@evolinkai/mcp 0.0.0-stage → 1.3.0

package/dist/core/src/data/model-params.generated.js

@@ -0,0 +1,3 @@
+// Generated by scripts/build-model-params.mjs from the docs site OpenAPI files. Do not edit by hand.
+export const MODEL_PARAMS_JSON = "{\"meta\":{\"source\":\"mintlify-docs en/api-manual\",\"commit\":\"79a6b56a\",\"files\":198,\"endpoints\":153,\"models\":157},\"models\":{\"MiniMax-Hailuo-02\":{\"model\":\"MiniMax-Hailuo-02\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Hailuo 02 API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/hailuo/hailuo-02-video-generate\",\"required\":[],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing video content and camera motion. Required for T2V, optional for I2V/FLF. Max 2000 characters 15 Camera Commands: Truck: [Truck left], [Truck right]; Pan: [Pan left], [Pan right]; Dolly: [Push in], [Pull out]; Pedestal: [Pedestal up], [Pedestal down]; Tilt: [Tilt up], [Tilt down]; Zoom: [Zoom in], [Zoom out]; Special: [Shake]; Follow: [Tracking shot]; Static: [Static shot] Usage: Combined: Multiple commands in one [] execute simultaneously, e.g. [Pan left,Pedestal up], max 3 recommended; Sequential: Commands execute in text order, e.g. ...slowly [Push in], then quickly [Pull…\",\"maxLength\":2000},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URLs for I2V and FLF modes Mode Detection: 0 images = T2V (Text-to-Video); 1 image = I2V (Image-to-Video); 2 images = FLF (First-Last-Frame transition) Requirements: Image size: max 20MB; Formats: JPG, JPEG, PNG, WebP; Aspect ratio: 2:5 to 5:2; Short edge > 300px FLF Note: Video resolution follows first frame, last frame will be cropped to match\",\"maxItems\":2,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution Supported by mode: I2V: 512p, 768p, 1080p; T2V: 768p, 1080p; FLF: 768p, 1080p Duration & Resolution: 512p: 6s, 10s; 768p: 6s, 10s; 1080p: 6s only Note: 512p only available in I2V mode\",\"enum\":[\"512p\",\"768p\",\"1080p\"],\"default\":\"768p\"},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds); 6 seconds (default); 10 seconds (not available for 1080p)\",\"enum\":[6,10],\"default\":6},\"model_params\":{\"type\":\"object\",\"description\":\"Model-specific parameters\",\"properties\":{\"prompt_optimizer\":{\"type\":\"boolean\",\"description\":\"Auto-optimize prompt. Set false for precise control\",\"default\":true},\"fast_pretreatment\":{\"type\":\"boolean\",\"description\":\"Enable fast preprocessing to reduce optimization time\",\"default\":false}}}},\"example\":{\"prompt\":\"A beautiful sunset over the ocean [Static shot]\"}},\"MiniMax-Hailuo-2.3\":{\"model\":\"MiniMax-Hailuo-2.3\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Hailuo 2.3 API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/hailuo/hailuo-2-3-video-generate\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing video content and camera motion. Required for T2V, optional for I2V. Max 2000 characters 15 Camera Commands: Truck: [Truck left], [Truck right]; Pan: [Pan left], [Pan right]; Dolly: [Push in], [Pull out]; Pedestal: [Pedestal up], [Pedestal down]; Tilt: [Tilt up], [Tilt down]; Zoom: [Zoom in], [Zoom out]; Special: [Shake]; Follow: [Tracking shot]; Static: [Static shot] Usage: Combined: Multiple commands in one [] execute simultaneously, e.g. [Pan left,Pedestal up], max 3 recommended; Sequential: Commands execute in text order, e.g. ...slowly [Push in], then quickly [Pull out]\",\"maxLength\":2000,\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URLs for I2V mode, optional Mode Detection: 0 images = T2V (Text-to-Video); 1 image = I2V (Image-to-Video) Requirements: Image size: max 20MB; Formats: JPG, JPEG, PNG, WebP; Aspect ratio: 2:5 to 5:2; Short edge > 300px\",\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution Supported by mode: I2V: 768p, 1080p; T2V: 768p, 1080p Duration & Resolution: 768p: 6s, 10s; 1080p: 6s only\",\"enum\":[\"768p\",\"1080p\"],\"default\":\"768p\"},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds); 6 seconds (default); 10 seconds (not available for 1080p)\",\"enum\":[6,10],\"default\":6},\"model_params\":{\"type\":\"object\",\"description\":\"Model-specific parameters\",\"properties\":{\"prompt_optimizer\":{\"type\":\"boolean\",\"description\":\"Auto-optimize prompt. Set false for precise control\",\"default\":true},\"fast_pretreatment\":{\"type\":\"boolean\",\"description\":\"Enable fast preprocessing to reduce optimization time\",\"default\":false}}}},\"example\":{\"prompt\":\"A beautiful sunset over the ocean [Static shot]\"}},\"MiniMax-Hailuo-2.3-Fast\":{\"model\":\"MiniMax-Hailuo-2.3-Fast\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Hailuo 2.3 Fast API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/hailuo/hailuo-2-3-fast-video-generate\",\"required\":[\"image_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing motion and camera movement, optional. Max 2000 characters 15 Camera Commands: Truck: [Truck left], [Truck right]; Pan: [Pan left], [Pan right]; Dolly: [Push in], [Pull out]; Pedestal: [Pedestal up], [Pedestal down]; Tilt: [Tilt up], [Tilt down]; Zoom: [Zoom in], [Zoom out]; Special: [Shake]; Follow: [Tracking shot]; Static: [Static shot] Usage: Combined: Multiple commands in one [] execute simultaneously, e.g. [Pan left,Pedestal up], max 3 recommended; Sequential: Commands execute in text order, e.g. ...slowly [Push in], then quickly [Pull out]\",\"maxLength\":2000},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL for I2V mode, required for Hailuo 2.3 Fast Requirements: Must provide 1 image; Image size: max 20MB; Formats: JPG, JPEG, PNG, WebP; Aspect ratio: 2:5 to 5:2; Short edge > 300px\",\"minItems\":1,\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution I2V supported: 768p (default); 1080p Duration & Resolution: 768p: 6s, 10s; 1080p: 6s only\",\"enum\":[\"768p\",\"1080p\"],\"default\":\"768p\"},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds); 6 seconds (default); 10 seconds (not available for 1080p)\",\"enum\":[6,10],\"default\":6},\"model_params\":{\"type\":\"object\",\"description\":\"Model-specific parameters\",\"properties\":{\"prompt_optimizer\":{\"type\":\"boolean\",\"description\":\"Auto-optimize prompt. Set false for precise control\",\"default\":true}}}},\"example\":{\"prompt\":\"A cat slowly opens its eyes and looks around [Pan left]\",\"image_urls\":[\"https://example.com/image.jpg\"]}},\"doubao-seed-audio-1-0\":{\"model\":\"doubao-seed-audio-1-0\",\"kind\":\"audio\",\"path\":\"/v1/audios/generations\",\"title\":\"Seed-Audio 1.0 Audio Generation\",\"docs\":\"https://evolink.ai/docs/en/api-manual/audio-series/doubao-seed-audio/doubao-seed-audio-1-0\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"The prompt or text to synthesize into audio Three generation modes (auto-detected by which reference resources you pass): Text-to-audio: pass only prompt to generate audio directly from the prompt; Reference-audio (voice cloning): pair with audio_references; use the literal marker @audioN to reference the Nth item (numbered from 1, in array order); Reference-image: pair with image_urls; prompt only needs the text to synthesize > Audio references (audio_references) and image references (image_urls) are mutually exclusive — only one may be used per request. Constraints: Up to 1500 characters\",\"maxLength\":1500,\"required\":true},\"audio_references\":{\"type\":\"array\",\"description\":\"List of reference resources. Each item can be a voice ID or a reference-audio URL, and the two may be mixed within the same array; Voice ID: the voice_type of a preset voice — see the full list in [Seed-Audio 1.0 Voice List](/en/api-manual/audio-series/doubao-seed-audio/doubao-seed-audio-1-0-voices); Audio URL: upload a reference audio clip for voice cloning; Mutually exclusive with image_urls: reference audio and reference image are either-or; they cannot be sent together in one request; Use the literal marker @audioN in prompt to reference the Nth item (numbered from 1, in array order); If…\",\"maxItems\":3,\"items\":{\"type\":\"string\"}},\"image_urls\":{\"type\":\"array\",\"description\":\"List of reference-image URLs; generates audio matching the mood of the image; When using an image reference, prompt only needs the text to synthesize; Mutually exclusive with audio_references: reference image and reference audio are either-or; they cannot be sent together in one request Constraints: Currently only 1 image, ≤ 10 MB; Formats: jpeg / png / webp\",\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"format\":{\"type\":\"string\",\"description\":\"Output audio format\",\"enum\":[\"wav\",\"mp3\",\"pcm\",\"ogg_opus\"],\"default\":\"wav\"},\"sample_rate\":{\"type\":\"integer\",\"description\":\"Output sample rate (Hz)\",\"enum\":[8000,16000,24000,32000,44100,48000],\"default\":24000},\"speech_rate\":{\"type\":\"number\",\"description\":\"Speech-rate multiplier (supports two decimal places); 1.0: normal speed (default); 2.0: 2x speed; 0.5: half speed Range 0.5 to 2.0\",\"default\":1,\"minimum\":0.5,\"maximum\":2},\"loudness_rate\":{\"type\":\"number\",\"description\":\"Loudness multiplier (supports two decimal places); 1.0: normal loudness (default); 2.0: 2x loudness; 0.5: half loudness Range 0.5 to 2.0\",\"default\":1,\"minimum\":0.5,\"maximum\":2},\"pitch_rate\":{\"type\":\"integer\",\"description\":\"Pitch adjustment, in semitones; 0: default pitch (no change); Positive values raise the pitch: the larger the value, the higher and sharper the voice; 12 raises it by one octave; Negative values lower the pitch: the smaller the value, the lower and deeper the voice; -12 lowers it by one octave Range -12 to 12\",\"default\":0,\"minimum\":-12,\"maximum\":12}},\"example\":{\"prompt\":\"Welcome to the audio generation service. The weather is lovely today.\",\"format\":\"mp3\"}},\"doubao-seedance-1.0-pro-fast\":{\"model\":\"doubao-seedance-1.0-pro-fast\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"doubao-seedance-1.0-pro-fast API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/seedance1.0/seedance-1.0-pro-fast-video-generate\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the video you want to generate, limited to 2000 tokens\",\"maxLength\":2000,\"required\":true},\"duration\":{\"type\":\"integer\",\"description\":\"Specifies the duration of the generated video (in seconds), defaults to 5 seconds Note: Supports any integer value between 2 and 12 seconds; Billing for a single request is based on the duration value; longer durations result in higher costs\",\"minimum\":2,\"maximum\":12},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution, defaults to 1080p Note: 480p: Lower resolution, lower pricing; 720p: Standard definition, standard pricing; 1080p: High definition, higher pricing, this is the default value\",\"enum\":[\"480p\",\"720p\",\"1080p\"]},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio Text-to-video mode: Default value: 16:9; Supported values: 16:9 (landscape), 9:16 (portrait), 1:1 (square), 4:3, 3:4, 21:9 (ultra-wide) Image-to-video mode (when using image_urls): Default value: adaptive; Supported values: In addition to the above 6 ratios, also supports keep_ratio (keep original aspect ratio) and adaptive (adaptive)\"},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL list for image-to-video functionality Note: Number of images supported per request: 1 image; Image size: Not exceeding 10MB; Supported file formats: .jpg, .jpeg, .png, .webp; Image URLs must be directly viewable by the server, or the URL should trigger a direct download when accessed (typically these URLs end with image extensions like .png, .jpg)\",\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"}}},\"example\":{\"prompt\":\"A cat playing piano\"}},\"doubao-seedream-4.0\":{\"model\":\"doubao-seedream-4.0\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"doubao-seedream-4.0 Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/seedream/seedream-4.0-image-generate\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the image to be generated, or describing how to edit the input image, limited to 2000 tokens\",\"maxLength\":2000,\"required\":true},\"n\":{\"type\":\"integer\",\"description\":\"Specifies the upper limit for the number of images to generate, supports any integer value between [1,15] Note: If you need to generate multiple images, please include in the prompt: \\\" generate 2 different images \\\" or similar instructions; Reference image count + final generated image count ≤ 15; If: reference image count + required images in prompt > 15, and required images in prompt ≤ parameter n value, then final generated image count = 15 - reference image count; Single request will pre-charge based on the value of n, actual billing is based on the number of images generated\"},\"size\":{\"type\":\"string\",\"description\":\"Size of generated image, supports two formats: Method 1 - Ratio format: auto, 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9, 9:21; Works with the quality parameter to automatically generate an image at the corresponding aspect ratio and resolution, without manually specifying pixels Method 2 - Pixel format: Width x height, e.g.: 1280x720, 1024x1024, 4096x4096; Total pixel range: [921600, 16777216]; Aspect ratio range: [1/16, 16]\",\"default\":\"auto\"},\"quality\":{\"type\":\"string\",\"description\":\"Resolution tier, used with the ratio format of size. | Aspect ratio | 1K | 2K | 4K | |---|---|---|---| | 1:1 | 1024×1024 | 2048×2048 | 4096×4096 | | 2:3 | 832×1248 | 1664×2496 | 3328×4992 | | 3:2 | 1248×832 | 2496×1664 | 4992×3328 | | 3:4 | 864×1152 | 1728×2304 | 3520×4704 | | 4:3 | 1152×864 | 2304×1728 | 4704×3520 | | 4:5 | 896×1120 | 1792×2240 | 3584×4480 | | 5:4 | 1120×896 | 2240×1792 | 4480×3584 | | 9:16 | 720×1280 | 1600×2848 | 3040×5504 | | 16:9 | 1280×720 | 2848×1600 | 5504×3040 | | 21:9 | 1512×648 | 3136×1344 | 6240×2656 | | 9:21 | 648×1512 | 1344×3136 | 2656×6240 |\",\"enum\":[\"1K\",\"2K\",\"4K\"],\"default\":\"2K\"},\"prompt_priority\":{\"type\":\"string\",\"description\":\"Prompt optimization strategy for setting the mode of prompt optimization function Options: standard: Standard mode, higher quality output, longer processing time; fast: Fast mode, faster generation speed, average quality\",\"enum\":[\"standard\",\"fast\"],\"default\":\"standard\"},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL list for image-to-image and image editing functions Note: Maximum number of input images per request: 14; Image size: not exceeding 10MB; Supported image formats: .jpeg, .jpg, .png, .webp, .bmp, .tiff, .gif; Aspect ratio (width/height) range: [1/16, 16]; Width/height (px) > 14; Total pixels: not exceeding 6000×6000; Image URLs must be directly accessible by the server, or the image URL should directly download when accessed (typically these URLs end with image file extensions, such as .png, .jpg)\",\"maxItems\":14,\"items\":{\"type\":\"string\",\"format\":\"uri\"}}},\"example\":{\"prompt\":\"A serene lake reflecting the beautiful sunset scenery\",\"size\":\"16:9\",\"quality\":\"2K\"}},\"doubao-seedream-4.5\":{\"model\":\"doubao-seedream-4.5\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"doubao-seedream-4.5 Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/seedream/seedream-4.5-image-generate\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the image you want to generate, or describing how to edit the input image, limited to 2000 tokens\",\"maxLength\":2000,\"required\":true},\"n\":{\"type\":\"integer\",\"description\":\"Maximum number of images to generate, supports any integer value between [1,15] Note: To generate multiple images, include prompts like: \\\"generate 2 different images\\\" in your prompt; Reference image count + final generated image count ≤ 15 images; If: reference image count + images requested in prompt > 15, and images requested in prompt ≤ parameter n value, then final generated images = 15 - reference image count; Each request will pre-charge based on the value of n, actual charges based on the number of images generated\"},\"size\":{\"type\":\"string\",\"description\":\"Size of generated image, supports two formats: Method 1 - Ratio format: auto, 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9, 9:21; Works with the quality parameter to automatically generate an image at the corresponding aspect ratio and resolution, without manually specifying pixels Method 2 - Pixel format: Width x height, e.g.: 2560x1440, 2048x2048, 4096x4096; Total pixel range: [3686400, 16777216]; Aspect ratio range: [1/16, 16]\",\"default\":\"auto\"},\"quality\":{\"type\":\"string\",\"description\":\"Resolution tier, used with the ratio format of size. | Aspect ratio | 2K | 4K | |---|---|---| | 1:1 | 2048×2048 | 4096×4096 | | 2:3 | 1664×2496 | 3328×4992 | | 3:2 | 2496×1664 | 4992×3328 | | 3:4 | 1728×2304 | 3520×4704 | | 4:3 | 2304×1728 | 4704×3520 | | 4:5 | 1792×2240 | 3584×4480 | | 5:4 | 2240×1792 | 4480×3584 | | 9:16 | 1600×2848 | 3040×5504 | | 16:9 | 2848×1600 | 5504×3040 | | 21:9 | 3136×1344 | 6240×2656 | | 9:21 | 1344×3136 | 2656×6240 |\",\"enum\":[\"2K\",\"4K\"],\"default\":\"2K\"},\"prompt_priority\":{\"type\":\"string\",\"description\":\"Prompt optimization strategy, used to set the mode for prompt optimization Options: standard: Standard mode, higher quality output, longer processing time\",\"enum\":[\"standard\"],\"default\":\"standard\"},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL list for image-to-image and image editing features Note: Single request supports input image quantity: 14 images; Image size: no more than 10MB; Supported image formats: .jpeg, .jpg, .png, .webp, .bmp, .tiff, .gif; Aspect ratio (width/height) range: [1/16, 16]; Width and height (px) > 14; Total pixels: no more than 6000×6000; Image URLs must be directly viewable by the server, or the image URL should trigger direct download when accessed (typically these URLs end with image file extensions, such as .png, .jpg)\",\"maxItems\":14,\"items\":{\"type\":\"string\",\"format\":\"uri\"}}},\"example\":{\"prompt\":\"A serene lake reflecting the beautiful sunset\",\"size\":\"16:9\",\"quality\":\"2K\"}},\"doubao-seedream-5.0-flash\":{\"model\":\"doubao-seedream-5.0-flash\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"doubao-seedream-5.0-flash Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/seedream/seedream-5.0-flash-image-generate\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the image you want to generate, or describing how to edit the input image Language support: In addition to Chinese and English, Seedream 5.0 Flash also supports Russian, Arabic, Filipino, Thai, Turkish, Korean, Malay, Spanish, Portuguese, Indonesian, French, German, Vietnamese and Japanese. Length limit: Up to 4000 tokens (about 2,600 Chinese characters or 5,000 English words); exceeding it returns 400 and is not billed. Recommendation: Keep prompts under 300 Chinese characters or 600 English words. A longer prompt still fits the limit but dilutes the information, and the mo…\",\"required\":true},\"size\":{\"type\":\"string\",\"description\":\"Size of generated image, supports two formats: Method 1 - Ratio format: auto, 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9, 9:21; Works with the quality parameter to automatically generate an image at the corresponding aspect ratio and resolution, without manually specifying pixels Method 2 - Pixel format: Width x height, e.g.: 1024x1024, 2048x2048; Total pixel range: [921600, 4624220]; Aspect ratio range: [1/16, 16]; Both width and height must be greater than 14px Defaults to auto when size is omitted. auto means no explicit ratio: the model decides the composition from the prompt, an…\",\"default\":\"auto\"},\"quality\":{\"type\":\"string\",\"description\":\"Resolution tier, used with the ratio format of size, defaults to 1K. | Aspect ratio | 1K | 1.5K | 2K | |---|---|---|---| | 1:1 | 1024×1024 | 1536×1536 | 2048×2048 | | 2:3 | 832×1248 | 1248×1872 | 1664×2496 | | 3:2 | 1248×832 | 1872×1248 | 2496×1664 | | 3:4 | 864×1152 | 1344×1792 | 1776×2368 | | 4:3 | 1152×864 | 1792×1344 | 2368×1776 | | 4:5 | 896×1120 | 1344×1680 | 1792×2240 | | 5:4 | 1120×896 | 1680×1344 | 2240×1792 | | 9:16 | 800×1424 | 1152×2048 | 1584×2816 | | 16:9 | 1424×800 | 2048×1152 | 2816×1584 | | 21:9 | 1568×672 | 2352×1008 | 3136×1344 | | 9:21 | 672×1568 | 1008×2352 | 1344×3136 |…\",\"enum\":[\"1K\",\"1.5K\",\"2K\"],\"default\":\"1K\"},\"prompt_priority\":{\"type\":\"string\",\"description\":\"Prompt optimization strategy, used to set the prompt optimization mode Options: standard: Standard mode Note: Seedream 5.0 Flash only supports standard; passing fast returns 400. Flash already provides faster generation and does not offer a separate fast mode.\",\"enum\":[\"standard\"],\"default\":\"standard\"},\"image_urls\":{\"type\":\"array\",\"description\":\"List of reference image URLs for image-to-image generation and image editing Notes: Reference images are free; Up to 10 input images per request; Image size: no more than 30MB; Supported formats: .jpeg, .jpg, .png, .webp, .bmp, .tiff, .gif, .heic, .heif; Aspect ratio (width/height): [1/16, 16]; Both width and height must be greater than 14px; Total pixels: [196, 6000×6000]; Image URLs must be directly accessible to the server or trigger a direct download when accessed (such URLs typically end in an image extension such as .png or .jpg)\",\"maxItems\":10,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"output_format\":{\"type\":\"string\",\"description\":\"Output image format Options: png: PNG format; jpeg: JPEG format Note: With background=transparent, output is always png: omitting output_format automatically selects png, while specifying jpeg is rejected.\",\"enum\":[\"png\",\"jpeg\"],\"default\":\"jpeg\"},\"watermark\":{\"type\":\"boolean\",\"description\":\"Whether to add a watermark to the generated image\",\"default\":false},\"background\":{\"type\":\"string\",\"description\":\"Transparency channel setting Options: opaque: Standard opaque background (default); transparent: Preserve the existing alpha channel of the input image > transparent preserves the input image’s existing transparent background; it does not remove the background. Restrictions (only for transparent): Exactly 1 input image is required; The input must be a PNG with at least one transparent pixel; webp, jpeg, other formats, or PNG files without transparent pixels are rejected by the model (failed tasks are fully refunded); Output is always png: omitting output_format automatically selects png, whil…\",\"enum\":[\"opaque\",\"transparent\"],\"default\":\"opaque\"}},\"example\":{\"prompt\":\"A serene lake reflecting the beautiful sunset\",\"size\":\"16:9\",\"quality\":\"2K\"}},\"doubao-seedream-5.0-flash-layerize\":{\"model\":\"doubao-seedream-5.0-flash-layerize\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"doubao-seedream-5.0-flash-layerize Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/seedream/seedream-5.0-flash-layerize-image-generate\",\"required\":[\"image_urls\"],\"params\":{\"image_urls\":{\"type\":\"array\",\"description\":\"URL of the image to decompose (required) Note: Exactly 1 image is required; omitting it or passing 2 or more returns an error; Supported formats: .png, .jpeg, .jpg (stricter than plain generation — webp and others are rejected); Image size: no more than 30MB; Total pixels: [262144, 6000×6000], i.e. at least 512×512 (a higher lower bound than plain generation); Aspect ratio (width/height) range: [1/16, 16]; The image URL must be directly viewable by the server, or the URL must trigger a direct download when accessed (usually such URLs end with an image file extension, such as .png, .jpg)\",\"minItems\":1,\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"prompt\":{\"type\":\"string\",\"description\":\"Which elements to split out (optional) Three ways to use it: Omit it: the model detects every major element in the image and splits them one by one; Natural language: e.g. Split out the parrot and the title text — elements are identified semantically and turned into layers; Exact coordinates: use <bbox> tags to pin down a position, e.g. title text<bbox>179 58 809 197</bbox>; normalized coordinates (0~1000) are recommended\"},\"quality\":{\"type\":\"string\",\"description\":\"Output resolution tier, defaults to auto Options: auto, 1K, 1.5K, 2K Notes: Layer mode only accepts tiers; passing a ratio (such as 16:9) or explicit pixels (such as 2048x2048) returns an error; auto makes the output follow the input image: if the original size falls within [921600, 4624220] pixels it is kept as is, below 1K it is output at 1K, above 2K it is output at 2K; Each layer keeps its own aspect ratio from the original image, and the base image keeps the aspect ratio of the input Billing: Billed per image regardless of resolution tier; 1K, 1.5K, 2K, and auto cost the same.