Recraft V4.1 is the main raster model in Recraft’s V4.1 family. It is built for expressive image creation, including natural-looking photographs, illustration and dimensional visual concepts. The manufacturer presents it as a model that can supply aesthetic decisions from a short prompt while also responding to more detailed creative direction. Use it for exploration, concepting and images where mood, lighting and composition form part of the result rather than being reduced to a simple front-facing product view.
The exact producer code is recraftv4_1. It returns 1K raster images in lossless WebP or PNG, with square output at 1024 × 1024 pixels and 16:9 at 1344 × 768. Other supported ratios use their own dimensions. V4.1 Pro is the separate 2K raster edition, Vector returns editable SVG, and Utility favours simpler lighting and scenes. These branches serve different deliverables and should not be merged into one set of output properties.
The manufacturer highlights more natural photographic scenes, a quieter background, smoother gradients and a broad illustration range. Its examples include expressive lettering, flat character illustration and a drawn character reference sheet. A short prompt can leave room for the model’s interpretation; a detailed brief can fix the subject, pose, material, background and composition. For a dimensional visual, specify the surface and lighting treatment, while remembering that the result is an image rather than a mesh or an editable 3D project.
For a reading-space concept, request an intimate photograph of a small reading nook, warm daylight, books and one ceramic object, with a relaxed rather than showroom-like arrangement. A controlled illustration brief could instead name the graphic subject, colour relationships and line treatment. State the intended aspect ratio and the visual decisions that matter most. This makes it easier to decide whether an unexpected detail is useful creative interpretation or something that should change in the next brief.
The generation reference permits prompts up to 10,000 characters, a random seed, preferred colours and a desired background colour, with one to six outputs. Optional reference images or compatible saved styles can establish a visual language with flexible or precise matching. They are not required for the main V4.1 edition. Select clean references that agree with each other and use the prompt for the new content; reference colour reproduction is not guaranteed. For reference-style generation, use one to ten PNG, JPG or WebP images, no more than 64 MB in total and under 20 MB each. Each reference needs a shortest side of at least 256 pixels, a longest side of no more than 4,096 pixels and a resolution of no more than 16 megapixels. Use either these references or a compatible saved style, rather than both.
V4.1 also supports a separate image-to-image workflow with an existing image, text and strength from 0 to 1. The operation uses strength to control how closely the new image stays to the source, and does not accept V4.1 custom style controls. The model’s current generation reference excludes negative_prompt, curated styles, text_layout, artistic_level and no_text. Describe the intended scene directly and inspect the resulting asset in the target layout, including its details, crop and any lettering, before deciding which visual direction to keep. For image-to-image, supply PNG, JPG, WebP or SVG under 20 MB, no more than 16 megapixels, with both sides between 256 and 4,096 pixels.
", "aboutText": "Recraft V4.1 is the main raster model in Recraft’s V4.1 family. It is built for expressive image creation, including natural-looking photographs, illustration and dimensional visual concepts. The manufacturer presents it as a model that can supply aesthetic decisions from a short prompt while also responding to more detailed creative direction. Use it for exploration, concepting and images where mood, lighting and composition form part of the result rather than being reduced to a simple front-facing product view.\n\nThe exact producer code is recraftv4_1. It returns 1K raster images in lossless WebP or PNG, with square output at 1024 × 1024 pixels and 16:9 at 1344 × 768. Other supported ratios use their own dimensions. V4.1 Pro is the separate 2K raster edition, Vector returns editable SVG, and Utility favours simpler lighting and scenes. These branches serve different deliverables and should not be merged into one set of output properties.\n\nThe manufacturer highlights more natural photographic scenes, a quieter background, smoother gradients and a broad illustration range. Its examples include expressive lettering, flat character illustration and a drawn character reference sheet. A short prompt can leave room for the model’s interpretation; a detailed brief can fix the subject, pose, material, background and composition. For a dimensional visual, specify the surface and lighting treatment, while remembering that the result is an image rather than a mesh or an editable 3D project.\n\nFor a reading-space concept, request an intimate photograph of a small reading nook, warm daylight, books and one ceramic object, with a relaxed rather than showroom-like arrangement. A controlled illustration brief could instead name the graphic subject, colour relationships and line treatment. State the intended aspect ratio and the visual decisions that matter most. This makes it easier to decide whether an unexpected detail is useful creative interpretation or something that should change in the next brief.\n\nThe generation reference permits prompts up to 10,000 characters, a random seed, preferred colours and a desired background colour, with one to six outputs. Optional reference images or compatible saved styles can establish a visual language with flexible or precise matching. They are not required for the main V4.1 edition. Select clean references that agree with each other and use the prompt for the new content; reference colour reproduction is not guaranteed. For reference-style generation, use one to ten PNG, JPG or WebP images, no more than 64 MB in total and under 20 MB each. Each reference needs a shortest side of at least 256 pixels, a longest side of no more than 4,096 pixels and a resolution of no more than 16 megapixels. Use either these references or a compatible saved style, rather than both.\n\nV4.1 also supports a separate image-to-image workflow with an existing image, text and strength from 0 to 1. The operation uses strength to control how closely the new image stays to the source, and does not accept V4.1 custom style controls. The model’s current generation reference excludes negative_prompt, curated styles, text_layout, artistic_level and no_text. Describe the intended scene directly and inspect the resulting asset in the target layout, including its details, crop and any lettering, before deciding which visual direction to keep. For image-to-image, supply PNG, JPG, WebP or SVG under 20 MB, no more than 16 megapixels, with both sides between 256 and 4,096 pixels.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "49455c151f29f348b27c837272096964f55f7c6da0cd17d56bedd9ccb1acf46e", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "recraft/recraft-v4.1Recraft V4.1 creates 1K raster images with natural photorealism, expressive illustration and deliberate composition. It can develop a short creative direction or follow a detailed brief, with optional image and custom-style inputs.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Recraft V4.1 is the main raster model in Recraft’s V4.1 family. It is built for expressive image creation, including natural-looking photographs, illustration and dimensional visual concepts. The manufacturer presents it as a model that can supply aesthetic decisions from a short prompt while also responding to more detailed creative direction. Use it for exploration, concepting and images where mood, lighting and composition form part of the result rather than being reduced to a simple front-facing product view.
