{ "aboutHtml": "

Recraft V4 Styles Vector is the SVG-producing model in Recraft’s dedicated style-consistent generation line. It turns a text brief into new vector artwork while using a supplied reference style to guide the rendering, colour logic and overall look. It is useful for coordinated icon sets, brand illustration and graphic systems where subjects change but the visual treatment should stay recognisable. The Vector edition returns an editable graphic rather than a raster photograph.

The producer identifies this edition as recraftv4_styles_vector. Its output is always SVG; raster image_format settings do not convert it into WebP or PNG. Every vector variant accepts the fourteen documented aspect ratios as width-to-height ratios rather than exact pixel sizes. SVG has no fixed pixel resolution, so the standard raster model’s 1K output is not an architectural size for this edition. Choose the desired shape of the asset and the intended small or large display use when preparing the brief.

A style is required for each generation. Use one to ten PNG, JPG or WebP references, or a compatible saved style instead of new references. The producer rejects a request that combines a saved style identifier with style reference images. The documented reference allowance is 64 MB in total and under 20 MB per file. A single clear icon or illustration can establish the treatment; several references are useful when their line weight, corners, fill logic and palette already belong to the same visual system. Each reference must have a shortest side of at least 256 pixels, a longest side of no more than 4,096 pixels and a total resolution of no more than 16 megapixels.

Flexible matching is the default and takes a looser reading of the reference, while precise matching follows its rendering, colour, composition and lighting more closely. For a vector system, use the prompt to define the graphic type, silhouette, object count and layout. For a navigation icon set, use bold rounded outlines, one centred object per image and a two-colour palette. Keep the same reference style and change the named object in each brief, rather than mixing unrelated references to obtain variety.

The generation reference permits prompts up to 10,000 characters, one to six outputs, a random seed, preferred colours and a desired background colour. Negative prompts, curated style names and the older text_layout control are unsupported. This Styles edition also does not provide image-to-image or inpainting: an image reference supplies a visual language rather than a region to erase or an existing graphic to preserve unchanged. Structural instructions in the positive brief should describe the intended finished asset.

Inspect the SVG at the size where it will be used, especially when the design contains lettering, narrow gaps or small details. Colour matching to a reference is not guaranteed, and unrelated references can compete. For an icon set that becomes repetitive, change the object, pose or arrangement in the prompt while retaining the coherent style. The useful deliverable is a consistent vector asset that can be reshaped and recoloured in a design workflow, with its geometry and legibility evaluated against the brief.

Through Ailoot, select this exact model ID in /v1/images/generations and supply the creative prompt. Retain every returned data entry, whether the response carries a URL or encoded image content, and save the actual bytes with their returned content type. Keep usage and any media task_id with the asset, then review its shapes, lettering and colour regions in the intended design.

", "aboutText": "Recraft V4 Styles Vector is the SVG-producing model in Recraft’s dedicated style-consistent generation line. It turns a text brief into new vector artwork while using a supplied reference style to guide the rendering, colour logic and overall look. It is useful for coordinated icon sets, brand illustration and graphic systems where subjects change but the visual treatment should stay recognisable. The Vector edition returns an editable graphic rather than a raster photograph.\n\nThe producer identifies this edition as recraftv4_styles_vector. Its output is always SVG; raster image_format settings do not convert it into WebP or PNG. Every vector variant accepts the fourteen documented aspect ratios as width-to-height ratios rather than exact pixel sizes. SVG has no fixed pixel resolution, so the standard raster model’s 1K output is not an architectural size for this edition. Choose the desired shape of the asset and the intended small or large display use when preparing the brief.\n\nA style is required for each generation. Use one to ten PNG, JPG or WebP references, or a compatible saved style instead of new references. The producer rejects a request that combines a saved style identifier with style reference images. The documented reference allowance is 64 MB in total and under 20 MB per file. A single clear icon or illustration can establish the treatment; several references are useful when their line weight, corners, fill logic and palette already belong to the same visual system. Each reference must have a shortest side of at least 256 pixels, a longest side of no more than 4,096 pixels and a total resolution of no more than 16 megapixels.\n\nFlexible matching is the default and takes a looser reading of the reference, while precise matching follows its rendering, colour, composition and lighting more closely. For a vector system, use the prompt to define the graphic type, silhouette, object count and layout. For a navigation icon set, use bold rounded outlines, one centred object per image and a two-colour palette. Keep the same reference style and change the named object in each brief, rather than mixing unrelated references to obtain variety.\n\nThe generation reference permits prompts up to 10,000 characters, one to six outputs, a random seed, preferred colours and a desired background colour. Negative prompts, curated style names and the older text_layout control are unsupported. This Styles edition also does not provide image-to-image or inpainting: an image reference supplies a visual language rather than a region to erase or an existing graphic to preserve unchanged. Structural instructions in the positive brief should describe the intended finished asset.\n\nInspect the SVG at the size where it will be used, especially when the design contains lettering, narrow gaps or small details. Colour matching to a reference is not guaranteed, and unrelated references can compete. For an icon set that becomes repetitive, change the object, pose or arrangement in the prompt while retaining the coherent style. The useful deliverable is a consistent vector asset that can be reshaped and recoloured in a design workflow, with its geometry and legibility evaluated against the brief.\n\nThrough Ailoot, select this exact model ID in /v1/images/generations and supply the creative prompt. Retain every returned data entry, whether the response carries a URL or encoded image content, and save the actual bytes with their returned content type. Keep usage and any media task_id with the asset, then review its shapes, lettering and colour regions in the intended design.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "ed16413e5295ddf636506169d5e356b2b208c8981f913848e807a0b0d26a7622", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "
•

Recraft: Recraft V4 Styles Vector

Other /recraft/recraft-v4-styles-vector

Overview

Recraft V4 Styles Vector creates editable SVG graphics from a text brief and a required visual style. It suits coordinated icons, logos and illustrations whose line treatment, palette and rendering should follow the same reference direction.

Accepted inputs
Text · Images
Results
Images
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 Styles Vector is the SVG-producing model in Recraft’s dedicated style-consistent generation line. It turns a text brief into new vector artwork while using a supplied reference style to guide the rendering, colour logic and overall look. It is useful for coordinated icon sets, brand illustration and graphic systems where subjects change but the visual treatment should stay recognisable. The Vector edition returns an editable graphic rather than a raster photograph.