\",\"enum\":[\"auto\",\"1K\",\"1.5K\",\"2K\"],\"default\":\"auto\"},\"prompt_priority\":{\"type\":\"string\",\"description\":\"Prompt optimization strategy, used to set the prompt optimization mode Options: standard: Standard mode Note: Seedream 5.0 Flash only supports standard; passing fast returns 400. Flash already provides faster generation and does not offer a separate fast mode.\",\"enum\":[\"standard\"],\"default\":\"standard\"},\"output_format\":{\"type\":\"string\",\"description\":\"Output image format Options: jpeg: JPEG format (default); png: PNG format Note: This parameter only controls the base image. The layers are always PNG with an alpha channel and are not affected by it.\",\"enum\":[\"jpeg\",\"png\"],\"default\":\"jpeg\"}},\"example\":{\"image_urls\":[\"https://example.com/poster.png\"],\"quality\":\"auto\",\"output_format\":\"jpeg\"}},\"doubao-seedream-5.0-lite\":{\"model\":\"doubao-seedream-5.0-lite\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"doubao-seedream-5.0-lite Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/seedream/seedream-5.0-lite-image-generate\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the image you want to generate, or describing how to edit the input image, limited to 2000 tokens\",\"maxLength\":2000,\"required\":true},\"n\":{\"type\":\"integer\",\"description\":\"Maximum number of images to generate, supports any integer value between [1,15] Note: To generate multiple images, include prompts like: \\\"generate 2 different images\\\" in your prompt; Reference image count + final generated image count ≤ 15 images; If: reference image count + images requested in prompt > 15, and images requested in prompt ≤ parameter n value, then final generated images = 15 - reference image count; Each request will pre-charge based on the value of n, actual charges based on the number of images generated\"},\"size\":{\"type\":\"string\",\"description\":\"Size of generated image, supports two formats: Method 1 - Ratio format: auto, 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9, 9:21; Works with the quality parameter to automatically generate an image at the corresponding aspect ratio and resolution, without manually specifying pixels Method 2 - Pixel format: Width x height, e.g.: 2560x1440, 2048x2048, 4096x4096; Total pixel range: [3686400, 16777216]; Aspect ratio range: [1/16, 16]\",\"default\":\"auto\"},\"quality\":{\"type\":\"string\",\"description\":\"Resolution tier, used with the ratio format of size. | Aspect ratio | 2K | 3K | 4K | |---|---|---|---| | 1:1 | 2048×2048 | 3072×3072 | 4096×4096 | | 2:3 | 1664×2496 | 2496×3744 | 3328×4992 | | 3:2 | 2496×1664 | 3744×2496 | 4992×3328 | | 3:4 | 1728×2304 | 2592×3456 | 3520×4704 | | 4:3 | 2304×1728 | 3456×2592 | 4704×3520 | | 4:5 | 1792×2240 | 2688×3360 | 3584×4480 | | 5:4 | 2240×1792 | 3360×2688 | 4480×3584 | | 9:16 | 1600×2848 | 2304×4096 | 3040×5504 | | 16:9 | 2848×1600 | 4096×2304 | 5504×3040 | | 21:9 | 3136×1344 | 4704×2016 | 6240×2656 | | 9:21 | 1344×3136 | 2016×4704 | 2656×6240 |\",\"enum\":[\"2K\",\"3K\",\"4K\"],\"default\":\"2K\"},\"prompt_priority\":{\"type\":\"string\",\"description\":\"Prompt optimization strategy, used to set the mode for prompt optimization Options: standard: Standard mode, higher quality output, longer processing time\",\"enum\":[\"standard\"],\"default\":\"standard\"},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL list for image-to-image and image editing features Note: Single request supports input image quantity: 14 images; Image size: no more than 10MB; Supported image formats: .jpeg, .jpg, .png, .webp, .bmp, .tiff, .gif; Aspect ratio (width/height) range: [1/16, 16]; Width and height (px) > 14; Total pixels: no more than 6000×6000; Image URLs must be directly viewable by the server, or the image URL should trigger direct download when accessed (typically these URLs end with image file extensions, such as .png, .jpg)\",\"maxItems\":14,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"model_params\":{\"type\":\"object\",\"description\":\"Supported parameters: output_format: Output image format; tools: Web search tool\",\"properties\":{\"output_format\":{\"type\":\"string\",\"description\":\"Output image format Options: png: PNG format; jpeg: JPEG format\",\"enum\":[\"png\",\"jpeg\"],\"default\":\"jpeg\"},\"tools\":{\"type\":\"array\",\"description\":\"Web search tool. When enabled, the model will automatically decide whether to search based on the prompt. Search will incur additional charges Format: [{\\\"type\\\": \\\"web_search\\\"}]\",\"items\":{\"type\":\"object\",\"properties\":{\"type\":{\"type\":\"string\",\"description\":\"Tool type\",\"enum\":[\"web_search\"],\"required\":true}}}}}}},\"example\":{\"prompt\":\"Generate an illustration of the latest fashion trends from Paris Fashion Week 2025\",\"size\":\"3:4\",\"quality\":\"2K\",\"model_params\":{\"tools\":[{\"type\":\"web_search\"}]}}},\"doubao-seedream-5.0-pro\":{\"model\":\"doubao-seedream-5.0-pro\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"doubao-seedream-5.0-pro Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/seedream/seedream-5.0-pro-image-generate\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the image you want to generate, or describing how to edit the input image Language support: In addition to Chinese and English, Seedream 5.0 Pro also supports Russian, Arabic, Filipino, Thai, Turkish, Korean, Malay, Spanish, Portuguese, Indonesian, French, German, Vietnamese and Japanese. Length limit: Up to 4000 tokens (about 2,600 Chinese characters or 5,000 English words); exceeding it returns 400 and is not billed. Recommendation: Keep prompts under 300 Chinese characters or 600 English words. A longer prompt still fits the limit but dilutes the information, and the mode…\",\"required\":true},\"size\":{\"type\":\"string\",\"description\":\"Size of generated image, supports two formats: Method 1 - Ratio format: auto, 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9, 9:21; Works with the quality parameter to automatically generate an image at the corresponding aspect ratio and resolution, without manually specifying pixels Method 2 - Pixel format: Width x height, e.g.: 1024x1024, 2048x2048; Total pixel range: [921600, 4624220]; Aspect ratio range: [1/16, 16]; Both width and height must be greater than 14px Defaults to auto when size is omitted. auto means no explicit ratio: the model decides the composition from the prompt, an…\",\"default\":\"auto\"},\"quality\":{\"type\":\"string\",\"description\":\"Resolution tier, used with the ratio format of size, defaults to 1K. | Aspect ratio | 1K | 1.5K | 2K | |---|---|---|---| | 1:1 | 1024×1024 | 1536×1536 | 2048×2048 | | 2:3 | 832×1248 | 1248×1872 | 1664×2496 | | 3:2 | 1248×832 | 1872×1248 | 2496×1664 | | 3:4 | 864×1152 | 1344×1792 | 1776×2368 | | 4:3 | 1152×864 | 1792×1344 | 2368×1776 | | 4:5 | 896×1120 | 1344×1680 | 1792×2240 | | 5:4 | 1120×896 | 1680×1344 | 2240×1792 | | 9:16 | 800×1424 | 1152×2048 | 1584×2816 | | 16:9 | 1424×800 | 2048×1152 | 2816×1584 | | 21:9 | 1568×672 | 2352×1008 | 3136×1344 | | 9:21 | 672×1568 | 1008×2352 | 1344×3136 |…\",\"enum\":[\"1K\",\"1.5K\",\"2K\"],\"default\":\"1K\"},\"prompt_priority\":{\"type\":\"string\",\"description\":\"Prompt optimization strategy, used to set the mode for prompt optimization Options: standard: Standard mode, higher quality output, longer processing time; fast: Fast mode, shorter processing time, slightly lower quality than standard mode\",\"enum\":[\"standard\",\"fast\"],\"default\":\"standard\"},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL list for image-to-image and image editing features Note: Single request supports input image quantity: 10 images; Image size: no more than 30MB; Supported image formats: .jpeg, .jpg, .png, .webp, .bmp, .tiff, .gif, .heic, .heif; Aspect ratio (width/height) range: [1/16, 16]; Width and height (px) > 14; Total pixels: [196, 6000×6000]; Image URLs must be directly viewable by the server, or the image URL should trigger direct download when accessed (typically these URLs end with image file extensions, such as .png, .jpg)\",\"maxItems\":10,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"output_format\":{\"type\":\"string\",\"description\":\"Output image format Options: png: PNG format; jpeg: JPEG format Note: When background=transparent is set, the output is always png; passing output_format=jpeg at the same time is rejected.\",\"enum\":[\"png\",\"jpeg\"],\"default\":\"jpeg\"},\"watermark\":{\"type\":\"boolean\",\"description\":\"Whether to add a watermark to the generated image\",\"default\":false},\"background\":{\"type\":\"string\",\"description\":\"Transparency switch Options: opaque: Regular solid background (default); transparent: Preserve the alpha channel the input image already has > transparent preserves the transparent background of the input image — it does not cut out the subject or remove the background. Limits (apply to transparent only): Exactly one input image must be supplied, and it must have an alpha channel; The output is always png; passing output_format=jpeg at the same time is rejected; Input images in formats without alpha support (such as jpeg) are rejected by the model\",\"enum\":[\"opaque\",\"transparent\"],\"default\":\"opaque\"}},\"example\":{\"prompt\":\"A serene lake reflecting the beautiful sunset\",\"size\":\"16:9\",\"quality\":\"2K\"}},\"doubao-seedream-5.0-pro-layerize\":{\"model\":\"doubao-seedream-5.0-pro-layerize\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"doubao-seedream-5.0-pro-layerize Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/seedream/seedream-5.0-pro-layerize-image-generate\",\"required\":[\"image_urls\"],\"params\":{\"image_urls\":{\"type\":\"array\",\"description\":\"URL of the image to decompose (required) Note: Exactly 1 image is required; omitting it or passing 2 or more returns an error; Supported formats: .png, .jpeg, .jpg (stricter than plain generation — webp and others are rejected); Image size: no more than 30MB; Total pixels: [262144, 6000×6000], i.e. at least 512×512 (a higher lower bound than plain generation); Aspect ratio (width/height) range: [1/16, 16]; The image URL must be directly viewable by the server, or the URL must trigger a direct download when accessed (usually such URLs end with an image file extension, such as .png, .jpg)\",\"minItems\":1,\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"prompt\":{\"type\":\"string\",\"description\":\"Which elements to split out (optional) Three ways to use it: Omit it: the model detects every major element in the image and splits them one by one; Natural language: e.g. Split out the parrot and the title text — elements are identified semantically and turned into layers; Exact coordinates: use <bbox> tags to pin down a position, e.g. title text<bbox>179 58 809 197</bbox>; normalized coordinates (0~1000) are recommended\"},\"quality\":{\"type\":\"string\",\"description\":\"Output resolution tier, defaults to auto Options: auto, 1K, 1.5K, 2K Notes: Layer mode only accepts tiers; passing a ratio (such as 16:9) or explicit pixels (such as 2048x2048) returns an error; auto makes the output follow the input image: if the original size falls within [921600, 4624220] pixels it is kept as is, below 1K it is output at 1K, above 2K it is output at 2K; Each layer keeps its own aspect ratio from the original image, and the base image keeps the aspect ratio of the input Billing: the tier is decided per output image from its own pixel count; 1K and 1.5K cost the same, and an…\",\"enum\":[\"auto\",\"1K\",\"1.5K\",\"2K\"],\"default\":\"auto\"},\"prompt_priority\":{\"type\":\"string\",\"description\":\"Prompt optimization strategy, used to set the mode for prompt optimization Options: standard: Standard mode, higher quality output, longer processing time; fast: Fast mode, shorter processing time, slightly lower quality than standard mode\",\"enum\":[\"standard\",\"fast\"],\"default\":\"standard\"},\"output_format\":{\"type\":\"string\",\"description\":\"Output image format Options: jpeg: JPEG format (default); png: PNG format Note: This parameter only controls the base image. The layers are always PNG with an alpha channel and are not affected by it.\",\"enum\":[\"jpeg\",\"png\"],\"default\":\"jpeg\"}},\"example\":{\"image_urls\":[\"https://example.com/poster.png\"],\"quality\":\"auto\",\"output_format\":\"jpeg\"}},\"gemini-3-pro-image-preview\":{\"model\":\"gemini-3-pro-image-preview\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"Nano Banana Pro Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/nanobanana/nanobanana-pro-image-generate\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the image to be generated, or describing how to edit the input image, limited to 2000 tokens\",\"maxLength\":2000,\"required\":true},\"size\":{\"type\":\"string\",\"description\":\"Aspect ratio of the generated image, default is auto\",\"enum\":[\"auto\",\"1:1\",\"2:3\",\"3:2\",\"3:4\",\"4:3\",\"4:5\",\"5:4\",\"9:16\",\"16:9\",\"21:9\"]},\"quality\":{\"type\":\"string\",\"description\":\"Quality of the generated image, default is 2K Note: 4K quality will incur additional charges\",\"enum\":[\"1K\",\"2K\",\"4K\"]},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL list for image-to-image and image editing functions Note: Maximum number of input images per request: 14; Image size: not exceeding 20MB; Supported file formats: .jpeg, .jpg, .png, .webp; Image URLs must be directly accessible by the server, or the image URL should directly download when accessed (typically these URLs end with image file extensions, such as .png, .jpg); Maximum of 5 real person images can be uploaded\",\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"model_params\":{\"type\":\"object\",\"description\":\"Model extension parameters\",\"properties\":{\"web_search\":{\"type\":\"boolean\",\"description\":\"Whether to enable web search. When enabled, the model will use web search results to optimize image generation\"}}}},\"example\":{\"prompt\":\"A cat playing on the grass\"}},\"gemini-3.1-flash-image-preview\":{\"model\":\"gemini-3.1-flash-image-preview\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"Nano Banana 2 Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/nanobanana/nanobanana-2-image-generate\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the image to be generated, or describing how to edit the input image, limited to 2000 tokens\",\"maxLength\":2000,\"required\":true},\"size\":{\"type\":\"string\",\"description\":\"Aspect ratio of the generated image, default is auto\",\"enum\":[\"auto\",\"1:1\",\"1:4\",\"4:1\",\"1:8\",\"8:1\",\"2:3\",\"3:2\",\"3:4\",\"4:3\",\"4:5\",\"5:4\",\"9:16\",\"16:9\",\"21:9\"]},\"quality\":{\"type\":\"string\",\"description\":\"Quality of the generated image, default is 2K Note: Different quality levels have different pricing\",\"enum\":[\"0.5K\",\"1K\",\"2K\",\"4K\"]},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL list for image-to-image and image editing functions Note: Maximum number of input images per request: 14; Image size: not exceeding 20MB; Supported file formats: .jpeg, .jpg, .png, .webp; Image URLs must be directly accessible by the server, or the image URL should directly download when accessed (typically these URLs end with image file extensions, such as .png, .jpg); Maximum of 4 real person images can be uploaded\",\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"model_params\":{\"type\":\"object\",\"description\":\"Model extension parameters\",\"properties\":{\"web_search\":{\"type\":\"boolean\",\"description\":\"Whether to enable web search. When enabled, the model will use web search results to optimize image generation\"},\"image_search\":{\"type\":\"boolean\",\"description\":\"Whether to enable image search. When enabled, the model will use web image search results to optimize image generation\"},\"thinking_level\":{\"type\":\"string\",\"description\":\"Thinking level, controls the depth of reasoning the model performs before generating images, defaults to auto; auto: Automatically selects thinking level; min: Minimal reasoning, fastest; high: Deep reasoning, best quality\",\"enum\":[\"auto\",\"min\",\"high\"]}}}},\"example\":{\"prompt\":\"A cat playing on the grass\"}},\"gemini-3.1-flash-lite-image\":{\"model\":\"gemini-3.1-flash-lite-image\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"Nano Banana 2 Lite Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/nanobanana/nanobanana-2-lite-image-generate\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the image to be generated, or describing how to edit the input image, limited to 2000 tokens\",\"maxLength\":2000,\"required\":true},\"size\":{\"type\":\"string\",\"description\":\"Aspect ratio of the generated image, default is auto\",\"enum\":[\"auto\",\"1:1\",\"1:4\",\"4:1\",\"1:8\",\"8:1\",\"2:3\",\"3:2\",\"3:4\",\"4:3\",\"4:5\",\"5:4\",\"9:16\",\"16:9\",\"21:9\"]},\"quality\":{\"type\":\"string\",\"description\":\"Quality of the generated image, default is 1K\",\"enum\":[\"1K\"]},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL list for image-to-image and image editing functions Note: Maximum number of input images per request: 14; Image size: not exceeding 20MB; Supported file formats: .jpeg, .jpg, .png, .webp; Image URLs must be directly accessible by the server, or the image URL should directly download when accessed (typically these URLs end with image file extensions, such as .png, .jpg)\",\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"model_params\":{\"type\":\"object\",\"description\":\"Model extension parameters\",\"properties\":{\"thinking_level\":{\"type\":\"string\",\"description\":\"Thinking level, controls the depth of reasoning the model performs before generating images, defaults to auto; auto: Automatically selects thinking level; min: Minimal reasoning, fastest; high: Deep reasoning, best quality\",\"enum\":[\"auto\",\"min\",\"high\"]}}}},\"example\":{\"prompt\":\"A cat playing on the grass\"}},\"gemini-omni-1.1-flash-image-to-video\":{\"model\":\"gemini-omni-1.1-flash-image-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Gemini Omni 1.1 Flash Image-to-Video\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/gemini-omni-1.1-flash/gemini-omni-1.1-flash-image-to-video\",\"required\":[\"prompt\",\"image_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing how the first frame should move and how the scene should evolve.\",\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"First/last-frame image URL array. One image is the first frame; with two images, the first is the first frame and the second is the last frame. HTTP/HTTPS image URLs only; png, jpeg, webp.\",\"minItems\":1,\"maxItems\":2,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution; default 720p. Supported values: 360p: landscape 640×360 / portrait 360×640; 720p: landscape 1280×720 / portrait 720×1280; default; 1080p: landscape 1920×1080 / portrait 1080×1920; 4k: landscape 3840×2160 / portrait 2160×3840 Orientation is controlled by aspect_ratio: 16:9 produces landscape and 9:16 produces portrait. Billing: Video output is billed by output tokens, which scale linearly with resolution. Relative to 720p, 360p uses about one third, 1080p about 1.5×, and 4k about 3×. Actual charges are based on generated usage.\",\"enum\":[\"360p\",\"720p\",\"1080p\",\"4k\"],\"default\":\"720p\"},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration in seconds; default 3. Notes: Accepts any integer from 3 to 10; Duration directly affects billing\",\"default\":3,\"minimum\":3,\"maximum\":10},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Aspect ratio: 16:9, 9:16, or auto; default auto.\",\"enum\":[\"16:9\",\"9:16\",\"auto\"],\"default\":\"auto\"}},\"example\":{\"prompt\":\"The subject slowly turns and smiles.\",\"image_urls\":[\"https://example.com/portrait.jpg\"],\"quality\":\"720p\",\"aspect_ratio\":\"16:9\",\"duration\":3}},\"gemini-omni-1.1-flash-reference-to-video\":{\"model\":\"gemini-omni-1.1-flash-reference-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Gemini Omni 1.1 Flash Reference-to-Video\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/gemini-omni-1.1-flash/gemini-omni-1.1-flash-reference-to-video\",\"required\":[\"prompt\",\"image_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing how the reference subjects, style, and motion should appear in the output.\",\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL array. Required; supports 1 to 10 images for constraining subjects, style, or elements. Input requirements: HTTP/HTTPS image URLs only; Supported formats: png, jpeg, webp\",\"minItems\":1,\"maxItems\":10,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"video_urls\":{\"type\":\"array\",\"description\":\"Optional reference video array; up to 3 videos. Videos can provide motion, camera movement, or style references and may be used together with image_urls. Input requirements: HTTP/HTTPS video URLs only; Format: mp4; Each video must be no longer than 10 seconds Billing: Every reference video contributes input tokens.\",\"minItems\":1,\"maxItems\":3,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution; default 720p. Supported values: 360p: landscape 640×360 / portrait 360×640; 720p: landscape 1280×720 / portrait 720×1280; default; 1080p: landscape 1920×1080 / portrait 1080×1920; 4k: landscape 3840×2160 / portrait 2160×3840 Orientation is controlled by aspect_ratio: 16:9 produces landscape and 9:16 produces portrait. Billing: Video output is billed by output tokens, which scale linearly with resolution. Relative to 720p, 360p uses about one third, 1080p about 1.5×, and 4k about 3×. Actual charges are based on generated usage.\",\"enum\":[\"360p\",\"720p\",\"1080p\",\"4k\"],\"default\":\"720p\"},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration in seconds; default 3. Notes: Accepts any integer from 3 to 10; Duration directly affects billing\",\"default\":3,\"minimum\":3,\"maximum\":10},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Aspect ratio: 16:9, 9:16, or auto; default auto.\",\"enum\":[\"16:9\",\"9:16\",\"auto\"],\"default\":\"auto\"}},\"example\":{\"prompt\":\"Keep the character appearance and camera motion from the references.\",\"image_urls\":[\"https://example.com/character.png\",\"https://example.com/scene.png\"],\"quality\":\"720p\",\"aspect_ratio\":\"16:9\",\"duration\":3}},\"gemini-omni-1.1-flash-text-to-video\":{\"model\":\"gemini-omni-1.1-flash-text-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Gemini Omni 1.1 Flash Text-to-Video\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/gemini-omni-1.1-flash/gemini-omni-1.1-flash-text-to-video\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing the subject, action, scene, and camera movement. Write negative requirements directly in the prompt.\",\"required\":true},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution; default 720p. Supported values: 360p: landscape 640×360 / portrait 360×640; 720p: landscape 1280×720 / portrait 720×1280; default; 1080p: landscape 1920×1080 / portrait 1080×1920; 4k: landscape 3840×2160 / portrait 2160×3840 Orientation is controlled by aspect_ratio: 16:9 produces landscape and 9:16 produces portrait. Billing: Video output is billed by output tokens, which scale linearly with resolution. Relative to 720p, 360p uses about one third, 1080p about 1.5×, and 4k about 3×. Actual charges are based on generated usage.