background replacement or generation. Image-to-image work combines an existing image with a new brief. Inpainting regenerates the selected region using an image and a matching mask; outpainting adds content beyond the original frame. Background operations address the surroundings of a subject.
The accompanying toolset also includes erasing, background removal, vectorization and two upscaling approaches. Creative upscaling can introduce new detail; crisp upscaling targets a sharper larger rendition of existing content. These are distinct operations with their own inputs and results, rather than additional meanings of the raster or vector model name.
The manufacturer's V3 generation specification accepts a prompt of up to 1000 characters and 1–6 images per request. It supports 14 aspect ratios: 1:1, 2:1, 1:2, 3:2, 2:3, 4:3, 3:4, 5:4, 4:5, 6:10, 14:10, 10:14, 16:9 and 9:16. Documented raster examples include 1024x1024, 1820x1024 and 1024x1820. Exact raster dimensions must be from the supported list; SVG uses aspect ratios without a fixed pixel size. When size is omitted, the manufacturer's system selects it from the prompt.
For image-input operations, the manufacturer lists PNG, JPG and WebP, with SVG where the particular operation allows it. Files must be under 20 MB, no larger than 16 MP, with a longest side of at most 4096 pixels. The shortest side is at least 256 pixels, with a 32-pixel exception for crisp upscaling. Masks match the image size and use pure black and white; style references have a combined 64 MB limit.
For an Ailoot API project, turn the task into a focused image brief: the exact copy, object arrangement, visual style and desired composition. A poster, a product scene and an icon series call for different briefs; preserve the relevant V3 variant and operation distinctions when deciding how each result will be used.
POST /v1/images/generationstext, imageimage| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits recraft/recraft-v3 | Default— |
Fieldprompt | Typestring | RequirementRequired | Values & limits Minimum length: 1 | Default— |
Fieldn | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Maximum: 6 | Default— |
Fieldaspect_ratio | Typestring | RequirementOptional | Values & limits 1:1, 4:3, 3:4, 16:9, 9:16, auto | Default— |
Fieldinput_references | Typearray | RequirementOptional | Values & limits Minimum items: 0 Maximum items: 1 | Default— |
Text to image · Required: prompt
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, prompt |
Parametermaterial_types | Contracttext, image |
Parameteroptional_controls | Contractaspect_ratio, n, input_references |
Parameterexact_supported_parameters | Contract{"aspect_ratio":{"type":"enum","values":["1:1","4:3","3:4","16:9","9:16","auto"]},"n":{"type":"range","min":1,"max":6},"input_references":{"type":"range","min":0,"max":1}} |
Parameterreference_material_rule | ContractActual customer image references only; provider endpoint conditions govern them. |
Method aliases: /v1/images
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}
Use the exact model and documented input fields.
Keep the complete response, every actual output and original returned IDs.
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 | Billing unit | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Forecast quantity— | Billing unit— | 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 |
| ConfigurationUltra | Rate schedule— | Forecast quantity— | Billing unitper image output | Charge Output · image output · Estimate for comparison only $0.08 per image output |
| ConfigurationEstimated generation cost | Rate schedule— | Forecast quantityone generation estimate | Billing unit— | Charge Output · Estimated generation cost · Estimate for comparison only $0.08 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 →
Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.
| Configuration | Billing conditions | Charge |
|---|---|---|
| ConfigurationOutput image | Billing conditionsNo pricing variant is declared. | Charge Output · Output image $0.08 per image Equivalent listings describe the same charge; they do not add a second fee. |
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\nexport AILOOT_API_KEY\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np={'model': 'recraft/recraft-v3', '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\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\nrequest={'model': 'recraft/recraft-v3', 'prompt': 'a red panda astronaut floating in space, studio lighting'}\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": "recraft/recraft-v3", "prompt": "a red panda astronaut floating in space, studio lighting"};\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.
Retain every data item and complete usage; own and save all actual returned images. No invented URLs or IDs.
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 |
Ailoot Ultra recraft/recraft-v3
/v1/images