The producer identifies this edition as recraftv4_styles_vector. Its output is always SVG; raster image_format settings do not convert it into WebP or PNG. Every vector variant accepts the fourteen documented aspect ratios as width-to-height ratios rather than exact pixel sizes. SVG has no fixed pixel resolution, so the standard raster model’s 1K output is not an architectural size for this edition. Choose the desired shape of the asset and the intended small or large display use when preparing the brief.

A style is required for each generation. Use one to ten PNG, JPG or WebP references, or a compatible saved style instead of new references. The producer rejects a request that combines a saved style identifier with style reference images. The documented reference allowance is 64 MB in total and under 20 MB per file. A single clear icon or illustration can establish the treatment; several references are useful when their line weight, corners, fill logic and palette already belong to the same visual system. Each reference must have a shortest side of at least 256 pixels, a longest side of no more than 4,096 pixels and a total resolution of no more than 16 megapixels.

Flexible matching is the default and takes a looser reading of the reference, while precise matching follows its rendering, colour, composition and lighting more closely. For a vector system, use the prompt to define the graphic type, silhouette, object count and layout. For a navigation icon set, use bold rounded outlines, one centred object per image and a two-colour palette. Keep the same reference style and change the named object in each brief, rather than mixing unrelated references to obtain variety.

The generation reference permits prompts up to 10,000 characters, one to six outputs, a random seed, preferred colours and a desired background colour. Negative prompts, curated style names and the older text_layout control are unsupported. This Styles edition also does not provide image-to-image or inpainting: an image reference supplies a visual language rather than a region to erase or an existing graphic to preserve unchanged. Structural instructions in the positive brief should describe the intended finished asset.

Inspect the SVG at the size where it will be used, especially when the design contains lettering, narrow gaps or small details. Colour matching to a reference is not guaranteed, and unrelated references can compete. For an icon set that becomes repetitive, change the object, pose or arrangement in the prompt while retaining the coherent style. The useful deliverable is a consistent vector asset that can be reshaped and recoloured in a design workflow, with its geometry and legibility evaluated against the brief.

Through Ailoot, select this exact model ID in /v1/images/generations and supply the creative prompt. Retain every returned data entry, whether the response carries a URL or encoded image content, and save the actual bytes with their returned content type. Keep usage and any media task_id with the asset, then review its shapes, lettering and colour regions in the intended design.

Available in Ailoot · inputs & methods

Ailoot Ultra · Images POST /v1/images/generations
Input types
text, image
Output types
image
Output format
Image file
FieldTypeRequirementValues & limitsDefault
FieldmodelTypestringRequirementRequiredValues & limits
recraft/recraft-v4-styles-vector
Conditions: Use this exact Ailoot routing selector.
Default—
FieldpromptTypestringRequirementRequiredValues & limits
Conditions:
Default—
FieldnTypeintegerRequirementOptionalValues & limits
Minimum: 1
Maximum: 6
Conditions:
Default—
Fieldaspect_ratioTypestringRequirementOptionalValues & limits
1:1, 2:1, 1:2, 3:2, 2:3, 4:3, 3:4, 5:4, 4:5, 16:9, 9:16, auto
Conditions:
Default—
Fieldoutput_formatTypestringRequirementOptionalValues & limits
svg
Conditions:
Default—
Fieldinput_referencesTypearrayRequirementRequiredValues & limits
Conditions:
Default—
FieldqualityTypestringRequirementOptionalValues & limits
auto, low, medium, high, xhigh, max
Conditions:
Default—
Input material combinations

reference_guided_image

Method parameters and lifecycle
ParameterContract
Parametercontent_typeContractapplication/json
ParameterrequiredContractmodel, prompt, input_references
ParameteroptionalContractn, aspect_ratio, output_format, quality
Parametermaterial_typesContracttext, image
ParameterconditionsContractUse this exact Ailoot routing selector., quality is a common documented control; providers without a quality knob ignore it. No per-model quality improvement is promised.

Lifecycle: synchronous_result_then_owned_library

GET /v1/media/tasks/{task_id} · actual returned task_id or selected library record; operation_id is a separate identifier

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.

ConfigurationRate scheduleForecast quantityBilling unitBilling conditionsCharge
ConfigurationBase token ratesRate scheduleBase rateForecast quantity—Billing unit—Billing conditions—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
ConfigurationInput referenceRate schedule—Forecast quantity—Billing unitper requestBilling conditionsStyle creation when generating with style references; once per request, in addition to the output-image price.Charge
Input · Input reference · Estimate for comparison only $0.01 per request

Reference estimate only; final charge follows the recorded original invoice.

Configurationoutput imageRate schedule—Forecast quantity—Billing unitper output imageBilling conditions—Charge
Output · output image · Estimate for comparison only $0.1 per output image
ConfigurationEstimated generation costRate schedule—Forecast quantityone generation estimateBilling unit—Billing conditions—Charge
Output · Estimated generation cost · Estimate for comparison only $0.1 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 →

Example requests

Ailoot Ultra · Images

set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\nexport AILOOT_API_KEY\n: "${AILOOT_IMAGE_URL:?Set an actual customer material or documented value}"\nexport AILOOT_IMAGE_URL\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "recraft/recraft-v4-styles-vector", "prompt": "A portrait of an Asian woman with neon green lights in the background, shallow depth of field.", "input_references": [{"type": "image_url", "image_url": {"url": "YOUR_ACCESSIBLE_IMAGE_URL"}}]}')\np['input_references'][0]['image_url']['url']=os.environ['AILOOT_IMAGE_URL']\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\n# Submit once. Retain the complete result, original identifiers and every response header.\n

Receive and save results

Ailoot Ultra · Images

Download each returned image or save its Base64 contents

Keep all completed results

Save every completed image; retrieve each returned URL or decode its Base64 contents.

Retain the complete response and headers, original identifiers, every actual output and all usage/accounting fields. Save each unique owned asset and retain every role pointing to it.

If the original response needs checking

Keep the original X-Client-Request-ID, response and headers. An unknown or result_pending_check outcome does not authorize a second creation.