\",\"enum\":[\"360p\",\"720p\",\"1080p\",\"4k\"],\"default\":\"720p\"},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration in seconds; default 3. Notes: Accepts any integer from 3 to 10; Duration directly affects billing\",\"default\":3,\"minimum\":3,\"maximum\":10},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Aspect ratio: 16:9, 9:16, or auto; default auto.\",\"enum\":[\"16:9\",\"9:16\",\"auto\"],\"default\":\"auto\"}},\"example\":{\"prompt\":\"A glass marble rolls down a wooden track and splashes into water.\",\"quality\":\"1080p\",\"aspect_ratio\":\"16:9\",\"duration\":3}},\"gemini-omni-1.1-flash-video-edit\":{\"model\":\"gemini-omni-1.1-flash-video-edit\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Gemini Omni 1.1 Flash Video Edit\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/gemini-omni-1.1-flash/gemini-omni-1.1-flash-video-edit\",\"required\":[\"prompt\",\"video_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text instruction describing the desired edit and what should remain unchanged.\",\"required\":true},\"video_urls\":{\"type\":\"array\",\"description\":\"Exactly one directly reachable HTTP/HTTPS MP4, no longer than 10 seconds.\",\"minItems\":1,\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Optional reference image array, up to 10 images. It may be used with the input video to constrain subjects, style, or elements. Input requirements: HTTP/HTTPS image URLs only; Supported formats: png, jpeg, webp Billing: Every reference image contributes input tokens.\",\"minItems\":1,\"maxItems\":10,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"quality\":{\"type\":\"string\",\"description\":\"Output video resolution; default auto. Supported values: 360p: short side 360; 720p: short side 720; 1080p: short side 1080; 4k: short side 2160; auto: follows the input video's resolution; default Choosing a specific resolution can upscale or downscale the output. Billing: Input and output video tokens are both calculated using the final output resolution; higher resolutions cost more.\",\"enum\":[\"360p\",\"720p\",\"1080p\",\"4k\",\"auto\"],\"default\":\"auto\"},\"duration\":{\"type\":\"string\",\"description\":\"Only auto is accepted and it is the default. Output duration follows the input video.\",\"enum\":[\"auto\"],\"default\":\"auto\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Only auto is accepted and it is the default. Output aspect ratio follows the input video.\",\"enum\":[\"auto\"],\"default\":\"auto\"}},\"example\":{\"prompt\":\"Make the lighting warmer while keeping everything else unchanged.\",\"video_urls\":[\"https://example.com/source.mp4\"],\"quality\":\"auto\",\"duration\":\"auto\",\"aspect_ratio\":\"auto\"}},\"gemini-omni-1.1-flash-video-extend\":{\"model\":\"gemini-omni-1.1-flash-video-extend\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Gemini Omni 1.1 Flash Video Extend\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/gemini-omni-1.1-flash/gemini-omni-1.1-flash-video-extend\",\"required\":[\"prompt\",\"video_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing what should happen after the input video ends.\",\"required\":true},\"video_urls\":{\"type\":\"array\",\"description\":\"Exactly one directly reachable HTTP/HTTPS MP4, no longer than 30 seconds.\",\"minItems\":1,\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Optional reference image array, up to 10 images. It may be used with the video being extended to constrain subjects, style, or elements. Input requirements: HTTP/HTTPS image URLs only; Supported formats: png, jpeg, webp Billing: Every reference image contributes input tokens.\",\"minItems\":1,\"maxItems\":10,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"duration\":{\"type\":\"integer\",\"description\":\"Appended video duration in seconds; default 3. Notes: Accepts any integer from 3 to 10; Specifies how many seconds are generated after the input video, not the total output duration; Total output duration = input video duration + duration; Appended duration directly affects billing\",\"default\":3,\"minimum\":3,\"maximum\":10},\"quality\":{\"type\":\"string\",\"description\":\"Output video resolution; default auto. Supported values: 360p: short side 360; 720p: short side 720; 1080p: short side 1080; 4k: short side 2160; auto: follows the input video's resolution; default Choosing a specific resolution can upscale or downscale the output. Billing: Input and output video tokens are both calculated using the final output resolution; higher resolutions cost more.\",\"enum\":[\"360p\",\"720p\",\"1080p\",\"4k\",\"auto\"],\"default\":\"auto\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Only auto is accepted and it is the default. Output aspect ratio follows the input video.\",\"enum\":[\"auto\"],\"default\":\"auto\"}},\"example\":{\"prompt\":\"The person keeps walking and slowly exits the frame.\",\"video_urls\":[\"https://example.com/source.mp4\"],\"duration\":3,\"quality\":\"auto\",\"aspect_ratio\":\"auto\"}},\"gemini-omni-flash-image-to-video\":{\"model\":\"gemini-omni-flash-image-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"gemini-omni-flash-image-to-video API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/gemini-omni-flash-1.0/gemini-omni-flash-image-to-video\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt for video generation, supports both English and Chinese Usage tips: Describe the subject's actions, camera movement, mood changes, etc.; the more specific, the more stable the result; Write negative requirements directly into the prompt (e.g. No dialogue, no text on screen); this model does not provide a separate negative prompt parameter\",\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Array of input images; currently only 1 is supported Supported forms: HTTP/HTTPS image URL; Data URL in the form data:image/...;base64,...; Plain base64 image string Format requirements: png, jpeg, webp are supported\",\"minItems\":1,\"maxItems\":1,\"items\":{\"type\":\"string\"}},\"duration\":{\"type\":\"integer|string\",\"description\":\"Video duration (seconds), default 10 Value notes: Integer: range 3 ~ 10 seconds; auto: the model decides the output duration Billing note: The actual charge is based on the usage of the generated video\",\"default\":10,\"minimum\":3,\"maximum\":10},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio, default 16:9 Value notes: 16:9: landscape; 9:16: portrait; auto: the model decides the aspect ratio\",\"enum\":[\"16:9\",\"9:16\",\"auto\"],\"default\":\"16:9\"}},\"example\":{\"prompt\":\"Have the person in the image slowly turn their head and smile while the leaves in the background sway gently in the breeze\",\"image_urls\":[\"https://example.com/portrait.jpg\"],\"aspect_ratio\":\"16:9\",\"duration\":10}},\"gemini-omni-flash-reference-to-video\":{\"model\":\"gemini-omni-flash-reference-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"gemini-omni-flash-reference-to-video API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/gemini-omni-flash-1.0/gemini-omni-flash-reference-to-video\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt for video generation, supports both English and Chinese Usage tips: Describe how the subjects from the reference images move in the video, camera movement, scene mood, etc.; Write negative requirements directly into the prompt (e.g. No dialogue, no text on screen); this model does not provide a separate negative prompt parameter\",\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Array of reference images, supports 1~6 Supported forms: HTTP/HTTPS image URL; Data URL in the form data:image/...;base64,...; Plain base64 image string Format requirements: png, jpeg, webp are supported\",\"minItems\":1,\"maxItems\":6,\"items\":{\"type\":\"string\"}},\"duration\":{\"type\":\"integer|string\",\"description\":\"Video duration (seconds), default 10 Value notes: Integer: range 3 ~ 10 seconds; auto: the model decides the output duration Billing note: The actual charge is based on the usage of the generated video\",\"default\":10,\"minimum\":3,\"maximum\":10},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio, default 16:9 Value notes: 16:9: landscape; 9:16: portrait; auto: the model decides the aspect ratio\",\"enum\":[\"16:9\",\"9:16\",\"auto\"],\"default\":\"16:9\"}},\"example\":{\"prompt\":\"Have the character from the reference image stroll through the reference scene\",\"image_urls\":[\"https://example.com/character.png\",\"https://example.com/scene.png\"],\"aspect_ratio\":\"16:9\",\"duration\":10}},\"gemini-omni-flash-text-to-video\":{\"model\":\"gemini-omni-flash-text-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"gemini-omni-flash-text-to-video API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/gemini-omni-flash-1.0/gemini-omni-flash-text-to-video\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt for video generation, supports both English and Chinese Usage tips: Describe the subject, action, scene, camera movement, etc.; the more specific, the more stable the result; Write negative requirements directly into the prompt (e.g. No dialogue, no text on screen); this model does not provide a separate negative prompt parameter\",\"required\":true},\"duration\":{\"type\":\"integer|string\",\"description\":\"Video duration (seconds), default 10 Value notes: Integer: range 3 ~ 10 seconds; auto: the model decides the output duration Billing note: The actual charge is based on the usage of the generated video\",\"default\":10,\"minimum\":3,\"maximum\":10},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio, default 16:9 Value notes: 16:9: landscape; 9:16: portrait; auto: the model decides the aspect ratio\",\"enum\":[\"16:9\",\"9:16\",\"auto\"],\"default\":\"16:9\"}},\"example\":{\"prompt\":\"A glass marble rolls rapidly down a wooden track and finally drops into water with a splash\",\"aspect_ratio\":\"16:9\",\"duration\":10}},\"gemini-omni-flash-video-edit\":{\"model\":\"gemini-omni-flash-video-edit\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"gemini-omni-flash-video-edit API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/gemini-omni-flash-1.0/gemini-omni-flash-video-edit\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt for video editing, describing the desired editing effect, supports both English and Chinese Usage tips: Describe the elements to change and the parts to keep unchanged (e.g. \\\"make the lighting warmer and keep everything else unchanged\\\"); Write negative requirements directly into the prompt (e.g. No dialogue, no text on screen); this model does not provide a separate negative prompt parameter\",\"required\":true},\"video_urls\":{\"type\":\"array\",\"description\":\"Array of videos to edit; only 1 is supported Input requirements: Currently only HTTP/HTTPS video URLs are supported; Format: mp4; Duration: 3-10 seconds\",\"minItems\":1,\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"}}},\"example\":{\"prompt\":\"Make the lighting in the scene warmer and keep everything else unchanged\",\"video_urls\":[\"https://example.com/source.mp4\"]}},\"gpt-image-1.5\":{\"model\":\"gpt-image-1.5\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"gpt-image-1.5-lite API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/gpt-image-1.5/gpt-image-1.5-image-generation\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the image you want to generate, or describing how to edit the input image. Limited to 2000 tokens\",\"maxLength\":2000,\"required\":true},\"size\":{\"type\":\"string\",\"description\":\"Size of the generated image, supports two formats: Aspect Ratio Format: 1:1: Square; 2:3: Portrait; 3:2: Landscape Pixel Format: 1024x1024: Square; 1024x1536: Portrait; 1536x1024: Landscape\",\"enum\":[\"1:1\",\"2:3\",\"3:2\",\"1024x1024\",\"1024x1536\",\"1536x1024\"]},\"quality\":{\"type\":\"string\",\"description\":\"Quality of the generated image Supported quality levels: low: Low quality, faster generation; medium: Medium quality; high: High quality, slower generation (default)\",\"enum\":[\"low\",\"medium\",\"high\"],\"default\":\"high\"},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL list for image-to-image and image editing features Notes: Supports 1~16 images per request; Maximum size per image: 50MB; Supported formats: .jpeg, .jpg, .png, .webp; Image URLs must be directly accessible by the server, or URLs that trigger direct download (typically URLs ending with image extensions like .png, .jpg)\",\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"n\":{\"type\":\"integer\",\"description\":\"Number of images to generate, currently only supports 1\",\"enum\":[1],\"default\":1}},\"example\":{\"prompt\":\"A beautiful colorful sunset over the ocean\"}},\"gpt-image-2\":{\"model\":\"gpt-image-2\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"gpt-image-2 API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/gpt-image-2/gpt-image-2-image-generation\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the image to generate or how to edit the input image Length limits (both must be met): Up to 32,000 characters (counted as Unicode code points); The prompt text itself must not exceed 60,000 bytes when encoded in UTF-8 Different characters use different numbers of UTF-8 bytes. Use the actual encoded byte count. If either limit is exceeded, shorten the prompt before resubmitting. Recommendation: If the prompt exceeds 8000 tokens, the generated image may not match expectations; shortening the prompt is recommended.\",\"maxLength\":32000,\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL list for image-to-image and image editing functions Note: Number of input images per request: 1~16; Size of a single image: not exceeding 50MB; Pixels of a single image: width × height not exceeding 178,956,970 px; Side length of a single image: width / height each not exceeding 23170 px; exceeding this may cause errors; Supported file formats: .jpeg, .jpg, .png, .webp; Image URLs must be directly accessible by the server, or the image URL should directly download when accessed (typically these URLs end with image file extensions, such as .png, .jpg); In image-to-image / i…\",\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"mask_url\":{\"type\":\"string\",\"description\":\"Inpainting mask URL — marks the region of the reference image to regenerate. Only valid in image edit mode (must be combined with image_urls); the mask is silently ignored in pure text-to-image requests. Format requirements: Must be a PNG with an alpha channel: transparent pixels (alpha < 255) = regions to regenerate; opaque pixels = preserved; Mask dimensions must exactly match the reference image dimensions (width × height in pixels); Single mask per request Note: At least one reference image is required in image_urls; a mask sent alone has no effect; Common errors: Invalid mask image forma…\",\"format\":\"uri\"},\"size\":{\"type\":\"string\",\"description\":\"Size of the generated image. Supports both ratio format and explicit pixel format, defaults to auto ① Ratio format (recommended, 15 options); 1:1: Square; 1:2 / 2:1: Extreme portrait / landscape; 1:3 / 3:1: Ultra portrait / landscape (3:1 limit); 2:3 / 3:2: Standard portrait / landscape; 3:4 / 4:3: Classic portrait / landscape; 4:5 / 5:4: Common social media; 9:16 / 16:9: Mobile / desktop widescreen; 9:21 / 21:9: Ultra-wide ② Explicit pixel format: WxH (or W×H), e.g. 1024x1024, 1536x1024, 3840×2160; Both width and height must be multiples of 16; Each edge range: [16, 3840]; Pixel budget: 655,…\",\"default\":\"auto\"},\"resolution\":{\"type\":\"string\",\"description\":\"Resolution tier shortcut, only effective when size is a ratio; ignored in explicit pixel mode Pixel budget rules (dimensions are derived from the target pixel count and the size ratio, aligned to multiples of 16): 1K: ~1 MP (1024² = 1,048,576 pixels); 2K: ~4 MP (2048² = 4,194,304 pixels); 4K: ~8.29 MP (3840×2160 = 8,294,400 pixels, the maximum) Landscape / square output dimensions (portrait dimensions are the landscape width/height swapped, e.g. 2:3 = 3:2 reversed): | Ratio | 1K | 2K | 4K | |---|---|---|---| | 1:1 | 1024×1024 | 2048×2048 | 2880×2880 | | 2:1 | 1456×720 | 2896×1456 | 3840×1920…\",\"enum\":[\"1K\",\"2K\",\"4K\"],\"default\":\"1K\"},\"quality\":{\"type\":\"string\",\"description\":\"Rendering quality that controls the model's \\\"reasoning depth\\\", directly affecting output token count and cost. Defaults to medium | Value | Tile base | Relative cost (1024²) | |---|---|---| | low | 16 | ~0.11× | | medium | 48 | 1.0× | | high | 96 | ~4.0× |\",\"enum\":[\"low\",\"medium\",\"high\"],\"default\":\"medium\"},\"background\":{\"type\":\"string\",\"description\":\"Alpha channel of the output image. Defaults to opaque; opaque: Flat background, no alpha channel; transparent: Keeps the alpha channel Note: transparent is a Preview feature and results may be unstable; Not supported by gpt-image-2-beta; When using transparent, output_format must be png or webp\",\"enum\":[\"opaque\",\"transparent\"],\"default\":\"opaque\"},\"output_format\":{\"type\":\"string\",\"description\":\"Output image file format. Defaults to png; png: Lossless, supports transparent backgrounds; jpeg: Lossy compression, smaller files; webp: Balances file size and quality, also supports transparent backgrounds Note: When background is transparent, only png or webp can be used; jpeg cannot carry an alpha channel\",\"enum\":[\"png\",\"jpeg\",\"webp\"],\"default\":\"png\"},\"n\":{\"type\":\"integer\",\"description\":\"Number of images to generate, each billed independently Note: Text input tokens scale linearly with n; The official model's support for n > 1 is currently unreliable: even with a value greater than 1, only one image is often returned. The actual count is whatever results holds in the response, and billing follows the returned usage. If you need several images, send multiple single-image requests instead\",\"default\":1,\"minimum\":1,\"maximum\":10}},\"example\":{\"prompt\":\"A beautiful colorful sunset over the ocean\"}},\"gpt-image-2-beta\":{\"model\":\"gpt-image-2-beta\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"gpt-image-2-beta API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/gpt-image-2/gpt-image-2-beta-image-generation\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the image you want to generate, or describing how to edit the input image. Limited to 2000 tokens\",\"maxLength\":2000,\"required\":true},\"size\":{\"type\":\"string\",\"description\":\"Generated image size. Supports two modes: 1. auto (default) The model automatically determines the output size. In this mode, the resolution field is ignored and treated as 1K. 2. Ratio (must be used with resolution=\\\"1K\\\"); 1:1: Square; 3:2 / 2:3: Landscape / Portrait; 4:3 / 3:4: Landscape / Portrait; 5:4 / 4:5: Common social media; 16:9 / 9:16: Widescreen landscape / portrait; 21:9 / 9:21: Ultra-wide landscape / portrait; 2:1 / 1:2: Landscape / Portrait; 3:1 / 1:3: Panorama landscape / portrait (maximum aspect ratio) Note: Explicit pixel sizes (such as 1024x1024) are not currently supported.…\",\"default\":\"auto\"},\"resolution\":{\"type\":\"string\",\"description\":\"Resolution tier. Effective only when size is a ratio. Currently only 1K is supported. When ignored: When size=auto, this field is ignored and treated as 1K (no need to pass this parameter) Landscape / square output dimensions (portrait dimensions are the landscape width/height swapped): | Ratio | 1K | |---|---| | 1:1 | 1024×1024 | | 2:1 | 1456×720 | | 3:1 | 1776×592 | | 3:2 | 1248×832 | | 4:3 | 1184×880 | | 5:4 | 1152×912 | | 16:9 | 1360×768 | | 21:9 | 1568×672 | Note: 2K / 4K are not currently supported. For higher resolution, use [gpt-image-2](/en/api-manual/image-series/gpt-image-2/gpt-ima…\",\"enum\":[\"1K\"],\"default\":\"1K\"},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL list for image-to-image and image editing features Notes: Up to 16 reference images per request; Supported formats: .jpeg, .jpg, .png, .webp; Image URLs must be directly accessible by the server, or URLs that trigger direct download (typically URLs ending with image extensions like .png, .jpg)\",\"maxItems\":16,\"items\":{\"type\":\"string\",\"format\":\"uri\"}}},\"example\":{\"prompt\":\"A beautiful colorful sunset over the ocean\"}},\"gpt-image-2.5-flare\":{\"model\":\"gpt-image-2.5-flare\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"gpt-image-2.5 API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/gpt-image-2.5/gpt-image-2.5-image-generation\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the image to generate or how to edit the input image Length limits (both must be met): Up to 32,000 characters (counted as Unicode code points); The prompt text itself must not exceed 60,000 bytes when encoded in UTF-8 Different characters use different numbers of UTF-8 bytes. Use the actual encoded byte count. If either limit is exceeded, shorten the prompt before resubmitting. Recommendation: If the prompt exceeds 8000 tokens, the generated image may not match expectations; shortening the prompt is recommended.