The exact producer code is recraftv4_1. It returns 1K raster images in lossless WebP or PNG, with square output at 1024 × 1024 pixels and 16:9 at 1344 × 768. Other supported ratios use their own dimensions. V4.1 Pro is the separate 2K raster edition, Vector returns editable SVG, and Utility favours simpler lighting and scenes. These branches serve different deliverables and should not be merged into one set of output properties.
The manufacturer highlights more natural photographic scenes, a quieter background, smoother gradients and a broad illustration range. Its examples include expressive lettering, flat character illustration and a drawn character reference sheet. A short prompt can leave room for the model’s interpretation; a detailed brief can fix the subject, pose, material, background and composition. For a dimensional visual, specify the surface and lighting treatment, while remembering that the result is an image rather than a mesh or an editable 3D project.
For a reading-space concept, request an intimate photograph of a small reading nook, warm daylight, books and one ceramic object, with a relaxed rather than showroom-like arrangement. A controlled illustration brief could instead name the graphic subject, colour relationships and line treatment. State the intended aspect ratio and the visual decisions that matter most. This makes it easier to decide whether an unexpected detail is useful creative interpretation or something that should change in the next brief.
The generation reference permits prompts up to 10,000 characters, a random seed, preferred colours and a desired background colour, with one to six outputs. Optional reference images or compatible saved styles can establish a visual language with flexible or precise matching. They are not required for the main V4.1 edition. Select clean references that agree with each other and use the prompt for the new content; reference colour reproduction is not guaranteed. For reference-style generation, use one to ten PNG, JPG or WebP images, no more than 64 MB in total and under 20 MB each. Each reference needs a shortest side of at least 256 pixels, a longest side of no more than 4,096 pixels and a resolution of no more than 16 megapixels. Use either these references or a compatible saved style, rather than both.
V4.1 also supports a separate image-to-image workflow with an existing image, text and strength from 0 to 1. The operation uses strength to control how closely the new image stays to the source, and does not accept V4.1 custom style controls. The model’s current generation reference excludes negative_prompt, curated styles, text_layout, artistic_level and no_text. Describe the intended scene directly and inspect the resulting asset in the target layout, including its details, crop and any lettering, before deciding which visual direction to keep. For image-to-image, supply PNG, JPG, WebP or SVG under 20 MB, no more than 16 megapixels, with both sides between 256 and 4,096 pixels.
POST /v1/images/generationstext, imageimage| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits recraft/recraft-v4.1 | Default— |
Fieldprompt | Typestring | RequirementRequired | Values & limits Minimum length: 1 | Default— |
Fieldaspect_ratio | Typestring | RequirementOptional | Values & limits 1:1, 4:3, 3:4, 16:9, 9:16, auto | Default— |
Fieldn | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Maximum: 6 | Default— |
Fieldinput_references | Typearray | RequirementOptional | Values & limits Minimum items: 0 Maximum items: 1 | 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 | 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 |
| Configurationoutput image | Rate schedule— | Forecast quantity— | Billing unitper output image | Charge Output · output image · Estimate for comparison only $0.07 per output image |
| ConfigurationEstimated generation cost | Rate schedule— | Forecast quantityone generation estimate | Billing unit— | Charge Output · Estimated generation cost · Estimate for comparison only $0.07 estimate before generation This estimate is not an additional charge or a fixed rate for the completed generation. |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\nexport AILOOT_API_KEY\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np={'model': 'recraft/recraft-v4.1', '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 Ultra recraft/recraft-v4.1
/v1/images