Response fields
FieldType
Fielddata[].urlTypestring
Fielddata[].b64_jsonTypestring
FieldusageTypeobject
Errors and next steps
ResponseConditionNext step
Response400 · invalid_request_errorConditionA required field, model selector, type or input representation is invalid.Next stepInspect the returned validation detail before preparing a separate request.
ResponseConditionThe original request or result is unknown or requires a check.Next stepKeep original identifiers and headers; read only supported status/library records. Do not submit creation again.

Aliases

Model aliases

Ailoot Ultra recraft/recraft-v4-styles-vector

Method path aliases

Use the method paths shown above.

Related caller IDs

recraft/recraft-v4-styles-vector

", "method_identity": { "effective_request_model_id": "recraft/recraft-v4-styles-vector", "fmt": "images", "http": "POST", "path": "/v1/images/generations", "request_model_id": "recraft/recraft-v4-styles-vector", "route_label": "Ultra" }, "method_key": "Ultra|images|/v1/images/generations|recraft%2Frecraft-v4-styles-vector", "ordinal": 0, "rawMethod": { "available": null, "billing_basis": { "basis": "original_invoice_usd", "description": "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.", "forecast_quantity_is_estimate": true, "physical_output_is_billable_quantity": false, "version": "original_invoice_usd_v1" }, "cache_read": null, "cache_write": null, "cache_write_1h": null, "contract": { "data": { "all_results": "Retain the complete response and headers, original identifiers, every actual output and all usage/accounting fields. Save each unique owned asset and retain every role pointing to it.", "authentication": { "header": "Authorization", "scheme": "Bearer", "value": "$AILOOT_API_KEY" }, "control_semantics": { "other_documented_controls": "Source generic image parsing preserves request JSON. Additional documented controls stay subject to the exact model; missing DTO fields do not create Source refusals.", "quality": "The saved common image schema documents this control and says providers without a quality knob ignore it.", "style": "Selected generic Source passes JSON fields through but the saved dedicated image request schema does not declare a style field. Its omission here is not a Source ban or a supported per-model promise." }, "errors": [ { "condition": "A required field, model selector, type or input representation is invalid.", "http_status": 400, "recovery": "Inspect the returned validation detail before preparing a separate request.", "type": "invalid_request_error" }, { "condition": "The original request or result is unknown or requires a check.", "http_status": null, "recovery": "Keep original identifiers and headers; read only supported status/library records. Do not submit creation again.", "type": null } ], "lifecycle": { "assets": [ { "http": "GET", "path": "/v1/media/assets" }, { "http": "GET", "path": "/v1/media/assets/{asset_id}" } ], "cancel_endpoint": null, "create": { "http": "POST", "path": "/v1/images/generations" }, "mode": "synchronous_result_then_owned_library", "operation_id_is_not_task_id": true, "owned_content": { "http": "GET", "path": "/v1/media/assets/{asset_id}/content", "url_source": "Use the exact returned signed URL; never construct a token." }, "status": [ { "http": "GET", "id_source": "actual returned task_id or selected library record; operation_id is a separate identifier", "path": "/v1/media/tasks/{task_id}" } ], "unknown": "Keep the original X-Client-Request-ID, response and headers. An unknown or result_pending_check outcome does not authorize a second creation.", "unknown_no_replay": true }, "material_combinations": [ { "materials": [ "text", "image" ], "metadata_authority": "saved_model_discovery_union", "mode": "reference_guided_image", "reference_maximum": 10, "reference_minimum": 1 } ], "model_parameter_metadata": { "authority": "saved_model_discovery_union", "defaults_not_inferred": { "aspect_ratio": null, "exact_pixels": null, "explanation": "No universal/model default inferred. Omitted output_format uses provider default; dimensions are provider-derived, observed Ming2048 is not a universal default.", "n": null, "output_format": null, "quality": null, "resolution": null }, "known_parameter_choices": { "aspect_ratio": { "type": "enum", "values": [ "1:1", "2:1", "1:2", "3:2", "2:3", "4:3", "3:4", "5:4", "4:5", "16:9", "9:16", "auto" ] }, "input_references": { "max": 10, "min": 1, "type": "range" }, "n": { "max": 6, "min": 1, "type": "range" }, "output_format": { "type": "enum", "values": [ "svg" ] } }, "pointer": "/profiles/13", "scope": "Exact saved model metadata. Discovery unions are identified explicitly and are not represented as definitive selected-provider bounds." }, "outputs": { "all_results": "Retain the complete response and headers, original identifiers, every actual output and all usage/accounting fields. Save each unique owned asset and retain every role pointing to it.", "documented_formats": [ "svg" ], "every_actual_output": true, "family": "image", "fields": [ { "name": "data[].url", "type": "string" }, { "name": "data[].b64_json", "type": "string" }, { "name": "usage", "type": "object" } ], "format": "The exact saved model metadata lists SVG. Preserve the actual returned MIME and unchanged vector bytes; keep every actual output and owned signed image link." }, "parameters": [ { "conditions": "Use this exact Ailoot routing selector.", "default_known": false, "enum": [ "recraft/recraft-v4-styles-vector" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "conditions": "", "default_known": false, "enum_known": false, "name": "prompt", "required": true, "type": "string" }, { "conditions": "", "default_known": false, "enum_known": false, "maximum": 6, "minimum": 1, "name": "n", "required": false, "type": "integer" }, { "conditions": "", "default_known": false, "enum": [ "1:1", "2:1", "1:2", "3:2", "2:3", "4:3", "3:4", "5:4", "4:5", "16:9", "9:16", "auto" ], "enum_known": true, "name": "aspect_ratio", "required": false, "type": "string" }, { "conditions": "", "default_known": false, "enum": [ "svg" ], "enum_known": true, "name": "output_format", "required": false, "type": "string" }, { "conditions": "", "default_known": false, "enum_known": false, "items": { "properties": { "image_url": { "properties": { "url": { "type": "string" } }, "required": [ "url" ], "type": "object" }, "type": { "const": "image_url" } }, "required": [ "type", "image_url" ], "type": "object" }, "maxItems": 10, "minItems": 1, "name": "input_references", "required": true, "type": "array" }, { "conditions": "", "default_known": false, "enum": [ "auto", "low", "medium", "high", "xhigh", "max" ], "enum_known": true, "name": "quality", "required": false, "type": "string" } ], "request_schema": { "additionalProperties": true, "properties": { "aspect_ratio": { "enum": [ "1:1", "2:1", "1:2", "3:2", "2:3", "4:3", "3:4", "5:4", "4:5", "16:9", "9:16", "auto" ], "type": "string" }, "input_references": { "items": { "properties": { "image_url": { "properties": { "url": { "type": "string" } }, "required": [ "url" ], "type": "object" }, "type": { "const": "image_url" } }, "required": [ "type", "image_url" ], "type": "object" }, "maxItems": 10, "minItems": 1, "type": "array" }, "model": { "enum": [ "recraft/recraft-v4-styles-vector" ], "type": "string" }, "n": { "maximum": 6, "minimum": 1, "type": "integer" }, "output_format": { "enum": [ "svg" ], "type": "string" }, "prompt": { "type": "string" }, "quality": { "enum": [ "auto", "low", "medium", "high", "xhigh", "max" ], "type": "string" } }, "required": [ "model", "prompt", "input_references" ], "type": "object" }, "schema_template": { "actual_file_preparation_required": true, "body": { "input_references": [ { "image_url": { "url": "YOUR_ACCESSIBLE_IMAGE_URL" }, "type": "image_url" } ], "model": "recraft/recraft-v4-styles-vector", "prompt": "A portrait of an Asian woman with neon green lights in the background, shallow depth of field." }, "content_type": "application/json", "example_is_offline_content": true }, "usage": { "meter": "Use the accepted method price and actual recorded usage; the request reserve is an estimate. A billing unit does not add an input capability.", "preserve": "Keep all returned usage, accounting and request identifiers with every actual output.", "settlement": "Retain the original operation; reconcile its result and accounting once." } }, "input": { "conditions": [ "Use this exact Ailoot routing selector.", "quality is a common documented control; providers without a quality knob ignore it. No per-model quality improvement is promised." ], "content_type": "application/json", "material_types": [ "text", "image" ], "optional": [ "n", "aspect_ratio", "output_format", "quality" ], "required": [ "model", "prompt", "input_references" ] }, "lifecycle": { "assets": [ { "http": "GET", "path": "/v1/media/assets" }, { "http": "GET", "path": "/v1/media/assets/{asset_id}" } ], "cancel_endpoint": null, "create": { "http": "POST", "path": "/v1/images/generations" }, "mode": "synchronous_result_then_owned_library", "operation_id_is_not_task_id": true, "owned_content": { "http": "GET", "path": "/v1/media/assets/{asset_id}/content", "url_source": "Use the exact returned signed URL; never construct a token." }, "status": [ { "http": "GET", "id_source": "actual returned task_id or selected library record; operation_id is a separate identifier", "path": "/v1/media/tasks/{task_id}" } ], "unknown": "Keep the original X-Client-Request-ID, response and headers. An unknown or result_pending_check outcome does not authorize a second creation.", "unknown_no_replay": true }, "method": { "http": "POST", "path": "/v1/images/generations" }, "method_aliases": [], "output": { "all_results": "Retain the complete response and headers, original identifiers, every actual output and all usage/accounting fields. Save each unique owned asset and retain every role pointing to it.", "documented_formats": [ "svg" ], "every_actual_output": true, "family": "image", "fields": [ { "name": "data[].url", "type": "string" }, { "name": "data[].b64_json", "type": "string" }, { "name": "usage", "type": "object" } ], "format": "The saved exact model metadata lists SVG. Preserve actual MIME and bytes; storage MIME support alone does not prove completion of the full selected generic output path." } }, "ctx": null, "declared_pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] }, { "basis": "Reference estimate only; final charge follows the recorded original invoice.", "dimensions": { "conditions": "Style creation when generating with style references; once per request, in addition to the output-image price.", "quoted_unit": "per request" }, "label": "Input reference", "units": [ { "amount": "0.01", "amount_unit": "usd_per_request", "billing_input": false, "estimate_only": true, "key": "image_input_reference_request", "label": "Input reference", "native_amount_usd_per_unit": "0.01", "native_quantity": 1, "public_unit_label": "per request", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "request" } ] }, { "dimensions": { "quoted_unit": "per output image" }, "label": "output image", "units": [ { "amount": "0.1", "amount_unit": "usd_per_exact_native_unit", "billing_input": false, "estimate_only": true, "key": "image_output", "label": "output image", "native_amount_usd_per_unit": "0.1", "native_quantity": 1, "public_unit_label": "per output image", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "image_output" } ] }, { "basis": "This estimate is not an additional charge or a fixed rate for the completed generation.", "dimensions": { "forecast_quantity": "one generation estimate" }, "label": "Estimated generation cost", "units": [ { "amount": "0.1", "amount_unit": "usd_per_exact_native_unit", "billing_input": false, "estimate_only": true, "key": "forecast_usd", "label": "Estimated generation cost", "native_amount_usd_per_unit": "0.1", "native_quantity": 1, "public_unit_label": "estimate before generation", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "request_estimate" } ] } ], "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\nexport AILOOT_API_KEY\n: \"${AILOOT_IMAGE_URL:?Set an actual customer material or documented value}\"\nexport AILOOT_IMAGE_URL\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"recraft/recraft-v4-styles-vector\", \"prompt\": \"A portrait of an Asian woman with neon green lights in the background, shallow depth of field.\", \"input_references\": [{\"type\": \"image_url\", \"image_url\": {\"url\": \"YOUR_ACCESSIBLE_IMAGE_URL\"}}]}')\np['input_references'][0]['image_url']['url']=os.environ['AILOOT_IMAGE_URL']\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\n# Submit once. Retain the complete result, original identifiers and every response header.