\",\"maxLength\":32000,\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL list for image-to-image and image editing functions Note: Number of input images per request: 1~16; Size of a single image: not exceeding 50MB; Pixels of a single image: width × height not exceeding 178,956,970 px; Side length of a single image: width / height each not exceeding 23170 px; exceeding this may cause errors; Supported file formats: .jpeg, .jpg, .png, .webp; Image URLs must be directly accessible by the server, or the image URL should directly download when accessed (typically these URLs end with image file extensions, such as .png, .jpg); In image-to-image / i…\",\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"mask_url\":{\"type\":\"string\",\"description\":\"Inpainting mask URL — marks the region of the reference image to regenerate. Only valid in image edit mode (must be combined with image_urls); the mask is silently ignored in pure text-to-image requests. Format requirements: Must be a PNG with an alpha channel: transparent pixels (alpha < 255) = regions to regenerate; opaque pixels = preserved; Mask dimensions must exactly match the reference image dimensions (width × height in pixels); Single mask per request Note: At least one reference image is required in image_urls; a mask sent alone has no effect; Common errors: Invalid mask image forma…\",\"format\":\"uri\"},\"size\":{\"type\":\"string\",\"description\":\"Size of the generated image. Supports both ratio format and explicit pixel format, defaults to auto ① Ratio format (recommended, 15 options); 1:1: Square; 1:2 / 2:1: Extreme portrait / landscape; 1:3 / 3:1: Ultra portrait / landscape (3:1 limit); 2:3 / 3:2: Standard portrait / landscape; 3:4 / 4:3: Classic portrait / landscape; 4:5 / 5:4: Common social media; 9:16 / 16:9: Mobile / desktop widescreen; 9:21 / 21:9: Ultra-wide ② Explicit pixel format: WxH (or W×H), e.g. 1024x1024, 1536x1024, 3840×2160; Both width and height must be multiples of 16; Each edge range: [16, 3840]; Pixel budget: 655,…\",\"default\":\"auto\"},\"resolution\":{\"type\":\"string\",\"description\":\"Resolution tier shortcut, only effective when size is a ratio; ignored in explicit pixel mode Pixel budget rules (dimensions are derived from the target pixel count and the size ratio, aligned to multiples of 16): 1K: ~1 MP (1024² = 1,048,576 pixels); 2K: ~4 MP (2048² = 4,194,304 pixels); 4K: ~8.29 MP (3840×2160 = 8,294,400 pixels, the maximum) Landscape / square output dimensions (portrait dimensions are the landscape width/height swapped, e.g. 2:3 = 3:2 reversed): | Ratio | 1K | 2K | 4K | |---|---|---|---| | 1:1 | 1024×1024 | 2048×2048 | 2880×2880 | | 2:1 | 1456×720 | 2896×1456 | 3840×1920…\",\"enum\":[\"1K\",\"2K\",\"4K\"],\"default\":\"1K\"},\"quality\":{\"type\":\"string\",\"description\":\"Rendering quality that controls the model's \\\"reasoning depth\\\", directly affecting output token count and cost. Defaults to medium | Value | Tile base | Output tokens (1024²) | Relative cost (1024²) | |---|---|---|---| | low | 16 | 196 | ~0.45× | | medium | 24 | 439 | 1.0× | | high | 48 | 1,756 | ~4.0× | | xhigh | 64 | 3,122 | ~7.1× | | max | 96 | 7,024 | ~16.0× | Note: The tiers are more fine-grained than on GPT Image 2: low costs the same on both, while medium and high use only 1/4 of the output tokens of the same-named tier on GPT Image 2; high on 2.5 matches medium on GPT Image 2, and only…\",\"enum\":[\"low\",\"medium\",\"high\",\"xhigh\",\"max\"],\"default\":\"medium\"},\"background\":{\"type\":\"string\",\"description\":\"Alpha channel of the output image. Defaults to opaque; opaque: Flat background, no alpha channel; transparent: Keeps the alpha channel Note: transparent is a Preview feature and results may be unstable; When using transparent, output_format must be png or webp\",\"enum\":[\"opaque\",\"transparent\"],\"default\":\"opaque\"},\"output_format\":{\"type\":\"string\",\"description\":\"Output image file format. Defaults to png; png: Lossless, supports transparent backgrounds; jpeg: Lossy compression, smaller files; webp: Balances file size and quality, also supports transparent backgrounds Note: When background is transparent, only png or webp can be used; jpeg cannot carry an alpha channel\",\"enum\":[\"png\",\"jpeg\",\"webp\"],\"default\":\"png\"},\"n\":{\"type\":\"integer\",\"description\":\"Number of images to generate, each billed independently Note: Text input tokens scale linearly with n; The official model's support for n > 1 is currently unreliable: even with a value greater than 1, only one image is often returned. The actual count is whatever results holds in the response, and billing follows the returned usage. If you need several images, send multiple single-image requests instead\",\"default\":1,\"minimum\":1,\"maximum\":10}},\"example\":{\"prompt\":\"A beautiful colorful sunset over the ocean\"}},\"gpt-image-2.5-sunburst\":{\"model\":\"gpt-image-2.5-sunburst\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"gpt-image-2.5 API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/gpt-image-2.5/gpt-image-2.5-image-generation\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the image to generate or how to edit the input image Length limits (both must be met): Up to 32,000 characters (counted as Unicode code points); The prompt text itself must not exceed 60,000 bytes when encoded in UTF-8 Different characters use different numbers of UTF-8 bytes. Use the actual encoded byte count. If either limit is exceeded, shorten the prompt before resubmitting. Recommendation: If the prompt exceeds 8000 tokens, the generated image may not match expectations; shortening the prompt is recommended.\",\"maxLength\":32000,\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL list for image-to-image and image editing functions Note: Number of input images per request: 1~16; Size of a single image: not exceeding 50MB; Pixels of a single image: width × height not exceeding 178,956,970 px; Side length of a single image: width / height each not exceeding 23170 px; exceeding this may cause errors; Supported file formats: .jpeg, .jpg, .png, .webp; Image URLs must be directly accessible by the server, or the image URL should directly download when accessed (typically these URLs end with image file extensions, such as .png, .jpg); In image-to-image / i…\",\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"mask_url\":{\"type\":\"string\",\"description\":\"Inpainting mask URL — marks the region of the reference image to regenerate. Only valid in image edit mode (must be combined with image_urls); the mask is silently ignored in pure text-to-image requests. Format requirements: Must be a PNG with an alpha channel: transparent pixels (alpha < 255) = regions to regenerate; opaque pixels = preserved; Mask dimensions must exactly match the reference image dimensions (width × height in pixels); Single mask per request Note: At least one reference image is required in image_urls; a mask sent alone has no effect; Common errors: Invalid mask image forma…\",\"format\":\"uri\"},\"size\":{\"type\":\"string\",\"description\":\"Size of the generated image. Supports both ratio format and explicit pixel format, defaults to auto ① Ratio format (recommended, 15 options); 1:1: Square; 1:2 / 2:1: Extreme portrait / landscape; 1:3 / 3:1: Ultra portrait / landscape (3:1 limit); 2:3 / 3:2: Standard portrait / landscape; 3:4 / 4:3: Classic portrait / landscape; 4:5 / 5:4: Common social media; 9:16 / 16:9: Mobile / desktop widescreen; 9:21 / 21:9: Ultra-wide ② Explicit pixel format: WxH (or W×H), e.g. 1024x1024, 1536x1024, 3840×2160; Both width and height must be multiples of 16; Each edge range: [16, 3840]; Pixel budget: 655,…\",\"default\":\"auto\"},\"resolution\":{\"type\":\"string\",\"description\":\"Resolution tier shortcut, only effective when size is a ratio; ignored in explicit pixel mode Pixel budget rules (dimensions are derived from the target pixel count and the size ratio, aligned to multiples of 16): 1K: ~1 MP (1024² = 1,048,576 pixels); 2K: ~4 MP (2048² = 4,194,304 pixels); 4K: ~8.29 MP (3840×2160 = 8,294,400 pixels, the maximum) Landscape / square output dimensions (portrait dimensions are the landscape width/height swapped, e.g. 2:3 = 3:2 reversed): | Ratio | 1K | 2K | 4K | |---|---|---|---| | 1:1 | 1024×1024 | 2048×2048 | 2880×2880 | | 2:1 | 1456×720 | 2896×1456 | 3840×1920…\",\"enum\":[\"1K\",\"2K\",\"4K\"],\"default\":\"1K\"},\"quality\":{\"type\":\"string\",\"description\":\"Rendering quality that controls the model's \\\"reasoning depth\\\", directly affecting output token count and cost. Defaults to medium | Value | Tile base | Output tokens (1024²) | Relative cost (1024²) | |---|---|---|---| | low | 16 | 196 | ~0.45× | | medium | 24 | 439 | 1.0× | | high | 48 | 1,756 | ~4.0× | | xhigh | 64 | 3,122 | ~7.1× | | max | 96 | 7,024 | ~16.0× | Note: The tiers are more fine-grained than on GPT Image 2: low costs the same on both, while medium and high use only 1/4 of the output tokens of the same-named tier on GPT Image 2; high on 2.5 matches medium on GPT Image 2, and only…\",\"enum\":[\"low\",\"medium\",\"high\",\"xhigh\",\"max\"],\"default\":\"medium\"},\"background\":{\"type\":\"string\",\"description\":\"Alpha channel of the output image. Defaults to opaque; opaque: Flat background, no alpha channel; transparent: Keeps the alpha channel Note: transparent is a Preview feature and results may be unstable; When using transparent, output_format must be png or webp\",\"enum\":[\"opaque\",\"transparent\"],\"default\":\"opaque\"},\"output_format\":{\"type\":\"string\",\"description\":\"Output image file format. Defaults to png; png: Lossless, supports transparent backgrounds; jpeg: Lossy compression, smaller files; webp: Balances file size and quality, also supports transparent backgrounds Note: When background is transparent, only png or webp can be used; jpeg cannot carry an alpha channel\",\"enum\":[\"png\",\"jpeg\",\"webp\"],\"default\":\"png\"},\"n\":{\"type\":\"integer\",\"description\":\"Number of images to generate, each billed independently Note: Text input tokens scale linearly with n; The official model's support for n > 1 is currently unreliable: even with a value greater than 1, only one image is often returned. The actual count is whatever results holds in the response, and billing follows the returned usage. If you need several images, send multiple single-image requests instead\",\"default\":1,\"minimum\":1,\"maximum\":10}},\"example\":{\"prompt\":\"A beautiful colorful sunset over the ocean\"}},\"grok-imagine-image-2.0\":{\"model\":\"grok-imagine-image-2.0\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"grok-imagine-image-2.0 API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/grok/grok-imagine-image-2.0-image-generate\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the image you want to generate, or how to edit the reference images you provide Multi-image reference syntax: When passing multiple reference images, use <IMAGE_0>, <IMAGE_1>, <IMAGE_2> in the prompt to refer to the 1st, 2nd and 3rd reference image respectively; Indexes start at 0 and map one-to-one to the order of the image_urls array; Example: Place the person from <IMAGE_0> into the scene of <IMAGE_1>\",\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL list for image-to-image and image editing functions Note: Number of input images per request: 0~3 (omitted = text-to-image, 1~3 = image editing); Only publicly accessible http / https image URLs are supported; base64 and data URLs are not supported; Supported file formats: .jpeg, .jpg, .png, .webp; Image URLs must be directly accessible by the server, or the image URL should directly download when accessed (typically these URLs end with image file extensions, such as .png, .jpg); In image editing scenarios the reference images incur an additional charge, counted once per r…\",\"maxItems\":3,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"size\":{\"type\":\"string\",\"description\":\"Aspect ratio of the generated image, defaults to auto Supported ratios (13): | Ratio | Description | |---|---| | 1:1 | Square | | 4:3 / 3:4 | Classic landscape / portrait | | 3:2 / 2:3 | Standard landscape / portrait | | 16:9 / 9:16 | Widescreen / mobile portrait | | 2:1 / 1:2 | Ultra-wide / ultra-tall | | 19.5:9 / 9:19.5 | Full-screen phone landscape / portrait | | 20:9 / 9:20 | Ultra-wide landscape / portrait | Note: auto: the model decides the ratio itself; omitting this parameter is equivalent to auto (output is usually portrait); Values outside the table above are not supported\",\"enum\":[\"1:1\",\"4:3\",\"3:4\",\"3:2\",\"2:3\",\"16:9\",\"9:16\",\"2:1\",\"1:2\",\"19.5:9\",\"9:19.5\",\"20:9\",\"9:20\",\"auto\"],\"default\":\"auto\"},\"resolution\":{\"type\":\"string\",\"description\":\"Pixel tier of the output image, defaults to 1K; supports the 1K and 2K tiers Note: This model does not support 4K; Values are case-insensitive\",\"enum\":[\"1K\",\"2K\"],\"default\":\"1K\"},\"quality\":{\"type\":\"string\",\"description\":\"Generation quality tier, controls how deeply the model thinks, defaults to medium | Value | Description | |---|---| | low | Faster output, lower cost | | medium | Better image quality and detail | Note: This model only supports the low / medium tiers; other values such as high are not supported; quality (quality tier) and resolution (pixel tier) are independent and can be combined freely; Values are case-insensitive\",\"enum\":[\"low\",\"medium\"],\"default\":\"medium\"},\"n\":{\"type\":\"integer\",\"description\":\"Number of images to generate, range 1~10, defaults to 1 Note: Each image is billed independently, cost grows linearly with n; The additional charge for reference images is counted once per request and is not multiplied by n\",\"default\":1,\"minimum\":1,\"maximum\":10}},\"example\":{\"prompt\":\"Cyberpunk Tokyo street at night, neon lights reflecting on the wet pavement\"}},\"grok-imagine-image-to-video-beta\":{\"model\":\"grok-imagine-image-to-video-beta\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"grok-imagine-image-to-video Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/grok/grok-imagine-image-to-video\",\"required\":[\"prompt\",\"image_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Video description prompt\",\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL list Requirements: Supports 1 ~ 7 images per request; Image size: max 10MB; Supported formats: JPEG, PNG, WebP\",\"minItems\":1,\"maxItems\":7,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds), any integer between 6 and 30 seconds\",\"default\":6,\"minimum\":6,\"maximum\":30},\"mode\":{\"type\":\"string\",\"description\":\"Generation style Options: fun: Fun style; normal: Normal style (default); spicy: Spicy style\",\"enum\":[\"fun\",\"normal\",\"spicy\"],\"default\":\"normal\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Aspect ratio (only effective in multi-image mode; in single-image mode, video size follows the input image) Options: 16:9: Landscape (default); 9:16: Portrait; 1:1: Square; 3:2: Landscape 3:2; 2:3: Portrait 2:3\",\"enum\":[\"16:9\",\"9:16\",\"1:1\",\"3:2\",\"2:3\"],\"default\":\"16:9\"},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution, default is 480p Options: 480p: Standard definition (default); 720p: High definition\",\"enum\":[\"480p\",\"720p\"],\"default\":\"480p\"}},\"example\":{\"prompt\":\"The person starts dancing\",\"image_urls\":[\"https://example.com/image.jpg\"],\"duration\":6,\"mode\":\"normal\",\"quality\":\"480p\"}},\"grok-imagine-text-to-video-beta\":{\"model\":\"grok-imagine-text-to-video-beta\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"grok-imagine-text-to-video Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/grok/grok-imagine-text-to-video\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Video description prompt\",\"required\":true},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds), any integer between 6 and 30 seconds\",\"default\":6,\"minimum\":6,\"maximum\":30},\"mode\":{\"type\":\"string\",\"description\":\"Generation style Options: fun: Fun style; normal: Normal style (default); spicy: Spicy style\",\"enum\":[\"fun\",\"normal\",\"spicy\"],\"default\":\"normal\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Aspect ratio Options: 16:9: Landscape (default); 9:16: Portrait; 1:1: Square; 3:2: Landscape 3:2; 2:3: Portrait 2:3\",\"enum\":[\"16:9\",\"9:16\",\"1:1\",\"3:2\",\"2:3\"],\"default\":\"16:9\"},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution, default is 480p Options: 480p: Standard definition (default); 720p: High definition\",\"enum\":[\"480p\",\"720p\"],\"default\":\"480p\"}},\"example\":{\"prompt\":\"A cat playing piano in a jazz club\",\"duration\":6,\"mode\":\"fun\",\"aspect_ratio\":\"16:9\",\"quality\":\"480p\"}},\"grok-imagine-video-1.0-i2v\":{\"model\":\"grok-imagine-video-1.0-i2v\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"grok-imagine-video-1.0-i2v Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/grok/grok-imagine-video-1.0-i2v\",\"required\":[\"prompt\",\"image_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Video description prompt (required, cannot be empty)\",\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL list (required) Requirements: Supports 1 ~ 7 images per request; omitting it or passing more than 7 is rejected; Image size: max 10MB per image; Supported formats: JPEG, PNG, WebP\",\"minItems\":1,\"maxItems\":7,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds), any integer between 1 and 15 seconds\",\"default\":6,\"minimum\":1,\"maximum\":15},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Aspect ratio (only effective in multi-image mode; in single-image mode, video size follows the input image) Options: 16:9: Landscape (default); 9:16: Portrait; 1:1: Square; 3:2: Landscape 3:2; 2:3: Portrait 2:3; 4:3: Landscape 4:3; 3:4: Portrait 3:4\",\"enum\":[\"16:9\",\"9:16\",\"1:1\",\"3:2\",\"2:3\",\"4:3\",\"3:4\"],\"default\":\"16:9\"},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution, default is 480p Options: 480p: Standard definition (default); 720p: High definition\",\"enum\":[\"480p\",\"720p\"],\"default\":\"480p\"}},\"example\":{\"prompt\":\"The person starts dancing\",\"image_urls\":[\"https://cdn.evolink.ai/Model-Example/GrokImagine1.5/generated-image.png\"],\"duration\":6,\"quality\":\"480p\"}},\"grok-imagine-video-1.0-t2v\":{\"model\":\"grok-imagine-video-1.0-t2v\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"grok-imagine-video-1.0-t2v Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/grok/grok-imagine-video-1.0-t2v\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Video description prompt (required, cannot be empty)\",\"required\":true},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds), any integer between 1 and 15 seconds\",\"default\":6,\"minimum\":1,\"maximum\":15},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Aspect ratio Options: 16:9: Landscape (default); 9:16: Portrait; 1:1: Square; 3:2: Landscape 3:2; 2:3: Portrait 2:3; 4:3: Landscape 4:3; 3:4: Portrait 3:4\",\"enum\":[\"16:9\",\"9:16\",\"1:1\",\"3:2\",\"2:3\",\"4:3\",\"3:4\"],\"default\":\"16:9\"},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution, default is 480p Options: 480p: Standard definition (default); 720p: High definition\",\"enum\":[\"480p\",\"720p\"],\"default\":\"480p\"}},\"example\":{\"prompt\":\"A cat playing piano in a jazz club\",\"duration\":6,\"aspect_ratio\":\"16:9\",\"quality\":\"480p\"}},\"grok-imagine-video-1.5-preview\":{\"model\":\"grok-imagine-video-1.5-preview\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"grok-imagine-video-1.5-preview Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/grok/grok-imagine-video-1.5-preview\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Video description prompt (required, cannot be empty) Length limit: Up to 4096 characters\",\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Input image URLs (optional). The number of images selects the generation mode. Mode selection: 0 images (omit the field): text-to-video, no image charge; 1 image: image-to-video, used as the first frame; 2-7 images: reference-to-video, blended together Requirements: Up to 7 images; 8 or more are rejected; Image size: max 10MB each; Supported formats: JPEG, PNG, WebP\",\"minItems\":0,\"maxItems\":7,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds), any integer between 1 and 15 seconds\",\"default\":6,\"minimum\":1,\"maximum\":15},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution, default is 480p Description: 480p: Standard definition (default); 720p: High definition; 1080p: Full HD Reference-to-video (2-7 images) supports up to 720p. Sending 1080p together with 2 or more images is rejected. 1080p remains available for text-to-video and single-image image-to-video.\",\"enum\":[\"480p\",\"720p\",\"1080p\"],\"default\":\"480p\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Output aspect ratio, default is auto Applies to: text-to-video (0 images) and reference-to-video (2-7 images). With a single input image the output follows that image's dimensions and this parameter is ignored. Description: auto: The model decides the framing, which can differ between runs; this is the default value; 16:9: Landscape; 9:16: Portrait; 1:1: Square; 3:2: Landscape, classic photo ratio; 2:3: Portrait, classic photo ratio\",\"enum\":[\"auto\",\"16:9\",\"9:16\",\"1:1\",\"3:2\",\"2:3\"],\"default\":\"auto\"}},\"example\":{\"prompt\":\"A neon-lit street at night, slow dolly forward through the rain\",\"duration\":6,\"quality\":\"480p\",\"aspect_ratio\":\"16:9\"}},\"happyhorse-1.0-image-to-video\":{\"model\":\"happyhorse-1.0-image-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"HappyHorse 1.0 Image-to-Video\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/happyhorse1.0/happyhorse-1.0-image-to-video\",\"required\":[\"image_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt, optional (when omitted, the first frame drives free interpretation) Length limits: Chinese: up to 2500 characters; Non-Chinese: up to 5000 characters; Excess content is automatically truncated\"},\"image_urls\":{\"type\":\"array\",\"description\":\"First-frame image URL, required (the first item of the array is taken as the first frame) Image requirements: Supported formats: JPEG, JPG, PNG, WEBP; Resolution: width and height ≥ 300 px; Aspect ratio: 1:2.5 ~ 2.5:1; File size: ≤ 10MB; Image URLs must be publicly accessible (HTTP or HTTPS); private OSS, intranet, or authenticated links are not supported\",\"minItems\":1,\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution tier, defaults to 720p Options: 720p: Standard clarity, this is the default; 1080p: HD clarity Billing note: Resolution tier directly affects billing\",\"enum\":[\"720p\",\"1080p\"],\"default\":\"720p\"},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds), defaults to 5 seconds Range: Integer 3 ~ 15; Duration directly affects billing\",\"default\":5,\"minimum\":3,\"maximum\":15},\"seed\":{\"type\":\"integer\",\"description\":\"Random seed, default is random Details: Range: 1 ~ 2147483647; A fixed seed reduces parameter-induced variation when iterating on prompts and improves reproducibility\",\"minimum\":1,\"maximum\":2147483647}},\"example\":{\"prompt\":\"Make the cat in the picture run on the grass\",\"image_urls\":[\"https://cdn.example.com/cat.png\"],\"quality\":\"720p\",\"duration\":5}},\"happyhorse-1.0-reference-to-video\":{\"model\":\"happyhorse-1.0-reference-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"HappyHorse 1.0 Reference-to-Video\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/happyhorse1.0/happyhorse-1.0-reference-to-video\",\"required\":[\"prompt\",\"image_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt, required Length limits: Chinese: up to 2500 characters; Non-Chinese: up to 5000 characters; Excess content is automatically truncated Character reference convention (important): The prompt must explicitly use character1, character2, character3 ... keywords to reference images in image_urls in order; The 1st image corresponds to character1, the 2nd to character2, and so on; Missing explicit references may cause character confusion\",\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL array, required, 1 ~ 9 images Image requirements: Supported formats: JPEG, JPG, PNG, WEBP; Resolution: short edge ≥ 400 px; 720P or higher quality images are recommended (avoid extremely small, blurry, or heavily compressed images); Recommended aspect ratio: short edge / long edge ≥ 0.4, with consistent proportions across images (close to the target video ratio); File size: ≤ 10MB per image; Image URLs must be publicly accessible (HTTP or HTTPS); private OSS, intranet, or authenticated links are not supported Order: Array order corresponds to character1, character2 ... ref…\",\"minItems\":1,\"maxItems\":9,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution tier, defaults to 720p Options: 720p: Standard clarity, this is the default; 1080p: HD clarity Billing note: Resolution tier directly affects billing\",\"enum\":[\"720p\",\"1080p\"],\"default\":\"720p\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio, defaults to 16:9 Options: 16:9 (landscape); 9:16 (portrait); 1:1 (square); 4:3; 3:4; 4:5; 5:4; 9:21; 21:9\",\"enum\":[\"16:9\",\"9:16\",\"1:1\",\"4:3\",\"3:4\",\"4:5\",\"5:4\",\"9:21\",\"21:9\"],\"default\":\"16:9\"},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds), defaults to 5 seconds Range: Integer 3 ~ 15; Duration directly affects billing\",\"default\":5,\"minimum\":3,\"maximum\":15},\"seed\":{\"type\":\"integer\",\"description\":\"Random seed, default is random Details: Range: 1 ~ 2147483647; A fixed seed reduces parameter-induced variation when iterating on prompts and improves reproducibility\",\"minimum\":1,\"maximum\":2147483647}},\"example\":{\"prompt\":\"A woman in a red qipao character1, the camera first frames the slim cut of the qipao from a side medium shot, then switches to a low-angle upward shot capturing details as she gracefully lifts her hand to open a folding fan character2, with tasseled earrings character3 swaying lightly as she turns her head.\",\"image_urls\":[\"https://cdn.example.com/girl.jpg\",\"https://cdn.example.com/folding-fan.jpg\",\"https://cdn.example.com/earrings.jpg\"],\"quality\":\"720p\",\"aspect_ratio\":\"16:9\",\"duration\":5}},\"happyhorse-1.0-text-to-video\":{\"model\":\"happyhorse-1.0-text-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"HappyHorse 1.0 Text-to-Video\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/happyhorse1.0/happyhorse-1.0-text-to-video\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt, required Length limits: Chinese: up to 2500 characters; Non-Chinese: up to 5000 characters; Excess content is automatically truncated Prompt tips: Detailed shot-by-shot descriptions yield better multi-shot narrative results; Example: Shot 1 [0~3s] wide angle: ...; Shot 2 [3~6s] medium shot: ...