Source: https://ailoot.ai/models/en/recraft-recraft-v4-1/ Canonical: https://ailoot.ai/models/en/recraft-recraft-v4-1/ Language: en # Recraft: Recraft V4.1 [Markdown](https://ailoot.ai/models/en/recraft-recraft-v4-1/index.md) · [JSON](https://ailoot.ai/models/en/recraft-recraft-v4-1/facts.json) ## [Recraft: Recraft V4.1](https://ailoot.ai/models/en/recraft-recraft-v4-1/) Recraft 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. - [**Ailoot Ultra · Images** `POST /v1/images/generations` `recraft/recraft-v4.1`](https://ailoot.ai/models/en/recraft-recraft-v4-1/#method-0) About the model 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. **Ailoot Ultra · Images** `POST /v1/images/generations` `recraft/recraft-v4.1` [`recraft/recraft-v4.1`](https://ailoot.ai/models/en/#m=recraft%2Frecraft-v4.1&route=Ultra&caller=recraft%2Frecraft-v4.1&fmt=images) Recraft /`recraft/recraft-v4.1` ### Overview Recraft 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. Accepted inputs Text · Images Results Images ### Available in Ailoot · inputs & methods **Ailoot Ultra · Images** `POST /v1/images/generations` Input types `text`, `image` Output types `image` | Field | Type | Requirement | Values & limits | Default | | --- | --- | --- | --- | --- | | Field`model` | Type`string` | RequirementRequired | Values & limits recraft/recraft-v4.1 | Default— | | Field`prompt` | Type`string` | RequirementRequired | Values & limits Minimum length: 1 | Default— | | Field`aspect_ratio` | Type`string` | RequirementOptional | Values & limits 1:1, 4:3, 3:4, 16:9, 9:16, auto | Default— | | Field`n` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Maximum: 6 | Default— | | Field`input_references` | Type`array` | RequirementOptional | Values & limits Minimum items: 0 Maximum items: 1 | Default— | | Field`provider` | Type`object` | RequirementOptional | Values & limits | Default— | Method parameters and lifecycle | Parameter | Contract | | --- | --- | | Parameter`content_type` | Contractapplication/json | | Parameter`required` | Contractmodel, prompt | | Parameter`material_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}` ### Pricing ##### How the final charge is calculated 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. Fast mode Not specified When fast mode is selected Flex mode Not specified When flex mode is selected Maximum reasoning effort Not specified When maximum reasoning effort uses the default adjustment #### Estimated rates for comparison #### Prices by configuration 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 **$0.07** estimate before generation This estimate is not an additional charge or a fixed rate for the completed generation. | Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/) ### Example requests #### Ailoot Ultra · Images curl ```bash set -eu : "${AILOOT_API_KEY:?Set your Ailoot API key}" export AILOOT_API_KEY python3 - <<'PY_REQUEST' import json,os from pathlib import Path p={'model': 'recraft/recraft-v4.1', 'prompt': 'a red panda astronaut floating in space, studio lighting'} Path("request.json").write_text(json.dumps(p,ensure_ascii=False)) PY_REQUEST curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/images/generations \ -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \ --data-binary @request.json -D response-headers.txt -o result.json python3 - <<'PY_RESULT' import base64, json, os, subprocess from pathlib import Path from urllib.parse import urlsplit, urljoin def save_images(items): if not items: raise SystemExit("No completed images; retain the full response") for index, item in enumerate(items): encoded=item.get("b64_json") uri=item.get("url", "") if not encoded and uri.startswith("data:image/"): header, separator, encoded=uri.partition(",") if not separator or ";base64" not in header: raise SystemExit("Unsupported image data URI") if encoded: raw=base64.b64decode(encoded,validate=True) elif uri: uri=urljoin("https://api.ailoot.ai",uri) parsed=urlsplit(uri) if parsed.scheme!="https" or not parsed.netloc or parsed.username or parsed.password: raise SystemExit("Invalid returned image URL") owned=parsed.netloc=="api.ailoot.ai" and parsed.path.startswith("/v1/media/assets/") and parsed.path.endswith("/content") args=["curl","--fail-with-body","--silent","--show-error",uri] if owned: args += ["-H","Authorization: Bearer "+os.environ["AILOOT_API_KEY"]] temporary=Path(f"image-{index}.bin") subprocess.run(args+["-o",str(temporary)],check=True) raw=temporary.read_bytes() temporary.unlink() else: raise SystemExit("Image has neither bytes nor URL") if not raw: raise SystemExit("Empty image result") 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"