\n", "label": "curl · create once and retain the complete result", "language": "bash" } ], "family": "openai", "fast_multiplier": null, "flex_multiplier": null, "fmt": "images", "http": "POST", "in": null, "input": [ "text", "image" ], "input_conditions": { "image": "Use the exact model reference-input range in the saved model metadata; a reference becomes required only for the models whose listed minimum is positive." }, "label": "Images", "max_out": null, "max_reasoning_effort_multiplier": null, "method_aliases": [], "out": null, "output": [ "image" ], "path": "/v1/images/generations", "price_conditions": [ { "label": "Fast mode", "value": "Not specified", "when": "When fast mode is selected" }, { "label": "Flex mode", "value": "Not specified", "when": "When flex mode is selected" }, { "label": "Maximum reasoning effort", "value": "Not specified", "when": "When maximum reasoning effort uses the default adjustment" } ], "pricing": { "billing_mode": "original_invoice_usd", "image_input_price": null, "image_output_price": null }, "pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] }, { "basis": "Reference estimate only; final charge follows the recorded original invoice.", "dimensions": { "conditions": "Style creation when generating with style references; once per request, in addition to the output-image price.", "quoted_unit": "per request" }, "label": "Input reference", "units": [ { "amount": "0.01", "amount_unit": "usd_per_request", "billing_input": false, "estimate_only": true, "key": "image_input_reference_request", "label": "Input reference", "native_amount_usd_per_unit": "0.01", "native_quantity": 1, "public_unit_label": "per request", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "request" } ] }, { "dimensions": { "quoted_unit": "per output image" }, "label": "output image", "units": [ { "amount": "0.1", "amount_unit": "usd_per_exact_native_unit", "billing_input": false, "estimate_only": true, "key": "image_output", "label": "output image", "native_amount_usd_per_unit": "0.1", "native_quantity": 1, "public_unit_label": "per output image", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "image_output" } ] }, { "basis": "This estimate is not an additional charge or a fixed rate for the completed generation.", "dimensions": { "forecast_quantity": "one generation estimate" }, "label": "Estimated generation cost", "units": [ { "amount": "0.1", "amount_unit": "usd_per_exact_native_unit", "billing_input": false, "estimate_only": true, "key": "forecast_usd", "label": "Estimated generation cost", "native_amount_usd_per_unit": "0.1", "native_quantity": 1, "public_unit_label": "estimate before generation", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "request_estimate" } ] } ], "request_model_id": "recraft/recraft-v4-styles-vector", "route_label": "Ultra", "status_reads": [ "GET /v1/media/tasks/{task_id}" ], "tiers": [], "units": [ { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" }, { "amount": "0.01", "amount_unit": "usd_per_request", "billing_input": false, "estimate_only": true, "key": "image_input_reference_request", "label": "Input reference", "native_amount_usd_per_unit": "0.01", "native_quantity": 1, "public_unit_label": "per request", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "request" }, { "amount": "0.1", "amount_unit": "usd_per_exact_native_unit", "billing_input": false, "estimate_only": true, "key": "image_output", "label": "output image", "native_amount_usd_per_unit": "0.1", "native_quantity": 1, "public_unit_label": "per output image", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "image_output" }, { "amount": "0.1", "amount_unit": "usd_per_exact_native_unit", "billing_input": false, "estimate_only": true, "key": "forecast_usd", "label": "Estimated generation cost", "native_amount_usd_per_unit": "0.1", "native_quantity": 1, "public_unit_label": "estimate before generation", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "request_estimate" } ] } } ], "model_id": "recraft/recraft-v4-styles-vector", "nativeProvenance": { "input_facts_canonical_sha256": "8cee838d88c38f45d835088c1caedc7d70849e800328098d763cda29b167c752", "input_html_sha256": "9d058abea4ff2661c2d4a1e8c637ed65cf91fd4581b5fa30147650273afb1c9f", "private_audit_sha256": "a24e404e892fd406ee7f8873fa3c61e1a2ffc2762fa33f9d99867195d8164a9c", "role": "historical-normalized-input-audit-hashes", "schema": "ailoot-native-model-provenance-v2" }, "page": { "canonical": "https://ailoot.ai/models/en/recraft-recraft-v4-styles-vector/", "description": "Recraft V4 Styles Vector creates editable SVG graphics from a text brief and a required visual style. It suits coordinated icons, logos and illustrations whose line treatment, palette and rendering should follow the same reference direction.", "locale": "en", "md_url": "https://ailoot.ai/models/en/recraft-recraft-v4-styles-vector/index.md", "title": "Recraft: Recraft V4 Styles Vector — Ailoot", "url": "https://ailoot.ai/models/en/recraft-recraft-v4-styles-vector/" }, "rawModel": { "about": "Recraft V4 Styles Vector is the SVG-producing model in Recraft’s dedicated style-consistent generation line. It turns a text brief into new vector artwork while using a supplied reference style to guide the rendering, colour logic and overall look. It is useful for coordinated icon sets, brand illustration and graphic systems where subjects change but the visual treatment should stay recognisable. The Vector edition returns an editable graphic rather than a raster photograph.\n\nThe producer identifies this edition as recraftv4_styles_vector. Its output is always SVG; raster image_format settings do not convert it into WebP or PNG. Every vector variant accepts the fourteen documented aspect ratios as width-to-height ratios rather than exact pixel sizes. SVG has no fixed pixel resolution, so the standard raster model’s 1K output is not an architectural size for this edition. Choose the desired shape of the asset and the intended small or large display use when preparing the brief.\n\nA style is required for each generation. Use one to ten PNG, JPG or WebP references, or a compatible saved style instead of new references. The producer rejects a request that combines a saved style identifier with style reference images. The documented reference allowance is 64 MB in total and under 20 MB per file. A single clear icon or illustration can establish the treatment; several references are useful when their line weight, corners, fill logic and palette already belong to the same visual system. Each reference must have a shortest side of at least 256 pixels, a longest side of no more than 4,096 pixels and a total resolution of no more than 16 megapixels.\n\nFlexible matching is the default and takes a looser reading of the reference, while precise matching follows its rendering, colour, composition and lighting more closely. For a vector system, use the prompt to define the graphic type, silhouette, object count and layout. For a navigation icon set, use bold rounded outlines, one centred object per image and a two-colour palette. Keep the same reference style and change the named object in each brief, rather than mixing unrelated references to obtain variety.