\",\"required\":true},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution tier, defaults to 720p Options: 720p: Standard clarity, this is the default; 1080p: HD clarity Billing note: Resolution tier directly affects billing\",\"enum\":[\"720p\",\"1080p\"],\"default\":\"720p\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio, defaults to 16:9 Options: 16:9 (landscape); 9:16 (portrait); 1:1 (square); 4:3; 3:4; 4:5; 5:4; 9:21; 21:9\",\"enum\":[\"16:9\",\"9:16\",\"1:1\",\"4:3\",\"3:4\",\"4:5\",\"5:4\",\"9:21\",\"21:9\"],\"default\":\"16:9\"},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds), defaults to 5 seconds Range: Integer 3 ~ 15; Duration directly affects billing\",\"default\":5,\"minimum\":3,\"maximum\":15},\"seed\":{\"type\":\"integer\",\"description\":\"Random seed, default is random Details: Range: 1 ~ 2147483647; A fixed seed reduces parameter-induced variation when iterating on prompts and improves reproducibility\",\"minimum\":1,\"maximum\":2147483647}},\"example\":{\"prompt\":\"A miniature city built from cardboard and bottle caps comes to life at night. A cardboard train slowly passes through, dotted with tiny lights illuminating the path ahead.\",\"quality\":\"720p\",\"aspect_ratio\":\"16:9\",\"duration\":5,\"seed\":42}},\"happyhorse-1.0-video-edit\":{\"model\":\"happyhorse-1.0-video-edit\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"HappyHorse 1.0 Video-Edit\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/happyhorse1.0/happyhorse-1.0-video-edit\",\"required\":[\"prompt\",\"video_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Edit instruction text, required Length limits: Chinese: up to 2500 characters; Non-Chinese: up to 5000 characters; Excess content is automatically truncated Prompt tips: Use editing instructions instead of creative descriptions; Examples: Replace the protagonist's clothes with the striped sweater in the image, Replace the video background with snowy mountains\",\"required\":true},\"video_urls\":{\"type\":\"array\",\"description\":\"Source video URL to edit, required, only 1 (the first item of the array is taken) Video requirements: Supported formats: MP4, MOV (H.264 encoding recommended); Duration: 3 ~ 60 seconds; The model automatically truncates inputs longer than 15 seconds to the first 15 seconds; Resolution: long edge ≤ 2160 px, short edge ≥ 320 px; Aspect ratio: 1:2.5 ~ 2.5:1; File size: ≤ 100MB; Frame rate: > 8 fps; Video URL must be publicly accessible (HTTP or HTTPS); private OSS, intranet, or authenticated links are not supported Compatible fields: video_url / video are also accepted (lower priority than video…\",\"minItems\":1,\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL array, optional, 0 ~ 5 images Used for style / subject guidance. Image requirements: Supported formats: JPEG, JPG, PNG, WEBP; Resolution: width and height ≥ 300 px; Aspect ratio: 1:2.5 ~ 2.5:1; File size: ≤ 10MB; Image URLs must be publicly accessible (HTTP or HTTPS)\",\"maxItems\":5,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"keep_original_sound\":{\"type\":\"boolean\",\"description\":\"Whether to keep the original audio of the input video, defaults to false Options: true: Keep the original audio of the input video; false: Discard the original audio; the model generates new audio\",\"default\":false},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution tier, defaults to 720p Options: 720p: Standard clarity, this is the default; 1080p: HD clarity Billing note: Resolution tier directly affects billing\",\"enum\":[\"720p\",\"1080p\"],\"default\":\"720p\"},\"seed\":{\"type\":\"integer\",\"description\":\"Random seed, default is random Details: Range: 1 ~ 2147483647; A fixed seed reduces parameter-induced variation when iterating on prompts and improves reproducibility\",\"minimum\":1,\"maximum\":2147483647}},\"example\":{\"prompt\":\"Have the character in the video wear the striped sweater from the image\",\"video_urls\":[\"https://cdn.example.com/source.mp4\"],\"image_urls\":[\"https://cdn.example.com/sweater.jpg\"],\"quality\":\"720p\",\"keep_original_sound\":true}},\"happyhorse-1.1-image-to-video\":{\"model\":\"happyhorse-1.1-image-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"HappyHorse 1.1 Image-to-Video\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/happyhorse1.1/happyhorse-1.1-image-to-video\",\"required\":[\"image_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt, optional (when omitted, the first frame drives free interpretation) Length limits: Chinese: up to 2500 characters; Non-Chinese: up to 5000 characters; Excess content is automatically truncated\"},\"image_urls\":{\"type\":\"array\",\"description\":\"First-frame image URL, required (the first item of the array is taken as the first frame) Image requirements: Supported formats: JPEG, JPG, PNG, WEBP; Resolution: width and height ≥ 300 px; Aspect ratio: 1:2.5 ~ 2.5:1; File size: ≤ 10MB; Image URLs must be publicly accessible (HTTP or HTTPS); private OSS, intranet, or authenticated links are not supported\",\"minItems\":1,\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution tier, defaults to 720p Options: 720p: Standard clarity, this is the default; 1080p: HD clarity Billing note: Resolution tier directly affects billing\",\"enum\":[\"720p\",\"1080p\"],\"default\":\"720p\"},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds), defaults to 5 seconds Range: Integer 3 ~ 15; Duration directly affects billing\",\"default\":5,\"minimum\":3,\"maximum\":15},\"seed\":{\"type\":\"integer\",\"description\":\"Random seed, default is random Details: Range: 1 ~ 2147483647; A fixed seed reduces parameter-induced variation when iterating on prompts and improves reproducibility\",\"minimum\":1,\"maximum\":2147483647}},\"example\":{\"prompt\":\"Make the cat in the picture run on the grass\",\"image_urls\":[\"https://cdn.example.com/cat.png\"],\"quality\":\"720p\",\"duration\":5}},\"happyhorse-1.1-reference-to-video\":{\"model\":\"happyhorse-1.1-reference-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"HappyHorse 1.1 Reference-to-Video\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/happyhorse1.1/happyhorse-1.1-reference-to-video\",\"required\":[\"prompt\",\"image_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt, required Length limits: Chinese: up to 2500 characters; Non-Chinese: up to 5000 characters; Excess content is automatically truncated Character reference convention (important): The prompt must explicitly use character1, character2, character3 ... keywords to reference images in image_urls in order; The 1st image corresponds to character1, the 2nd to character2, and so on; Missing explicit references may cause character confusion\",\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL array, required, 1 ~ 9 images Image requirements: Supported formats: JPEG, JPG, PNG, WEBP; Resolution: short edge ≥ 400 px; 720P or higher quality images are recommended (avoid extremely small, blurry, or heavily compressed images); Recommended aspect ratio: short edge / long edge ≥ 0.4, with consistent proportions across images (close to the target video ratio); File size: ≤ 10MB per image; Image URLs must be publicly accessible (HTTP or HTTPS); private OSS, intranet, or authenticated links are not supported Order: Array order corresponds to character1, character2 ... ref…\",\"minItems\":1,\"maxItems\":9,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution tier, defaults to 720p Options: 720p: Standard clarity, this is the default; 1080p: HD clarity Billing note: Resolution tier directly affects billing\",\"enum\":[\"720p\",\"1080p\"],\"default\":\"720p\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio, defaults to 16:9 Options: 16:9 (landscape); 9:16 (portrait); 1:1 (square); 4:3; 3:4; 4:5; 5:4; 9:21; 21:9\",\"enum\":[\"16:9\",\"9:16\",\"1:1\",\"4:3\",\"3:4\",\"4:5\",\"5:4\",\"9:21\",\"21:9\"],\"default\":\"16:9\"},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds), defaults to 5 seconds Range: Integer 3 ~ 15; Duration directly affects billing\",\"default\":5,\"minimum\":3,\"maximum\":15},\"seed\":{\"type\":\"integer\",\"description\":\"Random seed, default is random Details: Range: 1 ~ 2147483647; A fixed seed reduces parameter-induced variation when iterating on prompts and improves reproducibility\",\"minimum\":1,\"maximum\":2147483647}},\"example\":{\"prompt\":\"A woman in a red qipao character1, the camera first frames the slim cut of the qipao from a side medium shot, then switches to a low-angle upward shot capturing details as she gracefully lifts her hand to open a folding fan character2, with tasseled earrings character3 swaying lightly as she turns her head.\",\"image_urls\":[\"https://cdn.example.com/girl.jpg\",\"https://cdn.example.com/folding-fan.jpg\",\"https://cdn.example.com/earrings.jpg\"],\"quality\":\"720p\",\"aspect_ratio\":\"16:9\",\"duration\":5}},\"happyhorse-1.1-text-to-video\":{\"model\":\"happyhorse-1.1-text-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"HappyHorse 1.1 Text-to-Video\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/happyhorse1.1/happyhorse-1.1-text-to-video\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt, required Length limits: Chinese: up to 2500 characters; Non-Chinese: up to 5000 characters; Excess content is automatically truncated Prompt tips: Detailed shot-by-shot descriptions yield better multi-shot narrative results; Example: Shot 1 [0~3s] wide angle: ...; Shot 2 [3~6s] medium shot: ...\",\"required\":true},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution tier, defaults to 720p Options: 720p: Standard clarity, this is the default; 1080p: HD clarity Billing note: Resolution tier directly affects billing\",\"enum\":[\"720p\",\"1080p\"],\"default\":\"720p\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio, defaults to 16:9 Options: 16:9 (landscape); 9:16 (portrait); 1:1 (square); 4:3; 3:4; 4:5; 5:4; 9:21; 21:9\",\"enum\":[\"16:9\",\"9:16\",\"1:1\",\"4:3\",\"3:4\",\"4:5\",\"5:4\",\"9:21\",\"21:9\"],\"default\":\"16:9\"},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds), defaults to 5 seconds Range: Integer 3 ~ 15; Duration directly affects billing\",\"default\":5,\"minimum\":3,\"maximum\":15},\"seed\":{\"type\":\"integer\",\"description\":\"Random seed, default is random Details: Range: 1 ~ 2147483647; A fixed seed reduces parameter-induced variation when iterating on prompts and improves reproducibility\",\"minimum\":1,\"maximum\":2147483647}},\"example\":{\"prompt\":\"A miniature city built from cardboard and bottle caps comes to life at night. A cardboard train slowly passes through, dotted with tiny lights illuminating the path ahead.\",\"quality\":\"720p\",\"aspect_ratio\":\"16:9\",\"duration\":5,\"seed\":42}},\"kling-custom-element\":{\"model\":\"kling-custom-element\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"kling-custom-element API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/kling/kling-custom-element\",\"required\":[\"model_params\"],\"params\":{\"model_params\":{\"type\":\"object\",\"description\":\"Model parameters\",\"properties\":{\"element_name\":{\"type\":\"string\",\"description\":\"Subject element name Note: Maximum 20 characters\",\"maxLength\":20,\"required\":true},\"element_description\":{\"type\":\"string\",\"description\":\"Subject element description, helps the model understand the subject's appearance features Note: Maximum 100 characters\",\"maxLength\":100,\"required\":true},\"reference_type\":{\"type\":\"string\",\"description\":\"Reference material type | Value | Description | |---|---| | image_refer | Create subject using reference images | | video_refer | Create subject using reference video |\",\"enum\":[\"image_refer\",\"video_refer\"],\"required\":true},\"element_image_list\":{\"type\":\"object\",\"description\":\"Reference image list for creating subject elements. Required when reference_type = image_refer Note: It is recommended to use clear, well-lit images with a prominent subject; Image dimensions: width and height ≥ 300px, aspect ratio between 1:2.5 and 2.5:1; frontal_image (required): Frontal reference image URL; refer_images (required): Other-angle reference image list (1 to 3 items), each item contains an image_url field; Both frontal_image and refer_images are mandatory, omitting either one will cause the request to fail\",\"properties\":{\"frontal_image\":{\"type\":\"string\",\"description\":\"Frontal reference image URL (required), must be directly accessible by the server or trigger a direct download when accessed\",\"format\":\"uri\",\"required\":true},\"refer_images\":{\"type\":\"array\",\"description\":\"Other-angle reference image list (1 to 3 items), image URLs must be directly accessible by the server or trigger a direct download when accessed\",\"minItems\":1,\"maxItems\":3,\"items\":{\"type\":\"object\",\"properties\":{\"image_url\":{\"type\":\"string\",\"description\":\"Reference image URL, must be directly accessible by the server or trigger a direct download when accessed\",\"format\":\"uri\",\"required\":true}}},\"required\":true}}},\"element_video_list\":{\"type\":\"object\",\"description\":\"Reference video for creating subject elements. Required when reference_type = video_refer Note: refer_videos (required): must contain exactly 1 item, each item contains a video_url field; The reference video must contain a clearly visible human face, with no character transition; Video requirements: duration ≤ 8 seconds, width between 720px and 2160px\",\"properties\":{\"refer_videos\":{\"type\":\"array\",\"description\":\"Reference video list, must contain exactly 1 item\",\"minItems\":1,\"maxItems\":1,\"items\":{\"type\":\"object\",\"properties\":{\"video_url\":{\"type\":\"string\",\"description\":\"Reference video URL, must be directly accessible by the server\",\"format\":\"uri\",\"required\":true}}},\"required\":true}}},\"element_voice_id\":{\"type\":\"string\",\"description\":\"Voice ID assigned to the element. The voice will be used when the element speaks in generated videos Note: Only supported when reference_type = video_refer; Not available for image_refer\"}},\"required\":true}},\"example\":{\"model_params\":{\"element_name\":\"My Character\",\"element_description\":\"A young male character with short hair, wearing a white T-shirt\",\"reference_type\":\"image_refer\",\"element_image_list\":{\"frontal_image\":\"https://example.com/front.jpg\",\"refer_images\":[{\"image_url\":\"https://example.com/side.jpg\"}]}}}},\"kling-o1-image-to-video\":{\"model\":\"kling-o1-image-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"kling-o1-image-to-video API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/kling/kling-o1-image-to-video\",\"required\":[\"prompt\",\"image_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing what video to generate\",\"maxLength\":5000,\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL list for image-to-video generation Note: Supports 1 to 2 images per request (1 image for first-frame video generation, 2 images for first-and-last-frame video generation); Image size: up to 10MB; Supported formats: .jpg, .jpeg, .png, .webp; Image URL must be directly accessible by the server, or the URL should trigger a direct download when accessed (typically URLs ending with image extensions like .png, .jpg)\",\"minItems\":1,\"maxItems\":2,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio Options: 16:9: Landscape video; 9:16: Portrait video; 1:1: Square video\",\"enum\":[\"16:9\",\"9:16\",\"1:1\"]},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration in seconds, defaults to 5 seconds Note: Only supports 5 or 10 values, representing 5 seconds or 10 seconds; Billing is based on the duration value, longer duration costs more\",\"enum\":[5,10],\"default\":5}},\"example\":{\"prompt\":\"A cat walking gracefully\",\"image_urls\":[\"https://example.com/first-frame.jpg\"]}},\"kling-o1-video-edit\":{\"model\":\"kling-o1-video-edit\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"kling-o1-video-edit API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/kling/kling-o1-video-edit\",\"required\":[\"prompt\",\"video_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing how to edit the video\",\"maxLength\":5000,\"required\":true},\"video_urls\":{\"type\":\"array\",\"description\":\"Original video URL list for editing Note: Only 1 video per request; Supported video duration: 3 to 10 seconds (videos under 3 seconds are billed as 3 seconds, videos over 10 seconds are billed as 10 seconds); Video size: up to 100MB; Supported formats: .mp4, .mov; Video URL must be directly accessible by the server\",\"minItems\":1,\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL list for specifying editing effect Note: Supports up to 4 reference images per request; Image size: up to 10MB; Supported formats: .jpg, .jpeg, .png, .webp; Image URL must be directly accessible by the server\",\"minItems\":1,\"maxItems\":4,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"keep_original_sound\":{\"type\":\"boolean\",\"description\":\"Whether to keep the original video sound Options: true: Keep the original video sound; false: Do not keep the original video sound\"}},\"example\":{\"prompt\":\"Make the video more cinematic\",\"video_urls\":[\"https://example.com/original-video.mp4\"]}},\"kling-o1-video-edit-fast\":{\"model\":\"kling-o1-video-edit-fast\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"kling-o1-video-edit-fast API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/kling/kling-o1-video-edit-fast\",\"required\":[\"prompt\",\"video_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing how to edit the video\",\"maxLength\":5000,\"required\":true},\"video_urls\":{\"type\":\"array\",\"description\":\"Original video URL list for editing Note: Only 1 video per request; Supported video duration: 6 to 20 seconds (videos under 6 seconds are billed as 6 seconds, videos over 20 seconds are billed as 20 seconds); Video size: up to 100MB; Supported formats: .mp4, .mov; Video URL must be directly accessible by the server\",\"minItems\":1,\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL list for specifying editing effect Note: Supports up to 4 reference images per request; Image size: up to 10MB; Supported formats: .jpg, .jpeg, .png, .webp; Image URL must be directly accessible by the server\",\"minItems\":1,\"maxItems\":4,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"keep_original_sound\":{\"type\":\"boolean\",\"description\":\"Whether to keep the original video sound Options: true: Keep the original video sound; false: Do not keep the original video sound\"}},\"example\":{\"prompt\":\"Make the video more cinematic\",\"video_urls\":[\"https://example.com/original-video.mp4\"]}},\"kling-o3-image-to-video\":{\"model\":\"kling-o3-image-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"kling-o3-image-to-video API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/kling/kling-o3-image-to-video\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt. Required when multi_shot=false (default), provided by multi_prompt for each shot when multi_shot=true Note: Maximum 2500 characters; Use <<<element_1>>> to reference elements, <<<image_1>>> to reference images\",\"maxLength\":2500,\"required\":true},\"image_start\":{\"type\":\"string\",\"description\":\"First frame image URL Image format requirements: Format: JPG / JPEG / PNG; Size: <= 10MB; Dimensions: width and height >= 300px, aspect ratio between 1:2.5 and 2.5:1; Image URL must be directly accessible by the server or trigger a direct download when accessed\",\"format\":\"uri\"},\"image_end\":{\"type\":\"string\",\"description\":\"Last frame image URL Constraints: Last frame requires a first frame; Last frame not supported when total image count exceeds 2; Image URL must be directly accessible by the server or trigger a direct download when accessed\",\"format\":\"uri\"},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL array (not first/last frame, for style/scene/element reference) Note: Image URLs must be directly accessible by the server or trigger a direct download when accessed\",\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds), integer in range 3-15\",\"default\":5,\"minimum\":3,\"maximum\":15},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio\",\"enum\":[\"16:9\",\"9:16\",\"1:1\"]},\"quality\":{\"type\":\"string\",\"description\":\"Resolution tier Options: 720p: Standard 720P; 1080p: High quality 1080P; 4k: Ultra-high definition 4K\",\"enum\":[\"720p\",\"1080p\",\"4k\"]},\"sound\":{\"type\":\"string\",\"description\":\"Sound effect control\",\"enum\":[\"on\",\"off\"],\"default\":\"off\"},\"model_params\":{\"type\":\"object\",\"description\":\"Model extension parameters\",\"properties\":{\"multi_shot\":{\"type\":\"boolean\",\"description\":\"Whether to enable multi-shot mode. When enabled, the prompt parameter will be ignored — use multi_prompt to define content for each shot instead. The sum of all shot duration values must equal the total video duration\"},\"shot_type\":{\"type\":\"string\",\"description\":\"Shot segmentation method. Required when multi_shot=true\",\"enum\":[\"customize\"]},\"multi_prompt\":{\"type\":\"array\",\"description\":\"Shot information list. Required when multi_shot=true && shot_type=customize Format: [{\\\"index\\\": int, \\\"prompt\\\": \\\"string\\\", \\\"duration\\\": \\\"string\\\"}, ...]; Maximum 6 shots; Each shot prompt maximum 512 characters; Sum of all shot durations must equal total duration\"},\"element_list\":{\"type\":\"array\",\"description\":\"Element library list Constraints: Element count <= 3 when first frame is provided; Image count + element count <= 7 when no video; Reference in prompt using <<<element_1>>> syntax\",\"items\":{\"type\":\"object\",\"properties\":{\"element_id\":{\"type\":\"string\",\"description\":\"Element ID\"}}}},\"watermark_info\":{\"type\":\"object\",\"description\":\"Watermark configuration\",\"properties\":{\"enabled\":{\"type\":\"boolean\",\"description\":\"Whether to enable watermark\"}}}}}},\"example\":{\"prompt\":\"The person in the image slowly turns their head and smiles\",\"image_start\":\"https://example.com/portrait.jpg\",\"duration\":5,\"quality\":\"720p\"}},\"kling-o3-reference-to-video\":{\"model\":\"kling-o3-reference-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"kling-o3-reference-to-video API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/kling/kling-o3-reference-to-video\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt, max 2500 characters Reference syntax: You can reference elements, images, and videos in the prompt using <<<xxx>>> syntax, for example: <<<element_1>>> walking in the scene style of <<<video_1>>>\",\"maxLength\":2500,\"required\":true},\"video_url\":{\"type\":\"string\",\"description\":\"Reference video URL Video format requirements: Format: MP4 / MOV; Size: <= 200MB; Duration: >= 3 seconds; Dimensions: width and height 720px ~ 2160px; Frame rate: 24fps ~ 60fps; Video URL must be directly accessible by the server\",\"format\":\"uri\"},\"keep_original_sound\":{\"type\":\"boolean\",\"description\":\"Whether to keep original sound from reference video Options: true: Keep the original video sound (default); false: Do not keep the original video sound\",\"default\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL array (style/scene reference) Constraint: Image count + element count <= 4 when video is provided Note: Image URLs must be directly accessible by the server or trigger a direct download when accessed\",\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds), range 3~10 Note: Shorter than the 15-second maximum for text-to-video/image-to-video, max supported