\n\nThe generation reference permits prompts up to 10,000 characters, one to six outputs, a random seed, preferred colours and a desired background colour. Negative prompts, curated style names and the older text_layout control are unsupported. This Styles edition also does not provide image-to-image or inpainting: an image reference supplies a visual language rather than a region to erase or an existing graphic to preserve unchanged. Structural instructions in the positive brief should describe the intended finished asset.\n\nInspect the SVG at the size where it will be used, especially when the design contains lettering, narrow gaps or small details. Colour matching to a reference is not guaranteed, and unrelated references can compete. For an icon set that becomes repetitive, change the object, pose or arrangement in the prompt while retaining the coherent style. The useful deliverable is a consistent vector asset that can be reshaped and recoloured in a design workflow, with its geometry and legibility evaluated against the brief.\n\nThrough Ailoot, select this exact model ID in /v1/images/generations and supply the creative prompt. Retain every returned data entry, whether the response carries a URL or encoded image content, and save the actual bytes with their returned content type. Keep usage and any media task_id with the asset, then review its shapes, lettering and colour regions in the intended design.", "alias_of": null, "aliases": [], "card_routes": [ { "label": "Ultra", "rates": [ { "amount": "0.1", "amount_unit": "usd_per_exact_native_unit", "billing_input": false, "estimate_only": true, "key": "forecast_usd", "label": "Estimated generation cost", "native_amount_usd_per_unit": "0.1", "native_quantity": 1, "public_unit_label": "estimate before generation", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "request_estimate" } ], "summary": "Full configuration pricing in details." } ], "ctx": null, "formats": [ "images" ], "id": "recraft/recraft-v4-styles-vector", "input": [ "text", "image" ], "kind": "image", "max_out": null, "methods": [ { "available": null, "billing_basis": { "basis": "original_invoice_usd", "description": "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.", "forecast_quantity_is_estimate": true, "physical_output_is_billable_quantity": false, "version": "original_invoice_usd_v1" }, "cache_read": null, "cache_write": null, "cache_write_1h": null, "contract": { "data": { "all_results": "Retain the complete response and headers, original identifiers, every actual output and all usage/accounting fields. Save each unique owned asset and retain every role pointing to it.", "authentication": { "header": "Authorization", "scheme": "Bearer", "value": "$AILOOT_API_KEY" }, "control_semantics": { "other_documented_controls": "Source generic image parsing preserves request JSON. Additional documented controls stay subject to the exact model; missing DTO fields do not create Source refusals.", "quality": "The saved common image schema documents this control and says providers without a quality knob ignore it.", "style": "Selected generic Source passes JSON fields through but the saved dedicated image request schema does not declare a style field. Its omission here is not a Source ban or a supported per-model promise." }, "errors": [ { "condition": "A required field, model selector, type or input representation is invalid.", "http_status": 400, "recovery": "Inspect the returned validation detail before preparing a separate request.", "type": "invalid_request_error" }, { "condition": "The original request or result is unknown or requires a check.", "http_status": null, "recovery": "Keep original identifiers and headers; read only supported status/library records. Do not submit creation again.", "type": null } ], "lifecycle": { "assets": [ { "http": "GET", "path": "/v1/media/assets" }, { "http": "GET", "path": "/v1/media/assets/{asset_id}" } ], "cancel_endpoint": null, "create": { "http": "POST", "path": "/v1/images/generations" }, "mode": "synchronous_result_then_owned_library", "operation_id_is_not_task_id": true, "owned_content": { "http": "GET", "path": "/v1/media/assets/{asset_id}/content", "url_source": "Use the exact returned signed URL; never construct a token." }, "status": [ { "http": "GET", "id_source": "actual returned task_id or selected library record; operation_id is a separate identifier", "path": "/v1/media/tasks/{task_id}" } ], "unknown": "Keep the original X-Client-Request-ID, response and headers. An unknown or result_pending_check outcome does not authorize a second creation.", "unknown_no_replay": true }, "material_combinations": [ { "materials": [ "text", "image" ], "metadata_authority": "saved_model_discovery_union", "mode": "reference_guided_image", "reference_maximum": 10, "reference_minimum": 1 } ], "model_parameter_metadata": { "authority": "saved_model_discovery_union", "defaults_not_inferred": { "aspect_ratio": null, "exact_pixels": null, "explanation": "No universal/model default inferred. Omitted output_format uses provider default; dimensions are provider-derived, observed Ming2048 is not a universal default.", "n": null, "output_format": null, "quality": null, "resolution": null }, "known_parameter_choices": { "aspect_ratio": { "type": "enum", "values": [ "1:1", "2:1", "1:2", "3:2", "2:3", "4:3", "3:4", "5:4", "4:5", "16:9", "9:16", "auto" ] }, "input_references": { "max": 10, "min": 1, "type": "range" }, "n": { "max": 6, "min": 1, "type": "range" }, "output_format": { "type": "enum", "values": [ "svg" ] } }, "pointer": "/profiles/13", "scope": "Exact saved model metadata. Discovery unions are identified explicitly and are not represented as definitive selected-provider bounds." }, "outputs": { "all_results": "Retain the complete response and headers, original identifiers, every actual output and all usage/accounting fields. Save each unique owned asset and retain every role pointing to it.", "documented_formats": [ "svg" ], "every_actual_output": true, "family": "image", "fields": [ { "name": "data[].url", "type": "string" }, { "name": "data[].b64_json", "type": "string" }, { "name": "usage", "type": "object" } ], "format": "The exact saved model metadata lists SVG. Preserve the actual returned MIME and unchanged vector bytes; keep every actual output and owned signed image link." }, "parameters": [ { "conditions": "Use this exact Ailoot routing selector.", "default_known": false, "enum": [ "recraft/recraft-v4-styles-vector" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "conditions": "", "default_known": false, "enum_known": false, "name": "prompt", "required": true, "type": "string" }, { "conditions": "", "default_known": false, "enum_known": false, "maximum": 6, "minimum": 1, "name": "n", "required": false, "type": "integer" }, { "conditions": "", "default_known": false, "enum": [ "1:1", "2:1", "1:2", "3:2", "2:3", "4:3", "3:4", "5:4", "4:5", "16:9", "9:16", "auto" ], "enum_known": true, "name": "aspect_ratio", "required": false, "type": "string" }, { "conditions": "", "default_known": false, "enum": [ "svg" ], "enum_known": true, "name": "output_format", "required": false, "type": "string" }, { "conditions": "", "default_known": false, "enum_known": false, "items": { "properties": { "image_url": { "properties": { "url": { "type": "string" } }, "required": [ "url" ], "type": "object" }, "type": { "const": "image_url" } }, "required": [ "type", "image_url" ], "type": "object" }, "maxItems": 10, "minItems": 1, "name": "input_references", "required": true, "type": "array" }, { "conditions": "", "default_known": false, "enum": [ "auto", "low", "medium", "high", "xhigh", "max" ], "enum_known": true, "name": "quality", "required": false, "type": "string" } ], "request_schema": { "additionalProperties": true, "properties": { "aspect_ratio": { "enum": [ "1:1", "2:1", "1:2", "3:2", "2:3", "4:3", "3:4", "5:4", "4:5", "16:9", "9:16", "auto" ], "type": "string" }, "input_references": { "items": { "properties": { "image_url": { "properties": { "url": { "type": "string" } }, "required": [ "url" ], "type": "object" }, "type": { "const": "image_url" } }, "required": [ "type", "image_url" ], "type": "object" }, "maxItems": 10, "minItems": 1, "type": "array" }, "model": { "enum": [ "recraft/recraft-v4-styles-vector" ], "type": "string" }, "n": { "maximum": 6, "minimum": 1, "type": "integer" }, "output_format": { "enum": [ "svg" ], "type": "string" }, "prompt": { "type": "string" }, "quality": { "enum": [ "auto", "low", "medium", "high", "xhigh", "max" ], "type": "string" } }, "required": [ "model", "prompt", "input_references" ], "type": "object" }, "schema_template": { "actual_file_preparation_required": true, "body": { "input_references": [ { "image_url": { "url": "YOUR_ACCESSIBLE_IMAGE_URL" }, "type": "image_url" } ], "model": "recraft/recraft-v4-styles-vector", "prompt": "A portrait of an Asian woman with neon green lights in the background, shallow depth of field." }, "content_type": "application/json", "example_is_offline_content": true }, "usage": { "meter": "Use the accepted method price and actual recorded usage; the request reserve is an estimate. A billing unit does not add an input capability.", "preserve": "Keep all returned usage, accounting and request identifiers with every actual output.", "settlement": "Retain the original operation; reconcile its result and accounting once." } }, "input": { "conditions": [ "Use this exact Ailoot routing selector.", "quality is a common documented control; providers without a quality knob ignore it. No per-model quality improvement is promised." ], "content_type": "application/json", "material_types": [ "text", "image" ], "optional": [ "n", "aspect_ratio", "output_format", "quality" ], "required": [ "model", "prompt", "input_references" ] }, "lifecycle": { "assets": [ { "http": "GET", "path": "/v1/media/assets" }, { "http": "GET", "path": "/v1/media/assets/{asset_id}" } ], "cancel_endpoint": null, "create": { "http": "POST", "path": "/v1/images/generations" }, "mode": "synchronous_result_then_owned_library", "operation_id_is_not_task_id": true, "owned_content": { "http": "GET", "path": "/v1/media/assets/{asset_id}/content", "url_source": "Use the exact returned signed URL; never construct a token." }, "status": [ { "http": "GET", "id_source": "actual returned task_id or selected library record; operation_id is a separate identifier", "path": "/v1/media/tasks/{task_id}" } ], "unknown": "Keep the original X-Client-Request-ID, response and headers. An unknown or result_pending_check outcome does not authorize a second creation.", "unknown_no_replay": true }, "method": { "http": "POST", "path": "/v1/images/generations" }, "method_aliases": [], "output": { "all_results": "Retain the complete response and headers, original identifiers, every actual output and all usage/accounting fields. Save each unique owned asset and retain every role pointing to it.", "documented_formats": [ "svg" ], "every_actual_output": true, "family": "image", "fields": [ { "name": "data[].url", "type": "string" }, { "name": "data[].b64_json", "type": "string" }, { "name": "usage", "type": "object" } ], "format": "The saved exact model metadata lists SVG. Preserve actual MIME and bytes; storage MIME support alone does not prove completion of the full selected generic output path." } }, "ctx": null, "declared_pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] }, { "basis": "Reference estimate only; final charge follows the recorded original invoice.", "dimensions": { "conditions": "Style creation when generating with style references; once per request, in addition to the output-image price.", "quoted_unit": "per request" }, "label": "Input reference", "units": [ { "amount": "0.01", "amount_unit": "usd_per_request", "billing_input": false, "estimate_only": true, "key": "image_input_reference_request", "label": "Input reference", "native_amount_usd_per_unit": "0.01", "native_quantity": 1, "public_unit_label": "per request", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "request" } ] }, { "dimensions": { "quoted_unit": "per output image" }, "label": "output image", "units": [ { "amount": "0.1", "amount_unit": "usd_per_exact_native_unit", "billing_input": false, "estimate_only": true, "key": "image_output", "label": "output image", "native_amount_usd_per_unit": "0.1", "native_quantity": 1, "public_unit_label": "per output image", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "image_output" } ] }, { "basis": "This estimate is not an additional charge or a fixed rate for the completed generation.", "dimensions": { "forecast_quantity": "one generation estimate" }, "label": "Estimated generation cost", "units": [ { "amount": "0.1", "amount_unit": "usd_per_exact_native_unit", "billing_input": false, "estimate_only": true, "key": "forecast_usd", "label": "Estimated generation cost", "native_amount_usd_per_unit": "0.1", "native_quantity": 1, "public_unit_label": "estimate before generation", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "request_estimate" } ] } ], "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\nexport AILOOT_API_KEY\n: \"${AILOOT_IMAGE_URL:?Set an actual customer material or documented value}\"\nexport AILOOT_IMAGE_URL\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"recraft/recraft-v4-styles-vector\", \"prompt\": \"A portrait of an Asian woman with neon green lights in the background, shallow depth of field.