duration is 10 seconds\",\"default\":5,\"minimum\":3,\"maximum\":10},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio Options: 16:9: Landscape video; 9:16: Portrait video; 1:1: Square video\",\"enum\":[\"16:9\",\"9:16\",\"1:1\"]},\"quality\":{\"type\":\"string\",\"description\":\"Resolution tier Options: 720p: Standard 720P; 1080p: High quality 1080P\",\"enum\":[\"720p\",\"1080p\"],\"default\":\"720p\"},\"model_params\":{\"type\":\"object\",\"description\":\"Advanced parameters\",\"properties\":{\"element_list\":{\"type\":\"array\",\"description\":\"Element library list. Video character elements not supported (only multi-image elements supported) Constraint: Image count + element count <= 4 when video is provided\",\"items\":{\"type\":\"object\",\"properties\":{\"element_id\":{\"type\":\"string\",\"description\":\"Element ID\"}}}},\"watermark_info\":{\"type\":\"object\",\"description\":\"Watermark configuration\",\"properties\":{\"enabled\":{\"type\":\"boolean\",\"description\":\"Whether to enable watermark\"}}}}}},\"example\":{\"prompt\":\"Keep the same motion style, change to a snowy background\",\"video_url\":\"https://example.com/reference.mp4\",\"duration\":5,\"aspect_ratio\":\"16:9\",\"quality\":\"720p\"}},\"kling-o3-text-to-video\":{\"model\":\"kling-o3-text-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"kling-o3-text-to-video API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/kling/kling-o3-text-to-video\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing what video to generate Note: Maximum 2500 characters; Can be empty when multi_shot=true and shot_type=customize; You can reference elements using <<<element_1>>> syntax\",\"maxLength\":2500,\"required\":true},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration in seconds, defaults to 5 seconds Note: Supports integers from 3 to 15; Billing is based on the duration value, longer duration costs more\",\"default\":5,\"minimum\":3,\"maximum\":15},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio Options: 16:9: Landscape video; 9:16: Portrait video; 1:1: Square video\",\"enum\":[\"16:9\",\"9:16\",\"1:1\"],\"default\":\"16:9\"},\"quality\":{\"type\":\"string\",\"description\":\"Resolution quality Options: 720p: Standard 720P; 1080p: High quality 1080P; 4k: Ultra-high definition 4K\",\"enum\":[\"720p\",\"1080p\",\"4k\"],\"default\":\"720p\"},\"sound\":{\"type\":\"string\",\"description\":\"Sound effect control Options: on: Enable sound effects; off: Disable sound effects\",\"enum\":[\"on\",\"off\"],\"default\":\"off\"},\"model_params\":{\"type\":\"object\",\"description\":\"Model extension parameters Constraint: Maximum 7 elements\",\"properties\":{\"multi_shot\":{\"type\":\"boolean\",\"description\":\"Whether to use multi-shot mode. When enabled, the prompt parameter will be ignored — use multi_prompt to define content for each shot instead. The sum of all shot duration values must equal the total video duration\",\"default\":false},\"shot_type\":{\"type\":\"string\",\"description\":\"Shot segmentation method Options: customize: Custom shot segments; Required when multi_shot=true\",\"enum\":[\"customize\"]},\"multi_prompt\":{\"type\":\"array\",\"description\":\"Shot segment information list Note: Required when multi_shot=true and shot_type=customize; Maximum 6 shot segments\",\"maxItems\":6,\"items\":{\"type\":\"object\",\"properties\":{\"index\":{\"type\":\"integer\",\"description\":\"Shot segment index\",\"required\":true},\"prompt\":{\"type\":\"string\",\"description\":\"Shot segment description\",\"required\":true},\"duration\":{\"type\":\"string\",\"description\":\"Shot segment duration (seconds)\",\"required\":true}}}},\"element_list\":{\"type\":\"array\",\"description\":\"Element library list Constraint: Maximum 7 elements; Reference in prompt using <<<element_1>>> syntax\",\"maxItems\":7,\"items\":{\"type\":\"object\",\"properties\":{\"element_id\":{\"type\":\"string\",\"description\":\"Element ID\",\"required\":true}}}},\"watermark_info\":{\"type\":\"object\",\"description\":\"Watermark configuration\",\"properties\":{\"enabled\":{\"type\":\"boolean\",\"description\":\"Whether to enable watermark\"}}}}}},\"example\":{\"prompt\":\"A cat running on a grassy field under bright sunshine\",\"duration\":5,\"aspect_ratio\":\"16:9\",\"quality\":\"720p\"}},\"kling-o3-video-edit\":{\"model\":\"kling-o3-video-edit\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"kling-o3-video-edit API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/kling/kling-o3-video-edit\",\"required\":[],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Edit instruction, max 2500 characters Reference syntax: You can reference elements, images, and videos in the prompt using <<<xxx>>> syntax, for example: Replace the person in the video with <<<element_1>>>\",\"maxLength\":2500},\"video_url\":{\"type\":\"string\",\"description\":\"Video URL to edit Video format requirements: Format: MP4 / MOV; Size: <= 200MB; Duration: >= 3 seconds; Dimensions: width and height 720px ~ 2160px; Frame rate: 24fps ~ 60fps Constraints: First/last frame not supported; Reference image count + element count <= 4 when video is provided; Video character elements not supported (only multi-image elements supported); Video URL must be directly accessible by the server\",\"format\":\"uri\"},\"keep_original_sound\":{\"type\":\"boolean\",\"description\":\"Whether to keep original video sound Note: true: Keep the original video sound (default); false: Do not keep the original video sound\",\"default\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL array (style reference) Constraint: Reference image count + element count <= 4 when video is provided Note: Image URLs must be directly accessible by the server or trigger a direct download when accessed\",\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"quality\":{\"type\":\"string\",\"description\":\"Resolution quality Options: 720p: Standard 720P; 1080p: High quality 1080P Billing: Base unit price 81,000 UC/second x input video duration (rounded up). 1080p multiplier 1.334\",\"enum\":[\"720p\",\"1080p\"],\"default\":\"720p\"},\"model_params\":{\"type\":\"object\",\"description\":\"Advanced parameters\",\"properties\":{\"element_list\":{\"type\":\"array\",\"description\":\"Element library list. Video character elements not supported (only multi-image elements supported) Constraint: Reference image count + element count <= 4 when video is provided\",\"items\":{\"type\":\"object\",\"properties\":{\"element_id\":{\"type\":\"string\",\"description\":\"Element ID\"}}}},\"watermark_info\":{\"type\":\"object\",\"description\":\"Watermark configuration\",\"properties\":{\"enabled\":{\"type\":\"boolean\",\"description\":\"Whether to enable watermark\"}}}}}},\"example\":{\"prompt\":\"Adjust the color to warm tones and add a cinematic feel\",\"video_url\":\"https://example.com/original.mp4\",\"quality\":\"720p\",\"keep_original_sound\":true}},\"kling-v2.6-motion-control\":{\"model\":\"kling-v2.6-motion-control\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"kling-v2.6-motion-control API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/kling/kling-v2.6-motion-control\",\"required\":[\"image_urls\",\"video_urls\",\"model_params\"],\"params\":{\"image_urls\":{\"type\":\"array\",\"description\":\"Array of reference image URLs, used to provide the appearance source of the character/object Note: Provide one reference image; Image size: no larger than 10MB; Supported file formats: .jpg, .jpeg, .png; Image dimensions: width and height ≥ 300px, aspect ratio between 1:2.5 and 2.5:1; Image URL must be directly accessible by the server\",\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"video_urls\":{\"type\":\"array\",\"description\":\"Array of reference video URLs to provide motion trajectory Note: Provide one reference video; Video duration: 3 to 30 seconds; Supported formats: .mp4, .mov; Video size: up to 100MB; Video dimensions: width and height between 340px and 3850px; Avoid cuts, fast motion, and scene changes; The video URL must be directly accessible by the server\",\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt (optional), used to guide the generated content Note: Maximum 2500 characters; Can be left empty; the model will automatically generate based on the reference image and video\",\"maxLength\":2500},\"quality\":{\"type\":\"string\",\"description\":\"Resolution tier Details: 720p: Standard quality (std); 1080p: High quality (pro) Billing: 1080p costs 1.6× the 720p per-second rate\",\"enum\":[\"720p\",\"1080p\"],\"default\":\"720p\"},\"model_params\":{\"type\":\"object\",\"description\":\"Model-specific parameters (required), used for motion control configuration\",\"properties\":{\"character_orientation\":{\"type\":\"string\",\"description\":\"Controls the facing direction of the generated character. Values: image: Character faces the same direction as the reference image (max 10 seconds); video: Character faces the same direction as the reference video (max 30 seconds)\",\"enum\":[\"image\",\"video\"],\"required\":true},\"keep_sound\":{\"type\":\"boolean\",\"description\":\"Whether to keep the original sound from the reference video Details: true: Keep original sound (default); false: Mute\",\"default\":true},\"watermark_info\":{\"type\":\"object\",\"description\":\"Watermark configuration\",\"properties\":{\"enabled\":{\"type\":\"boolean\",\"description\":\"Whether to enable watermark\"}}}},\"required\":true}},\"example\":{\"prompt\":\"A girl dancing gracefully\",\"image_urls\":[\"https://example.com/character.jpg\"],\"video_urls\":[\"https://example.com/dance-reference.mp4\"],\"quality\":\"720p\",\"model_params\":{\"character_orientation\":\"image\"}}},\"kling-v3-image-to-video\":{\"model\":\"kling-v3-image-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"kling-v3-image-to-video API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/kling/kling-v3-image-to-video\",\"required\":[\"image_start\"],\"params\":{\"image_start\":{\"type\":\"string\",\"description\":\"First frame image URL for image-to-video generation (required) Note: Image size: up to 10MB; Supported formats: .jpg, .jpeg, .png; Image dimensions: width and height >= 300px, aspect ratio between 1:2.5 and 2.5:1; Image URL must be directly accessible by the server or trigger a direct download when accessed\",\"format\":\"uri\",\"required\":true},\"image_end\":{\"type\":\"string\",\"description\":\"Last frame image URL Note: image_start (first frame) must be provided when using last frame; Supported formats: .jpg, .jpeg, .png; Image size: up to 10MB; Image URL must be directly accessible by the server or trigger a direct download when accessed\",\"format\":\"uri\"},\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing what video to generate Note: Maximum 2500 characters; Can be empty when multi_shot=true and shot_type=customize; Use <<<element_1>>> reference syntax to reference elements in the prompt\",\"maxLength\":2500},\"negative_prompt\":{\"type\":\"string\",\"description\":\"Negative prompt describing content you do not want in the video\"},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration in seconds, defaults to 5 seconds Note: Range: integer from 3 to 15; Billing is based on the duration value, longer duration costs more\",\"default\":5,\"minimum\":3,\"maximum\":15},\"quality\":{\"type\":\"string\",\"description\":\"Resolution tier Options: 720p: Standard quality (std); 1080p: High quality (pro); 4k: Ultra-high definition 4K\",\"enum\":[\"720p\",\"1080p\",\"4k\"],\"default\":\"720p\"},\"sound\":{\"type\":\"string\",\"description\":\"Sound effect control Options: on: Generate sound effects; off: No sound effects\",\"enum\":[\"on\",\"off\"],\"default\":\"off\"},\"model_params\":{\"type\":\"object\",\"description\":\"Advanced parameters for multi-shot, element control, and watermark\",\"properties\":{\"multi_shot\":{\"type\":\"boolean\",\"description\":\"Whether to enable multi-shot mode Options: true: Multi-shot mode, must be used with shot_type. When shot_type=customize, the prompt parameter will be ignored — use multi_prompt to define content for each shot instead; when shot_type=intelligence, prompt remains effective. The sum of all shot duration values must equal the total video duration; false: Single-shot mode (default)\",\"default\":false},\"shot_type\":{\"type\":\"string\",\"description\":\"Shot segmentation method, required when multi_shot=true Options: customize: Custom shots, requires multi_prompt; intelligence: Intelligent shots, model automatically segments shots\",\"enum\":[\"customize\",\"intelligence\"]},\"multi_prompt\":{\"type\":\"array\",\"description\":\"Shot information list, required when multi_shot=true and shot_type=customize Note: Maximum 6 shots, minimum 1; Each shot prompt is up to 512 characters; Each shot duration >= 1 and <= total duration; The sum of all shot durations must equal the total task duration\",\"minItems\":1,\"maxItems\":6,\"items\":{\"type\":\"object\",\"properties\":{\"index\":{\"type\":\"integer\",\"description\":\"Shot sequence number, starting from 1\",\"required\":true},\"prompt\":{\"type\":\"string\",\"description\":\"Text description for this shot\",\"maxLength\":512,\"required\":true},\"duration\":{\"type\":\"string\",\"description\":\"Duration of this shot (seconds)\",\"required\":true}}}},\"element_list\":{\"type\":\"array\",\"description\":\"Element library list for referencing preset elements in the video Note: Maximum 3 elements; Use <<<element_1>>> reference syntax in the prompt to reference elements\",\"maxItems\":3,\"items\":{\"type\":\"object\",\"properties\":{\"element_id\":{\"type\":\"string\",\"description\":\"Element ID\",\"required\":true}}}},\"watermark_info\":{\"type\":\"object\",\"description\":\"Watermark configuration\",\"properties\":{\"enabled\":{\"type\":\"boolean\",\"description\":\"Whether to enable watermark\"}}}}}},\"example\":{\"prompt\":\"The person in the scene slowly turns their head and smiles\",\"image_start\":\"https://example.com/portrait.jpg\",\"duration\":5,\"quality\":\"720p\"}},\"kling-v3-motion-control\":{\"model\":\"kling-v3-motion-control\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"kling-v3-motion-control API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/kling/kling-v3-motion-control\",\"required\":[\"image_urls\",\"video_urls\",\"model_params\"],\"params\":{\"image_urls\":{\"type\":\"array\",\"description\":\"Array of reference image URLs, used to provide the appearance source of the character/object Note: Provide one reference image; Image size: no larger than 10MB; Supported file formats: .jpg, .jpeg, .png; Image dimensions: width and height ≥ 300px, aspect ratio between 1:2.5 and 2.5:1; Image URL must be directly accessible by the server\",\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"video_urls\":{\"type\":\"array\",\"description\":\"Array of reference video URLs to provide motion trajectory Note: Provide one reference video; Video duration: 3 to 30 seconds; Video size: up to 100MB; Video dimensions: width and height between 340px and 3850px; Avoid cuts, fast motion, and scene changes; The video URL must be directly accessible by the server\",\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt (optional), used to guide the generated content Note: Maximum 2500 characters; Can be left empty; the model will automatically generate based on the reference image and video\",\"maxLength\":2500},\"quality\":{\"type\":\"string\",\"description\":\"Resolution tier Details: 720p: Standard quality (std); 1080p: High quality (pro)\",\"enum\":[\"720p\",\"1080p\"],\"default\":\"720p\"},\"model_params\":{\"type\":\"object\",\"description\":\"Model-specific parameters (required), used for motion control configuration\",\"properties\":{\"character_orientation\":{\"type\":\"string\",\"description\":\"Controls the facing direction of the generated character. Values: image: Character faces the same direction as the reference image (max 10 seconds); video: Character faces the same direction as the reference video (max 30 seconds) Note: When using element_list, only video is supported\",\"enum\":[\"image\",\"video\"],\"required\":true},\"element_list\":{\"type\":\"array\",\"description\":\"Subject element list, used to specify the character/object to control Note: Maximum 1 subject element (Motion Control limitation); element_id: Subject element ID; Only supports elements created via video_refer reference type (image_refer is not supported)\",\"maxItems\":1,\"items\":{\"type\":\"object\",\"properties\":{\"element_id\":{\"type\":\"string\",\"description\":\"Subject element ID\",\"required\":true}}}},\"keep_sound\":{\"type\":\"boolean\",\"description\":\"Whether to keep the original sound from the reference video Details: true: Keep original sound (default); false: Mute\",\"default\":true},\"watermark_info\":{\"type\":\"object\",\"description\":\"Watermark configuration\",\"properties\":{\"enabled\":{\"type\":\"boolean\",\"description\":\"Whether to enable watermark\"}}}},\"required\":true}},\"example\":{\"prompt\":\"A girl dancing gracefully\",\"image_urls\":[\"https://example.com/character.jpg\"],\"video_urls\":[\"https://example.com/dance-reference.mp4\"],\"quality\":\"720p\",\"model_params\":{\"character_orientation\":\"image\"}}},\"kling-v3-text-to-video\":{\"model\":\"kling-v3-text-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"kling-v3-text-to-video API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/kling/kling-v3-text-to-video\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing what video to generate Note: Maximum 2500 characters; Can be empty when multi_shot=true and shot_type=customize (content provided by multi_prompt); Required when multi_shot=false or shot_type=intelligence\",\"maxLength\":2500,\"required\":true},\"negative_prompt\":{\"type\":\"string\",\"description\":\"Negative prompt describing what should not appear in the video\"},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration in seconds, defaults to 5 seconds Note: Range: integer from 3 to 15; Billing is based on the duration value, longer duration costs more\",\"default\":5,\"minimum\":3,\"maximum\":15},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio Options: 16:9: Landscape video; 9:16: Portrait video; 1:1: Square video\",\"enum\":[\"16:9\",\"9:16\",\"1:1\"]},\"quality\":{\"type\":\"string\",\"description\":\"Resolution quality Options: 720p: Standard quality (std); 1080p: High quality (pro); 4k: Ultra-high definition 4K\",\"enum\":[\"720p\",\"1080p\",\"4k\"],\"default\":\"720p\"},\"sound\":{\"type\":\"string\",\"description\":\"Sound effect control Options: on: Generate sound effects; off: No sound effects\",\"enum\":[\"on\",\"off\"],\"default\":\"off\"},\"model_params\":{\"type\":\"object\",\"description\":\"Model extension parameters for multi-shot and watermark control\",\"properties\":{\"multi_shot\":{\"type\":\"boolean\",\"description\":\"Whether to use multi-shot mode Options: true: Multi-shot mode, must be used with shot_type. When shot_type=customize, the prompt parameter will be ignored — use multi_prompt to define content for each shot instead; when shot_type=intelligence, prompt remains effective. The sum of all shot duration values must equal the total video duration; false: Single-shot mode (default)\",\"default\":false},\"shot_type\":{\"type\":\"string\",\"description\":\"Shot segmentation method, required when multi_shot=true Options: customize: Custom segmentation, requires multi_prompt; intelligence: Intelligent segmentation, model automatically segments shots\",\"enum\":[\"customize\",\"intelligence\"]},\"multi_prompt\":{\"type\":\"array\",\"description\":\"Shot information list, required when multi_shot=true and shot_type=customize Note: Maximum 6 shots, minimum 1; Each shot prompt supports up to 512 characters; Each shot duration must be >= 1 and <= total duration; The sum of all shot durations must equal the total task duration\",\"minItems\":1,\"maxItems\":6,\"items\":{\"type\":\"object\",\"properties\":{\"index\":{\"type\":\"integer\",\"description\":\"Shot sequence number, starting from 1\",\"required\":true},\"prompt\":{\"type\":\"string\",\"description\":\"Text description for this shot\",\"maxLength\":512,\"required\":true},\"duration\":{\"type\":\"string\",\"description\":\"Duration of this shot (seconds)\",\"required\":true}}}},\"watermark_info\":{\"type\":\"object\",\"description\":\"Watermark configuration\",\"properties\":{\"enabled\":{\"type\":\"boolean\",\"description\":\"Whether to enable watermark\"}}}}}},\"example\":{\"prompt\":\"A cat running on a grass field under bright sunshine\",\"duration\":5,\"aspect_ratio\":\"16:9\",\"quality\":\"720p\"}},\"kling-v3-turbo-image-to-video\":{\"model\":\"kling-v3-turbo-image-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"kling-v3-turbo-image-to-video API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/kling/kling-v3-turbo-image-to-video\",\"required\":[\"image_start\"],\"params\":{\"image_start\":{\"type\":\"string\",\"description\":\"First-frame image URL, used as the first frame of the video Image Requirements: Formats: .jpg / .jpeg / .png; Size: <= 50MB; Dimensions: width and height both >= 300px; Aspect ratio: between 1:2.5 and 2.5:1 The video aspect ratio is determined by the first-frame image\",\"format\":\"uri\",\"required\":true},\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing the desired motion or changes in the scene (optional)\",\"maxLength\":2500},\"quality\":{\"type\":\"string\",\"description\":\"Resolution tier Options: 720p: Standard quality; 1080p: High quality; 4k not supported\",\"enum\":[\"720p\",\"1080p\"],\"default\":\"720p\"},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration in seconds, defaults to 5 seconds Note: Range: integer from 3 to 15; Billing is based on the duration value, longer duration costs more\",\"default\":5,\"minimum\":3,\"maximum\":15}},\"example\":{\"image_start\":\"https://your-cdn.com/start-frame.jpg\",\"prompt\":\"A gentle breeze sweeps across the scene, bringing a subtle sense of motion\",\"quality\":\"720p\",\"duration\":5}},\"kling-v3-turbo-text-to-video\":{\"model\":\"kling-v3-turbo-text-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"kling-v3-turbo-text-to-video API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/kling/kling-v3-turbo-text-to-video\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing what video to generate Note: Recommended no more than 2500 characters; Multi-shot (optional): use 镜头 n, m, words; in the prompt to describe shots — n is the shot sequence number (up to 6), m is the duration of that shot (the sum of all shot durations must equal the total duration), and words is the shot prompt (<= 512 characters). For example: 镜头 1, 3, the girl walks toward the window; 镜头 2, 2, the camera zooms into her profile;\",\"maxLength\":2500,\"required\":true},\"quality\":{\"type\":\"string\",\"description\":\"Resolution tier Options: 720p: Standard quality; 1080p: High quality; 4k not supported\",\"enum\":[\"720p\",\"1080p\"],\"default\":\"720p\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio Options: 16:9: Landscape video; 9:16: Portrait video; 1:1: Square video\",\"enum\":[\"16:9\",\"9:16\",\"1:1\"],\"default\":\"16:9\"},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration in seconds, defaults to 5 seconds Note: Range: integer from 3 to 15; Billing is based on the duration value, longer duration costs more\",\"default\":5,\"minimum\":3,\"maximum\":15}},\"example\":{\"prompt\":\"A golden retriever running on a sunlit grass field, cinematic slow motion\",\"quality\":\"720p\",\"aspect_ratio\":\"16:9\",\"duration\":5}},\"krea-2-turbo\":{\"model\":\"krea-2-turbo\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"krea-2-turbo Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/krea/krea-2-turbo-image-generate\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the image to be generated. English works best, with a maximum length of 640 tokens\",\"required\":true},\"size\":{\"type\":\"string\",\"description\":\"Aspect ratio of the generated image; defaults to 1:1 when omitted. The actual output pixels are determined jointly by size and quality. Supported ratios (11 total): 1:1, 4:3, 3:4, 5:4, 4:5, 2:3, 3:2, 9:16, 16:9, 1:2, 2:1 Output pixel reference (size × quality): | Ratio | 1K | 2K | |---|---|---| | 1:1 | 1024×1024 | 2048×2048 | | 4:3 | 1152×896 | 2304×1728 | | 3:4 | 896×1152 | 1728×2304 | | 5:4 | 1152×896 | 2240×1792 | | 4:5 | 896×1152 | 1792×2240 | | 2:3 | 832×1280 | 1664×2496 | | 3:2 | 1280×832 | 2496×1664 | | 9:16 | 768×1344 | 1472×2688 | | 16:9 | 1344×768 | 2688×1472 | | 1:2 | 704×1472 | 14…\",\"enum\":[\"1:1\",\"4:3\",\"3:4\",\"5:4\",\"4:5\",\"2:3\",\"3:2\",\"9:16\",\"16:9\",\"1:2\",\"2:1\"],\"default\":\"1:1\"},\"quality\":{\"type\":\"string\",\"description\":\"Output resolution tier 1K / 2K; defaults to 1K when omitted. 