\", \"input_references\": [{\"type\": \"image_url\", \"image_url\": {\"url\": \"YOUR_ACCESSIBLE_IMAGE_URL\"}}]}')\np['input_references'][0]['image_url']['url']=os.environ['AILOOT_IMAGE_URL']\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\n# Submit once. Retain the complete result, original identifiers and every response header.\n", "label": "curl · create once and retain the complete result", "language": "bash" } ], "family": "openai", "fast_multiplier": null, "flex_multiplier": null, "fmt": "images", "http": "POST", "in": null, "input": [ "text", "image" ], "input_conditions": { "image": "Use the exact model reference-input range in the saved model metadata; a reference becomes required only for the models whose listed minimum is positive." }, "label": "Images", "max_out": null, "max_reasoning_effort_multiplier": null, "method_aliases": [], "out": null, "output": [ "image" ], "path": "/v1/images/generations", "price_conditions": [ { "label": "Fast mode", "value": "Not specified", "when": "When fast mode is selected" }, { "label": "Flex mode", "value": "Not specified", "when": "When flex mode is selected" }, { "label": "Maximum reasoning effort", "value": "Not specified", "when": "When maximum reasoning effort uses the default adjustment" } ], "pricing": { "billing_mode": "original_invoice_usd", "image_input_price": null, "image_output_price": null }, "pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] }, { "basis": "Reference estimate only; final charge follows the recorded original invoice.", "dimensions": { "conditions": "Style creation when generating with style references; once per request, in addition to the output-image price.", "quoted_unit": "per request" }, "label": "Input reference", "units": [ { "amount": "0.01", "amount_unit": "usd_per_request", "billing_input": false, "estimate_only": true, "key": "image_input_reference_request", "label": "Input reference", "native_amount_usd_per_unit": "0.01", "native_quantity": 1, "public_unit_label": "per request", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "request" } ] }, { "dimensions": { "quoted_unit": "per output image" }, "label": "output image", "units": [ { "amount": "0.1", "amount_unit": "usd_per_exact_native_unit", "billing_input": false, "estimate_only": true, "key": "image_output", "label": "output image", "native_amount_usd_per_unit": "0.1", "native_quantity": 1, "public_unit_label": "per output image", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "image_output" } ] }, { "basis": "This estimate is not an additional charge or a fixed rate for the completed generation.", "dimensions": { "forecast_quantity": "one generation estimate" }, "label": "Estimated generation cost", "units": [ { "amount": "0.1", "amount_unit": "usd_per_exact_native_unit", "billing_input": false, "estimate_only": true, "key": "forecast_usd", "label": "Estimated generation cost", "native_amount_usd_per_unit": "0.1", "native_quantity": 1, "public_unit_label": "estimate before generation", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "request_estimate" } ] } ], "request_model_id": "recraft/recraft-v4-styles-vector", "route_label": "Ultra", "status_reads": [ "GET /v1/media/tasks/{task_id}" ], "tiers": [], "units": [ { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" }, { "amount": "0.01", "amount_unit": "usd_per_request", "billing_input": false, "estimate_only": true, "key": "image_input_reference_request", "label": "Input reference", "native_amount_usd_per_unit": "0.01", "native_quantity": 1, "public_unit_label": "per request", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "request" }, { "amount": "0.1", "amount_unit": "usd_per_exact_native_unit", "billing_input": false, "estimate_only": true, "key": "image_output", "label": "output image", "native_amount_usd_per_unit": "0.1", "native_quantity": 1, "public_unit_label": "per output image", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "image_output" }, { "amount": "0.1", "amount_unit": "usd_per_exact_native_unit", "billing_input": false, "estimate_only": true, "key": "forecast_usd", "label": "Estimated generation cost", "native_amount_usd_per_unit": "0.1", "native_quantity": 1, "public_unit_label": "estimate before generation", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "request_estimate" } ] } ], "model_aliases": [ { "canonical_model_id": "recraft/recraft-v4-styles-vector", "request_model_id": "recraft/recraft-v4-styles-vector", "route_label": "Ultra" } ], "name": "Recraft: Recraft V4 Styles Vector", "price": { "estimate_only": true, "in": null, "in_label": null, "out": 0.1, "out_label": "estimate before generation", "scope_label": "Estimated generation cost", "sort_in": null, "sort_out": 0.1, "varies": false }, "short": "Recraft V4 Styles Vector creates editable SVG graphics from a text brief and a required visual style. It suits coordinated icons, logos and illustrations whose line treatment, palette and rendering should follow the same reference direction.", "title": "Recraft: Recraft V4 Styles Vector" }, "renderer_schema": { "method_order": "Original DTO methods order; every exact route/format/path/caller survives.", "prices": "Original public DTO fields and original native display HTML; no flattened or normalized offers." }, "representation": "exact-public-dto-and-native-renderer-html", "representationNotes": { "current_reference": { "about_json_pointer": "/aboutHtml", "methods": [ { "contract_json_pointer": "/methods/0/rawMethod/contract", "html_json_pointer": "/methods/0/html", "method_ordinal": 0 } ], "role": "current-semantic-reference" }, "raw_input": { "examples_role": "historical-input-not-current-ready-examples", "json_pointers": [ "/rawModel", "/methods/0/rawMethod" ], "role": "historical-owner-input" }, "schema": "ailoot-native-model-representations-v1" }, "schema": "ailoot-static-model-facts-v1", "schema_version": 1, "shortText": "Recraft V4 Styles Vector creates editable SVG graphics from a text brief and a required visual style. It suits coordinated icons, logos and illustrations whose line treatment, palette and rendering should follow the same reference direction.", "source": { "audit_sha256": "2e00086bcbfc28e64d0cebe97aa47c17d8d5618963027f8ffb9dc6123d7d25b1", "bridge_map_sha256": "1125275768b9636fc8461bc7da5061239a81ddfe508e2557843ca42c58ab0036", "raw_model_json_sha256": "cdc5ce0986e55f5e95a9fe4e1d3bd1243ad6a2d0560737b8b04f0fe115c8616d", "renderer_sha256": "fed50305bd3bcc4980ac14df23640efb8c1bc1e819f9d53643d6f43e8974d3fe" }, "sourceRevision": "a7e5eff85c452ba1321f723780978eee2467c30cca5150f34ce4cf3fb646ec4f" }