2K produces higher-resolution images than 1K. Billing differs by tier — see the pricing page\",\"enum\":[\"1K\",\"2K\"],\"default\":\"1K\"},\"seed\":{\"type\":\"integer\",\"description\":\"Random seed for generating similar compositions Note: Range: 0 to 1048576; 0 or empty uses a random seed; Same seed with same prompt may reproduce the same composition\",\"minimum\":0,\"maximum\":1048576},\"nsfw_check\":{\"type\":\"boolean\",\"description\":\"Enable additional NSFW content moderation Note: Default: false (disabled); Basic content moderation is always active even when disabled; Enable for stricter content filtering\",\"default\":false}},\"example\":{\"prompt\":\"A cinematic product poster, silver headphones floating against a deep matte-black backdrop with soft rim lighting\",\"size\":\"16:9\",\"quality\":\"1K\"}},\"minimax-h3-image-to-video\":{\"model\":\"minimax-h3-image-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Minimax H3 Image-to-Video\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/minimax/minimax-h3/h3/minimax-h3-image-to-video\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Describe how the input image should move, how the camera should change, and the desired video content. Prompt requirements: Required and cannot be empty; Chinese and English are supported; Maximum length 7000 characters (Chinese and English are both counted by character); The model may ignore some details in an overly long prompt Input restrictions: Use image_start and/or image_end to provide keyframes; image_urls, video_urls, and audio_urls are not supported; supplying them returns a parameter error\",\"minLength\":1,\"maxLength\":7000,\"required\":true},\"image_start\":{\"type\":\"string\",\"description\":\"HTTP(S) URL of the first-frame image. Combination rules: Provide at least one of image_start and image_end; image_start only: first-frame image-to-video; Both fields: first-and-last-frame image-to-video; At most 1 first frame; this field accepts one URL Image requirements: Formats: JPG, JPEG, PNG, WEBP, HEIC, HEIF; File size: no more than 30MB; Width and height: each from 256 to 5760 px; Aspect ratio (width/height): 0.4–2.5; The URL must use HTTP(S) and be directly accessible by the service; The complete JSON request body must not exceed 64MB; Base64 and mm_file:// inputs are not accepted\",\"format\":\"uri\"},\"image_end\":{\"type\":\"string\",\"description\":\"HTTP(S) URL of the last-frame image. Combination rules: Provide at least one of image_end and image_start; image_end only: the model generates natural motion that ends on this frame; Both fields: first-and-last-frame image-to-video; At most 1 last frame; this field accepts one URL Image requirements: Formats: JPG, JPEG, PNG, WEBP, HEIC, HEIF; File size: no more than 30MB; Width and height: each from 256 to 5760 px; Aspect ratio (width/height): 0.4–2.5; The URL must use HTTP(S) and be directly accessible by the service; The complete JSON request body must not exceed 64MB; Base64 and mm_file://…\",\"format\":\"uri\"},\"duration\":{\"type\":\"integer\",\"description\":\"Output video duration in seconds. Defaults to 4 seconds. Value restrictions: Only integers from 4 through 15, inclusive, are supported; Decimals, numeric strings, auto, and -1 are not supported; Output duration directly affects billing\",\"default\":4,\"minimum\":4,\"maximum\":15},\"quality\":{\"type\":\"string\",\"description\":\"Output video resolution. Defaults to 768p. Available values: 768p: default; 2k Notes: Omitting this parameter produces 768p output; pass quality=\\\"2k\\\" explicitly for 2K; Output bitrate, frame rate, video codec, and audio codec are selected by the platform and are not configurable\",\"enum\":[\"768p\",\"2k\"],\"default\":\"768p\"}},\"example\":{\"prompt\":\"Pull focus from the ramen bowl in the foreground to the people in the background. More steam rises naturally from the bowl as the camera gently pushes forward; preserve the characters and restaurant setting.\",\"image_start\":\"https://cdn.hailuoai.com/prod/hailuo_demo/testsets/H3_AA_I2VA/gallery/sr_v17_variants_seed42_43_20260724/inputs/4a3a90bf9100_KDmcbkhzYo5sjjxr9FqcVmWVnzb.png\",\"duration\":4,\"quality\":\"768p\"}},\"minimax-h3-max-image-to-video\":{\"model\":\"minimax-h3-max-image-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Minimax H3 Max Image-to-Video\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/minimax/minimax-h3/h3-max/minimax-h3-max-image-to-video\",\"required\":[\"prompt\",\"image_start\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Describe how the input image should move, how the camera should change, and the desired video content. Prompt requirements: Required and cannot be empty; Chinese and English are supported; Maximum length 7000 characters (Chinese and English are both counted by character); The model may ignore some details in an overly long prompt Input restrictions: Use image_start for the first frame and optionally image_end for the last frame; last-frame-only input is not supported; video_urls, and audio_urls are not supported; supplying them returns a parameter error\",\"minLength\":1,\"maxLength\":7000,\"required\":true},\"image_start\":{\"type\":\"string\",\"description\":\"HTTP(S) URL of the first-frame image. Combination rules: image_start is required; image_end cannot be provided on its own; image_start only: first-frame image-to-video; Both fields: first-and-last-frame image-to-video; At most 1 first frame; this field accepts one URL Image requirements: Formats: JPG, JPEG, PNG, WEBP, HEIC, HEIF; File size: no more than 30MB; Width and height: each from 256 to 5760 px; Aspect ratio (width/height): 0.4–2.5; The URL must use HTTP(S) and be directly accessible by the service; The complete JSON request body must not exceed 64MB; Base64 and mm_file:// inputs are n…\",\"minLength\":1,\"format\":\"uri\",\"required\":true},\"image_end\":{\"type\":\"string\",\"description\":\"HTTP(S) URL of the last-frame image. Combination rules: image_end is optional and must be provided together with image_start; image_end alone is not supported; use minimax-h3-image-to-video for last-frame-only generation; Both fields: first-and-last-frame image-to-video; At most 1 last frame; this field accepts one URL Image requirements: Formats: JPG, JPEG, PNG, WEBP, HEIC, HEIF; File size: no more than 30MB; Width and height: each from 256 to 5760 px; Aspect ratio (width/height): 0.4–2.5; The URL must use HTTP(S) and be directly accessible by the service; The complete JSON request body must…\",\"format\":\"uri\"},\"duration\":{\"type\":\"integer\",\"description\":\"Output video duration in seconds. Defaults to 5 seconds. Value restrictions: Only integers from 5 through 15, inclusive, are supported; Decimals, numeric strings, auto, and -1 are not supported; Output duration directly affects billing\",\"default\":5,\"minimum\":5,\"maximum\":15},\"quality\":{\"type\":\"string\",\"description\":\"Output video resolution. Defaults to 768p. Available values: 480p; 768p: default Notes: Omitting this parameter produces 768p output; Output bitrate, frame rate, video codec, and audio codec are selected by the platform and are not configurable\",\"enum\":[\"480p\",\"768p\"],\"default\":\"768p\"}},\"example\":{\"prompt\":\"Pull focus from the ramen bowl in the foreground to the people in the background. More steam rises naturally from the bowl as the camera gently pushes forward; preserve the characters and restaurant setting.\",\"image_start\":\"https://cdn.hailuoai.com/prod/hailuo_demo/testsets/H3_AA_I2VA/gallery/sr_v17_variants_seed42_43_20260724/inputs/4a3a90bf9100_KDmcbkhzYo5sjjxr9FqcVmWVnzb.png\",\"duration\":5,\"quality\":\"768p\"}},\"minimax-h3-max-reference-to-video\":{\"model\":\"minimax-h3-max-reference-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Minimax H3 Max Reference-to-Video\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/minimax/minimax-h3/h3-max/minimax-h3-max-reference-to-video\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Describe how the reference assets should be used and the video you want to generate. Prompt requirements: Required and cannot be empty; Chinese and English are supported; Maximum length 7000 characters (Chinese and English are both counted by character); The model may ignore some details in an overly long prompt Asset reference rules: Refer to assets as Image 1, Image 2, Video 1, Audio 1, and so on; do not use Seedance-style @image1 or @video1; Numbering starts at 1 and follows the order within each URL array; The first item in image_urls is Image 1, the first in video_urls is Video 1, and th…\",\"minLength\":1,\"maxLength\":7000,\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Array of HTTP(S) reference-image URLs. Defaults to []; maximum 9 images. Role and numbering: Every image is used as reference_image; The first item is Image 1, the second is Image 2, and so on Image requirements: Formats: JPG, JPEG, PNG, WEBP, HEIC, HEIF; File size: no more than 30MB each; Width and height: each from 256 to 5760 px; Aspect ratio (width/height): 0.4–2.5; URLs must use HTTP(S) and be directly accessible by the service; The complete JSON request body must not exceed 64MB; Base64 and mm_file:// inputs are not accepted Billing: The first 2 reference images are free; each image fro…\",\"default\":[],\"maxItems\":9,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"video_urls\":{\"type\":\"array\",\"description\":\"Array of HTTP(S) reference-video URLs. Defaults to []; maximum 3 videos. Role and numbering: Every video is used as reference_video; The first item is Video 1, the second is Video 2, and so on Video requirements: Containers: MP4 (.mp4), MOV (.mov); Video codecs: H.264/AVC, H.265/HEVC; Embedded audio codecs: AAC, MP3; File size: no more than 50MB each; Duration: 2–15 seconds per clip; total reference-video duration no more than 15 seconds; Width and height: each from 256 to 5760 px; Aspect ratio (width/height): 0.4–2.5; Frame rate: 23.976–60 FPS; URLs must use HTTP(S) and be directly accessibl…\",\"default\":[],\"maxItems\":3,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"audio_urls\":{\"type\":\"array\",\"description\":\"Array of HTTP(S) reference-audio URLs. Defaults to []; maximum 3 clips. Role and numbering: Every audio clip is used as reference_audio; The first item is Audio 1, the second is Audio 2, and so on Audio requirements: Formats: WAV, MP3; File size: no more than 15MB each; Duration: 2–15 seconds per clip; total reference-audio duration no more than 15 seconds; URLs must use HTTP(S) and be directly accessible by the service; The complete JSON request body must not exceed 64MB; Base64 and mm_file:// inputs are not accepted Billing: Reference audio is free and is not included in billable reference-…\",\"default\":[],\"maxItems\":3,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"duration\":{\"type\":\"integer\",\"description\":\"Output video duration in seconds. Defaults to 5 seconds. Value restrictions: Only integers from 5 through 15, inclusive, are supported; Decimals, numeric strings, auto, and -1 are not supported; Output duration directly affects billing\",\"default\":5,\"minimum\":5,\"maximum\":15},\"quality\":{\"type\":\"string\",\"description\":\"Output video resolution. Defaults to 768p. Available values: 480p; 768p: default Notes: Omitting this parameter produces 768p output; Output bitrate, frame rate, video codec, and audio codec are selected by the platform and are not configurable\",\"enum\":[\"480p\",\"768p\"],\"default\":\"768p\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Output video aspect ratio. Defaults to adaptive. Available values: adaptive: the model selects a suitable ratio from the reference assets and prompt; 16:9: landscape; 21:9: ultrawide; 4:3: standard landscape; 1:1: square; 3:4: standard portrait; 9:16: portrait\",\"enum\":[\"adaptive\",\"16:9\",\"21:9\",\"4:3\",\"1:1\",\"3:4\",\"9:16\"],\"default\":\"adaptive\"}},\"example\":{\"prompt\":\"Use the person in Image 1 as the sole character reference, preserving face, hairstyle, and clothing. The character walks into the wind on a seaside boardwalk as the camera tracks smoothly from a medium shot to a side close-up in sunset backlight.\",\"image_urls\":[\"https://cdn.hailuoai.com/prod/hailuo_demo/testsets/H3_AA_I2VA/gallery/sr_v17_variants_seed42_43_20260724/inputs/4a3a90bf9100_KDmcbkhzYo5sjjxr9FqcVmWVnzb.png\"],\"duration\":5,\"quality\":\"768p\",\"aspect_ratio\":\"adaptive\"}},\"minimax-h3-max-text-to-video\":{\"model\":\"minimax-h3-max-text-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Minimax H3 Max Text-to-Video\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/minimax/minimax-h3/h3-max/minimax-h3-max-text-to-video\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Describe the video you want to generate. Prompt requirements: Required and cannot be empty; Chinese and English are supported; Maximum length 7000 characters (Chinese and English are both counted by character); The model may ignore some details in an overly long prompt Input restrictions: This is a text-to-video model and accepts text input only; image_start, image_end, image_urls, video_urls, and audio_urls are not supported; Supplying any of these media fields returns a parameter error\",\"minLength\":1,\"maxLength\":7000,\"required\":true},\"duration\":{\"type\":\"integer\",\"description\":\"Output video duration in seconds. Defaults to 5 seconds. Value restrictions: Only integers from 5 through 15, inclusive, are supported; Decimals, numeric strings, auto, and -1 are not supported; Output duration directly affects billing\",\"default\":5,\"minimum\":5,\"maximum\":15},\"quality\":{\"type\":\"string\",\"description\":\"Output video resolution. Defaults to 768p. Available values: 480p; 768p: default Notes: Omitting this parameter produces 768p output; Output bitrate, frame rate, video codec, and audio codec are selected by the platform and are not configurable\",\"enum\":[\"480p\",\"768p\"],\"default\":\"768p\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Output video aspect ratio. Defaults to 16:9. Available values: 16:9: landscape; 21:9: ultrawide; 4:3: standard landscape; 1:1: square; 3:4: standard portrait; 9:16: portrait\",\"enum\":[\"16:9\",\"21:9\",\"4:3\",\"1:1\",\"3:4\",\"9:16\"],\"default\":\"16:9\"}},\"example\":{\"prompt\":\"Epic space-opera theatrical teaser: a female captain stands alone before a massive observation window as the last fleet gathers outside. The fleet jumps away in a blinding flash and the bridge shakes; when the light fades, she is left alone in silent deep space. Cinematic lighting, slow dolly-in, grand yet restrained mood.\",\"duration\":5,\"quality\":\"768p\",\"aspect_ratio\":\"16:9\"}},\"minimax-h3-max-turbo-image-to-video\":{\"model\":\"minimax-h3-max-turbo-image-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Minimax H3 Max Turbo Image-to-Video\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/minimax/minimax-h3/h3-max-turbo/minimax-h3-max-turbo-image-to-video\",\"required\":[\"prompt\",\"image_start\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Describe how the input image should move, how the camera should change, and the desired video content. Prompt requirements: Required and cannot be empty; Chinese and English are supported; Maximum length 7000 characters (Chinese and English are both counted by character); The model may ignore some details in an overly long prompt Input restrictions: Use image_start for the first frame and optionally image_end for the last frame; last-frame-only input is not supported; video_urls, and audio_urls are not supported; supplying them returns a parameter error\",\"minLength\":1,\"maxLength\":7000,\"required\":true},\"image_start\":{\"type\":\"string\",\"description\":\"HTTP(S) URL of the first-frame image. Combination rules: image_start is required; image_end cannot be provided on its own; image_start only: first-frame image-to-video; Both fields: first-and-last-frame image-to-video; At most 1 first frame; this field accepts one URL Image requirements: Formats: JPG, JPEG, PNG, WEBP, HEIC, HEIF; File size: no more than 30MB; Width and height: each from 256 to 5760 px; Aspect ratio (width/height): 0.4–2.5; The URL must use HTTP(S) and be directly accessible by the service; The complete JSON request body must not exceed 64MB; Base64 and mm_file:// inputs are n…\",\"minLength\":1,\"format\":\"uri\",\"required\":true},\"image_end\":{\"type\":\"string\",\"description\":\"HTTP(S) URL of the last-frame image. Combination rules: image_end is optional and must be provided together with image_start; image_end alone is not supported; use minimax-h3-image-to-video for last-frame-only generation; Both fields: first-and-last-frame image-to-video; At most 1 last frame; this field accepts one URL Image requirements: Formats: JPG, JPEG, PNG, WEBP, HEIC, HEIF; File size: no more than 30MB; Width and height: each from 256 to 5760 px; Aspect ratio (width/height): 0.4–2.5; The URL must use HTTP(S) and be directly accessible by the service; The complete JSON request body must…\",\"format\":\"uri\"},\"duration\":{\"type\":\"integer\",\"description\":\"Output video duration in seconds. Defaults to 5 seconds. Value restrictions: Only integers from 5 through 15, inclusive, are supported; Decimals, numeric strings, auto, and -1 are not supported; Output duration directly affects billing\",\"default\":5,\"minimum\":5,\"maximum\":15},\"quality\":{\"type\":\"string\",\"description\":\"Output video resolution. Defaults to 768p. Available values: 480p; 768p: default Notes: Omitting this parameter produces 768p output; Output bitrate, frame rate, video codec, and audio codec are selected by the platform and are not configurable\",\"enum\":[\"480p\",\"768p\"],\"default\":\"768p\"}},\"example\":{\"prompt\":\"Pull focus from the ramen bowl in the foreground to the people in the background. More steam rises naturally from the bowl as the camera gently pushes forward; preserve the characters and restaurant setting.\",\"image_start\":\"https://cdn.hailuoai.com/prod/hailuo_demo/testsets/H3_AA_I2VA/gallery/sr_v17_variants_seed42_43_20260724/inputs/4a3a90bf9100_KDmcbkhzYo5sjjxr9FqcVmWVnzb.png\",\"duration\":5,\"quality\":\"768p\"}},\"minimax-h3-max-turbo-text-to-video\":{\"model\":\"minimax-h3-max-turbo-text-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Minimax H3 Max Turbo Text-to-Video\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/minimax/minimax-h3/h3-max-turbo/minimax-h3-max-turbo-text-to-video\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Describe the video you want to generate. Prompt requirements: Required and cannot be empty; Chinese and English are supported; Maximum length 7000 characters (Chinese and English are both counted by character); The model may ignore some details in an overly long prompt Input restrictions: This is a text-to-video model and accepts text input only; image_start, image_end, image_urls, video_urls, and audio_urls are not supported; Supplying any of these media fields returns a parameter error\",\"minLength\":1,\"maxLength\":7000,\"required\":true},\"duration\":{\"type\":\"integer\",\"description\":\"Output video duration in seconds. Defaults to 5 seconds. Value restrictions: Only integers from 5 through 15, inclusive, are supported; Decimals, numeric strings, auto, and -1 are not supported; Output duration directly affects billing\",\"default\":5,\"minimum\":5,\"maximum\":15},\"quality\":{\"type\":\"string\",\"description\":\"Output video resolution. Defaults to 768p. Available values: 480p; 768p: default Notes: Omitting this parameter produces 768p output; Output bitrate, frame rate, video codec, and audio codec are selected by the platform and are not configurable\",\"enum\":[\"480p\",\"768p\"],\"default\":\"768p\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Output video aspect ratio. Defaults to 16:9. Available values: 16:9: landscape; 21:9: ultrawide; 4:3: standard landscape; 1:1: square; 3:4: standard portrait; 9:16: portrait\",\"enum\":[\"16:9\",\"21:9\",\"4:3\",\"1:1\",\"3:4\",\"9:16\"],\"default\":\"16:9\"}},\"example\":{\"prompt\":\"Epic space-opera theatrical teaser: a female captain stands alone before a massive observation window as the last fleet gathers outside. The fleet jumps away in a blinding flash and the bridge shakes; when the light fades, she is left alone in silent deep space. Cinematic lighting, slow dolly-in, grand yet restrained mood.\",\"duration\":5,\"quality\":\"768p\",\"aspect_ratio\":\"16:9\"}},\"minimax-h3-reference-to-video\":{\"model\":\"minimax-h3-reference-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Minimax H3 Reference-to-Video\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/minimax/minimax-h3/h3/minimax-h3-reference-to-video\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Describe how the reference assets should be used and the video you want to generate. Prompt requirements: Required and cannot be empty; Chinese and English are supported; Maximum length 7000 characters (Chinese and English are both counted by character); The model may ignore some details in an overly long prompt Asset reference rules: Refer to assets as Image 1, Image 2, Video 1, Audio 1, and so on; do not use Seedance-style @image1 or @video1; Numbering starts at 1 and follows the order within each URL array; The first item in image_urls is Image 1, the first in video_urls is Video 1, and th…\",\"minLength\":1,\"maxLength\":7000,\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Array of HTTP(S) reference-image URLs. Defaults to []; maximum 9 images. Role and numbering: Every image is used as reference_image; The first item is Image 1, the second is Image 2, and so on Image requirements: Formats: JPG, JPEG, PNG, WEBP, HEIC, HEIF; File size: no more than 30MB each; Width and height: each from 256 to 5760 px; Aspect ratio (width/height): 0.4–2.5; URLs must use HTTP(S) and be directly accessible by the service; The complete JSON request body must not exceed 64MB; Base64 and mm_file:// inputs are not accepted Combination rules: Provide at least one of image_urls, video_u…\",\"default\":[],\"maxItems\":9,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"video_urls\":{\"type\":\"array\",\"description\":\"Array of HTTP(S) reference-video URLs. Defaults to []; maximum 3 videos. Role and numbering: Every video is used as reference_video; The first item is Video 1, the second is Video 2, and so on Video requirements: Containers: MP4 (.mp4), MOV (.mov); Video codecs: H.264/AVC, H.265/HEVC; Embedded audio codecs: AAC, MP3; File size: no more than 50MB each; Duration: 2–15 seconds per clip; total reference-video duration no more than 15 seconds; Width and height: each from 256 to 5760 px; Aspect ratio (width/height): 0.4–2.5; Frame rate: 23.976–60 FPS; URLs must use HTTP(S) and be directly accessibl…\",\"default\":[],\"maxItems\":3,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"audio_urls\":{\"type\":\"array\",\"description\":\"Array of HTTP(S) reference-audio URLs. Defaults to []; maximum 3 clips. Role and numbering: Every audio clip is used as reference_audio; The first item is Audio 1, the second is Audio 2, and so on Audio requirements: Formats: WAV, MP3; File size: no more than 15MB each; Duration: 2–15 seconds per clip; total reference-audio duration no more than 15 seconds; URLs must use HTTP(S) and be directly accessible by the service; The complete JSON request body must not exceed 64MB; Base64 and mm_file:// inputs are not accepted Billing: Reference-audio duration is not billable Combination rules: audio_…\",\"default\":[],\"maxItems\":3,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"duration\":{\"type\":\"integer\",\"description\":\"Output video duration in seconds. Defaults to 4 seconds. Value restrictions: Only integers from 4 through 15, inclusive, are supported; Decimals, numeric strings, auto, and -1 are not supported; Output duration directly affects billing\",\"default\":4,\"minimum\":4,\"maximum\":15},\"quality\":{\"type\":\"string\",\"description\":\"Output video resolution. Defaults to 768p. Available values: 768p: default; 2k Notes: Omitting this parameter produces 768p output; pass quality=\\\"2k\\\" explicitly for 2K; Output bitrate, frame rate, video codec, and audio codec are selected by the platform and are not configurable\",\"enum\":[\"768p\",\"2k\"],\"default\":\"768p\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Output video aspect ratio. Defaults to adaptive. Available values: adaptive: the model selects a suitable ratio from the reference assets and prompt; 16:9: landscape; 21:9: ultrawide; 4:3: standard landscape; 1:1: square; 3:4: standard portrait; 9:16: portrait\",\"enum\":[\"adaptive\",\"16:9\",\"21:9\",\"4:3\",\"1:1\",\"3:4\",\"9:16\"],\"default\":\"adaptive\"}},\"example\":{\"prompt\":\"Use the person in Image 1 as the sole character reference, preserving face, hairstyle, and clothing. The character walks into the wind on a seaside boardwalk as the camera tracks smoothly from a medium shot to a side close-up in sunset backlight.\",\"image_urls\":[\"https://cdn.hailuoai.com/prod/hailuo_demo/testsets/H3_AA_I2VA/gallery/sr_v17_variants_seed42_43_20260724/inputs/4a3a90bf9100_KDmcbkhzYo5sjjxr9FqcVmWVnzb.png\"],\"duration\":4,\"quality\":\"768p\",\"aspect_ratio\":\"adaptive\"}},\"minimax-h3-text-to-video\":{\"model\":\"minimax-h3-text-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Minimax H3 Text-to-Video\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/minimax/minimax-h3/h3/minimax-h3-text-to-video\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Describe the video you want to generate. Prompt requirements: Required and cannot be empty; Chinese and English are supported; Maximum length 7000 characters (Chinese and English are both counted by character); The model may ignore some details in an overly long prompt Input restrictions: This is a text-to-video model and accepts text input only; image_start, image_end, image_urls, video_urls, and audio_urls are not supported; Supplying any of these media fields returns a parameter error\",\"minLength\":1,\"maxLength\":7000,\"required\":true},\"duration\":{\"type\":\"integer\",\"description\":\"Output video duration in seconds. Defaults to 4 seconds. Value restrictions: Only integers from 4 through 15, inclusive, are supported; Decimals, numeric strings, auto, and -1 are not supported; Output duration directly affects billing\",\"default\":4,\"minimum\":4,\"maximum\":15},\"quality\":{\"type\":\"string\",\"description\":\"Output video resolution. Defaults to 768p. Available values: 768p: default; 2k Notes: Omitting this parameter produces 768p output; pass quality=\\\"2k\\\" explicitly for 2K; Output bitrate, frame rate, video codec, and audio codec are selected by the platform and are not configurable\",\"enum\":[\"768p\",\"2k\"],\"default\":\"768p\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Output video aspect ratio. Defaults to 16:9. Available values: 16:9: landscape; 21:9: ultrawide; 4:3: standard landscape; 1:1: square; 3:4: standard portrait; 9:16: portrait\",\"enum\":[\"16:9\",\"21:9\",\"4:3\",\"1:1\",\"3:4\",\"9:16\"],\"default\":\"16:9\"}},\"example\":{\"prompt\":\"Epic space-opera theatrical teaser: a female captain stands alone before a massive observation window as the last fleet gathers outside. The fleet jumps away in a blinding flash and the bridge shakes; when the light fades, she is left alone in silent deep space. Cinematic lighting, slow dolly-in, grand yet restrained mood.\",\"duration\":4,\"quality\":\"768p\",\"aspect_ratio\":\"16:9\"}},\"mj-v7\":{\"model\":\"mj-v7\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"Midjourney V7 Image Generation Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v7-image-generate\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt, supports all Midjourney V7 native parameter syntax (e.g. --ar 16:9 --s 500). Image-to-Image: Place image URLs at the beginning of the prompt. Supported formats: .png, .gif, .webp, .jpg, .jpeg Image-to-Image Rules: 1 image + no text = invalid (will return error); 1 image + text description = valid; 2+ images + no text = valid; 2+ images + text description = valid\",\"maxLength\":8192,\"required\":true},\"model_params\":{\"type\":\"object\",\"description\":\"Model parameters\",\"properties\":{\"speed\":{\"type\":\"string\",\"description\":\"Speed mode; draft: Sketch mode, 10x faster, lower cost, can be enhanced later with mj-v7-enhance; fast: Standard mode (default); turbo: Ultra-fast mode, higher cost Pricing note: draft costs the least, turbo costs the most (approximately 2x fast)\",\"enum\":[\"draft\",\"fast\",\"turbo\"],\"default\":\"fast\"}}}},\"example\":{\"prompt\":\"A cinematic shot of a Maine Coon cat on a neon-lit balcony --ar 16:9 --s 500\",\"model_params\":{\"speed\":\"fast\"}}},\"mj-v7-edit\":{\"model\":\"mj-v7-edit\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"mj-v7-edit Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v7-edit\",\"required\":[\"prompt\",\"model_params\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Describe the desired fill content\",\"required\":true},\"model_params\":{\"type\":\"object\",\"description\":\"Canvas edit parameters\",\"properties\":{\"task_id\":{\"type\":\"string\",\"description\":\"Source task ID\",\"required\":true},\"image_number\":{\"type\":\"integer\",\"description\":\"Select which image from the source task\",\"enum\":[0,1,2,3],\"default\":0},\"canvas\":{\"type\":\"object\",\"description\":\"Canvas size (pixels)\",\"properties\":{\"width\":{\"type\":\"integer\",\"description\":\"Canvas width\",\"required\":true},\"height\":{\"type\":\"integer\",\"description\":\"Canvas height\",\"required\":true}},\"required\":true},\"img_pos\":{\"type\":\"object\",\"description\":\"Image position and size on the canvas\",\"properties\":{\"width\":{\"type\":\"integer\",\"description\":\"Render width\",\"required\":true},\"height\":{\"type\":\"integer\",\"description\":\"Render height\",\"required\":true},\"x\":{\"type\":\"integer\",\"description\":\"Top-left horizontal offset\",\"required\":true},\"y\":{\"type\":\"integer\",\"description\":\"Top-left vertical offset\",\"required\":true}},\"required\":true},\"mask\":{\"type\":\"object\",\"description\":\"Optional inpaint region (same format as inpaint)\"},\"speed\":{\"type\":\"string\",\"description\":\"Speed mode Pricing note: turbo mode costs more\",\"enum\":[\"fast\",\"turbo\"],\"default\":\"fast\"}},\"required\":true}},\"example\":{\"prompt\":\"Beautiful mountain scenery background\",\"model_params\":{\"task_id\":\"task-unified-xxx\",\"image_number\":0,\"canvas\":{\"width\":1024,\"height\":1024},\"img_pos\":{\"width\":512,\"height\":512,\"x\":256,\"y\":256},\"speed\":\"fast\"}}},\"mj-v7-enhance\":{\"model\":\"mj-v7-enhance\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"Midjourney V7 Enhance\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v7-enhance\",\"required\":[\"model_params\"],\"params\":{\"model_params\":{\"type\":\"object\",\"description\":\"Model parameters\",\"properties\":{\"task_id\":{\"type\":\"string\",\"description\":\"Source task ID (must be a task generated in draft mode)\",\"required\":true},\"image_number\":{\"type\":\"integer\",\"description\":\"Select which image (0-3)\",\"enum\":[0,1,2,3],\"default\":0}},\"required\":true}},\"example\":{\"model_params\":{\"task_id\":\"task-unified-xxx\",\"image_number\":0}}},\"mj-v7-inpaint\":{\"model\":\"mj-v7-inpaint\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"Midjourney V7 Inpaint\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v7-inpaint\",\"required\":[\"model_params\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Describe desired content for the inpaint region\"},\"model_params\":{\"type\":\"object\",\"description\":\"Model parameters\",\"properties\":{\"task_id\":{\"type\":\"string\",\"description\":\"Source task ID\",\"required\":true},\"image_number\":{\"type\":\"integer\",\"description\":\"Select which image (0-3)\",\"enum\":[0,1,2,3],\"default\":0},\"mask\":{\"type\":\"object\",\"description\":\"Inpaint region definition, supports two methods\",\"required\":true},\"speed\":{\"type\":\"string\",\"description\":\"Speed mode (only effective when prompt is provided) Pricing note: turbo mode costs more\",\"enum\":[\"fast\",\"turbo\"],\"default\":\"fast\"}},\"required\":true}},\"example\":{\"prompt\":\"Add a cherry blossom tree\",\"model_params\":{\"task_id\":\"task-unified-xxx\",\"image_number\":0,\"mask\":{\"areas\":[{\"width\":200,\"height\":200,\"points\":[50,50,50,250,250,250,250,50]}]}}}},\"mj-v7-outpaint\":{\"model\":\"mj-v7-outpaint\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"Midjourney V7 Outpaint\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v7-outpaint\",\"required\":[\"model_params\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Guide content for the expanded area\"},\"model_params\":{\"type\":\"object\",\"description\":\"Model parameters\",\"properties\":{\"task_id\":{\"type\":\"string\",\"description\":\"Source task ID\",\"required\":true},\"image_number\":{\"type\":\"integer\",\"description\":\"Select which image (0-3)\",\"enum\":[0,1,2,3],\"default\":0},\"scale\":{\"type\":\"number\",\"description\":\"Outpaint scale (max 2.0, smaller range than pan's 3.0)\",\"default\":1.5,\"minimum\":1.1,\"maximum\":2},\"speed\":{\"type\":\"string\",\"description\":\"Speed mode (only effective when prompt is provided) Pricing note: turbo mode costs more\",\"enum\":[\"fast\",\"turbo\"],\"default\":\"fast\"}},\"required\":true}},\"example\":{\"model_params\":{\"task_id\":\"task-unified-xxx\",\"image_number\":1,\"scale\":1.5}}},\"mj-v7-pan\":{\"model\":\"mj-v7-pan\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"Midjourney V7 Pan\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v7-pan\",\"required\":[\"model_params\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Guide content for the extended area\"},\"model_params\":{\"type\":\"object\",\"description\":\"Model parameters\",\"properties\":{\"task_id\":{\"type\":\"string\",\"description\":\"Source task ID\",\"required\":true},\"image_number\":{\"type\":\"integer\",\"description\":\"Select which image (0-3)\",\"enum\":[0,1,2,3],\"default\":0},\"direction\":{\"type\":\"string\",\"description\":\"Pan direction\",\"enum\":[\"down\",\"right\",\"up\",\"left\"],\"default\":\"down\"},\"scale\":{\"type\":\"number\",\"description\":\"Pan scale, larger values extend more area\",\"default\":1.5,\"minimum\":1.1,\"maximum\":3},\"speed\":{\"type\":\"string\",\"description\":\"Speed mode (only effective when prompt is provided) Pricing note: turbo mode costs more\",\"enum\":[\"fast\",\"turbo\"],\"default\":\"fast\"}},\"required\":true}},\"example\":{\"model_params\":{\"task_id\":\"task-unified-xxx\",\"image_number\":0,\"direction\":\"right\",\"scale\":2}}},\"mj-v7-remix\":{\"model\":\"mj-v7-remix\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"Midjourney V7 Remix Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v7-remix\",\"required\":[\"prompt\",\"model_params\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"New prompt describing desired adjustment, supports Midjourney parameter syntax\",\"required\":true},\"model_params\":{\"type\":\"object\",\"description\":\"Model parameters\",\"properties\":{\"task_id\":{\"type\":\"string\",\"description\":\"Source task ID\",\"required\":true},\"image_number\":{\"type\":\"integer\",\"description\":\"Select which image (0-3)\",\"enum\":[0,1,2,3],\"default\":0},\"mode\":{\"type\":\"string\",\"description\":\"Remix strength; strong: Major adjustment; subtle: Minor adjustment\",\"enum\":[\"strong\",\"subtle\"],\"default\":\"strong\"},\"speed\":{\"type\":\"string\",\"description\":\"Speed mode Pricing note: turbo mode costs more (approximately 2x fast)\",\"enum\":[\"fast\",\"turbo\"],\"default\":\"fast\"}},\"required\":true}},\"example\":{\"prompt\":\"Convert to oil painting style --ar 1:1\",\"model_params\":{\"task_id\":\"task-unified-xxx\",\"image_number\":0,\"mode\":\"strong\",\"speed\":\"fast\"}}},\"mj-v7-remove-bg\":{\"model\":\"mj-v7-remove-bg\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"mj-v7-remove-bg Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v7-remove-bg\",\"required\":[\"image_urls\"],\"params\":{\"image_urls\":{\"type\":\"array\",\"description\":\"Input image URL (uses the first one) Supported formats: .png, .gif, .webp, .jpg, .jpeg\",\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true}},\"example\":{\"image_urls\":[\"https://example.com/photo.jpg\"]}},\"mj-v7-retexture\":{\"model\":\"mj-v7-retexture\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"mj-v7-retexture Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v7-retexture\",\"required\":[\"prompt\",\"image_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Describe target texture/style\",\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Input image URL (uses the first one)\",\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"model_params\":{\"type\":\"object\",\"description\":\"Model parameters\",\"properties\":{\"speed\":{\"type\":\"string\",\"description\":\"Speed mode Pricing note: turbo mode costs more\",\"enum\":[\"fast\",\"turbo\"],\"default\":\"fast\"}}}},\"example\":{\"prompt\":\"Cyberpunk neon style\",\"image_urls\":[\"https://example.com/photo.jpg\"],\"model_params\":{\"speed\":\"fast\"}}},\"mj-v7-upload-paint\":{\"model\":\"mj-v7-upload-paint\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"mj-v7-upload-paint Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v7-upload-paint\",\"required\":[\"prompt\",\"image_urls\",\"model_params\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Edit prompt\",\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Input image URL (first one is used)\",\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"model_params\":{\"type\":\"object\",\"description\":\"Advanced edit parameters\",\"properties\":{\"mask\":{\"type\":\"object\",\"description\":\"Inpaint region (same format as inpaint: polygon coordinates or mask image) Method 1 - Polygon coordinates: json { \\\"areas\\\": [{ \\\"width\\\": 100, \\\"height\\\": 100, \\\"points\\\": [10, 10, 10, 100, 100, 100, 100, 10] }] } Method 2 - Mask image (white = inpaint, black = preserve): json { \\\"url\\\": \\\"https://example.com/mask.png\\\" }\",\"properties\":{\"areas\":{\"type\":\"array\",\"description\":\"Polygon region list\",\"items\":{\"type\":\"object\",\"properties\":{\"width\":{\"type\":\"integer\",\"description\":\"Region width\"},\"height\":{\"type\":\"integer\",\"description\":\"Region height\"},\"points\":{\"type\":\"array\",\"description\":\"Polygon vertex coordinates (x1,y1,x2,y2,...)\",\"items\":{\"type\":\"integer\"}}}}},\"url\":{\"type\":\"string\",\"description\":\"Mask image URL (white = inpaint, black = preserve)\",\"format\":\"uri\"}},\"required\":true},\"canvas\":{\"type\":\"object\",\"description\":\"Canvas size\",\"properties\":{\"width\":{\"type\":\"integer\",\"description\":\"Canvas width\",\"required\":true},\"height\":{\"type\":\"integer\",\"description\":\"Canvas height\",\"required\":true}},\"required\":true},\"img_pos\":{\"type\":\"object\",\"description\":\"Image position and size\",\"properties\":{\"width\":{\"type\":\"integer\",\"description\":\"Render width\",\"required\":true},\"height\":{\"type\":\"integer\",\"description\":\"Render height\",\"required\":true},\"x\":{\"type\":\"integer\",\"description\":\"Top-left horizontal offset\",\"required\":true},\"y\":{\"type\":\"integer\",\"description\":\"Top-left vertical offset\",\"required\":true}},\"required\":true},\"speed\":{\"type\":\"string\",\"description\":\"Speed mode Pricing note: turbo mode costs more\",\"enum\":[\"fast\",\"turbo\"],\"default\":\"fast\"}},\"required\":true}},\"example\":{\"prompt\":\"Beautiful mountain scenery background\",\"image_urls\":[\"https://example.com/photo.jpg\"],\"model_params\":{\"mask\":{\"areas\":[{\"width\":100,\"height\":100,\"points\":[10,10,10,100,100,100,100,10]}]},\"canvas\":{\"width\":1024,\"height\":1024},\"img_pos\":{\"width\":512,\"height\":512,\"x\":256,\"y\":256},\"speed\":\"fast\"}}},\"mj-v7-upscale\":{\"model\":\"mj-v7-upscale\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"Midjourney V7 Upscale Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v7-upscale\",\"required\":[\"model_params\"],\"params\":{\"model_params\":{\"type\":\"object\",\"description\":\"Model parameters\",\"properties\":{\"task_id\":{\"type\":\"string\",\"description\":\"Source task ID\",\"required\":true},\"image_number\":{\"type\":\"integer\",\"description\":\"Select which image (0-3)\",\"enum\":[0,1,2,3],\"default\":0},\"type\":{\"type\":\"string\",\"description\":\"Upscale mode; standard: Standard HD upscale; creative: Creative HD upscale, adds artistic detail while upscaling Pricing note: creative mode costs more than standard\",\"enum\":[\"standard\",\"creative\"],\"default\":\"standard\"}},\"required\":true}},\"example\":{\"model_params\":{\"task_id\":\"task-unified-xxx\",\"image_number\":1,\"type\":\"standard\"}}},\"mj-v7-variation\":{\"model\":\"mj-v7-variation\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"Midjourney V7 Variation Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v7-variation\",\"required\":[\"model_params\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Optional prompt; if provided, serves as remix prompt to modify content along with variation\"},\"model_params\":{\"type\":\"object\",\"description\":\"Model parameters\",\"properties\":{\"task_id\":{\"type\":\"string\",\"description\":\"Source task ID, must be a completed mj-v7 series task, and must belong to the current user\",\"required\":true},\"image_number\":{\"type\":\"integer\",\"description\":\"Select which of 4 source images (0-3)\",\"enum\":[0,1,2,3],\"default\":0},\"type\":{\"type\":\"string\",\"description\":\"Variation strength; subtle: Subtle variation; strong: Strong variation\",\"enum\":[\"subtle\",\"strong\"],\"default\":\"subtle\"},\"speed\":{\"type\":\"string\",\"description\":\"Speed mode (only effective when prompt is provided) Pricing note: turbo mode costs more\",\"enum\":[\"fast\",\"turbo\"],\"default\":\"fast\"}},\"required\":true}},\"example\":{\"model_params\":{\"task_id\":\"task-unified-xxx\",\"image_number\":2,\"type\":\"strong\"}}},\"mj-v8.1\":{\"model\":\"mj-v8.1\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"Midjourney V8.1 Image Generation Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v8-1-image-generate\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt, supports all Midjourney V8.1 native parameter syntax (e.g. --ar 16:9 --s 500). Image-to-Image: Place image URLs at the beginning of the prompt. Supported formats: .png, .gif, .webp, .jpg, .jpeg Image-to-Image Rules: 1 image + no text = invalid (will return error); 1 image + text description = valid; 2+ images + no text = valid; 2+ images + text description = valid\",\"maxLength\":1024,\"required\":true},\"quality\":{\"type\":\"string\",\"description\":\"Output quality; standard: Standard resolution (default), 1x multiplier; hd: Native HD output, 1.5x multiplier. Mutually exclusive with speed: draft Pricing note: the quality multiplier is combined (multiplied) with the speed multiplier.\",\"enum\":[\"standard\",\"hd\"],\"default\":\"standard\"},\"model_params\":{\"type\":\"object\",\"description\":\"Model parameters\",\"properties\":{\"speed\":{\"type\":\"string\",\"description\":\"Speed mode; draft: Sketch mode. Returns 24 lightweight 0.5K sketch images in a single run (instead of 4), ideal for quickly exploring composition ideas. Mutually exclusive with quality: hd; fast: Standard mode (default) Pricing note: draft and fast share the same speed multiplier (1x). This speed multiplier is then combined (multiplied) with the quality multiplier.\",\"enum\":[\"draft\",\"fast\"],\"default\":\"fast\"}}}},\"example\":{\"prompt\":\"A cinematic shot of a Maine Coon cat on a neon-lit balcony --ar 16:9 --s 500\",\"quality\":\"standard\",\"model_params\":{\"speed\":\"fast\"}}},\"mj-v8.1-edit\":{\"model\":\"mj-v8.1-edit\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"mj-v8.1-edit Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v8-1-edit\",\"required\":[\"prompt\",\"model_params\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Describe the desired fill content\",\"maxLength\":1024,\"required\":true},\"model_params\":{\"type\":\"object\",\"description\":\"Canvas edit parameters\",\"properties\":{\"task_id\":{\"type\":\"string\",\"description\":\"Source task ID (the task whose image you want to edit)\",\"required\":true},\"image_number\":{\"type\":\"integer\",\"description\":\"Select which image from the source task\",\"enum\":[0,1,2,3],\"default\":0},\"canvas\":{\"type\":\"object\",\"description\":\"Canvas size. Canvas aspect ratio (width/height) MUST match the source task image aspect ratio, otherwise the task fails (status: failed, execution error).\",\"properties\":{\"width\":{\"type\":\"integer\",\"description\":\"Canvas width\",\"required\":true},\"height\":{\"type\":\"integer\",\"description\":\"Canvas height\",\"required\":true}},\"required\":true},\"img_pos\":{\"type\":\"object\",\"description\":\"Image position and size within the canvas. Image fills the canvas (img W/H = canvas W/H) = pure edit/repaint; image smaller than canvas = outpaint (the surrounding blank area is generated from the prompt).\",\"properties\":{\"width\":{\"type\":\"integer\",\"description\":\"Render width\",\"required\":true},\"height\":{\"type\":\"integer\",\"description\":\"Render height\",\"required\":true},\"x\":{\"type\":\"integer\",\"description\":\"Top-left horizontal offset\",\"required\":true},\"y\":{\"type\":\"integer\",\"description\":\"Top-left vertical offset\",\"required\":true}},\"required\":true},\"mask\":{\"type\":\"object\",\"description\":\"Optional masked region to repaint within the placed image (polygon coordinates or mask image) Method 1 - Polygon coordinates: json { \\\"areas\\\": [{ \\\"width\\\": 100, \\\"height\\\": 100, \\\"points\\\": [10, 10, 10, 100, 100, 100, 100, 10] }] } Method 2 - Mask image (alpha channel: opaque = repaint, transparent = keep, opposite of typical inpaint masks): json { \\\"url\\\": \\\"https://example.com/mask.png\\\" }\",\"properties\":{\"areas\":{\"type\":\"array\",\"description\":\"Polygon region list\",\"items\":{\"type\":\"object\",\"properties\":{\"width\":{\"type\":\"integer\",\"description\":\"Region width\"},\"height\":{\"type\":\"integer\",\"description\":\"Region height\"},\"points\":{\"type\":\"array\",\"description\":\"Polygon vertex coordinates (x1,y1,x2,y2,...)\",\"items\":{\"type\":\"integer\"}}}}},\"url\":{\"type\":\"string\",\"description\":\"Mask image URL (alpha channel: opaque = repaint, transparent = keep, opposite of typical inpaint masks). Must match the reference image pixel dimensions.\",\"format\":\"uri\"}}},\"speed\":{\"type\":\"string\",\"description\":\"Speed mode\",\"enum\":[\"fast\"],\"default\":\"fast\"}},\"required\":true}},\"example\":{\"prompt\":\"Beautiful mountain scenery background\",\"model_params\":{\"task_id\":\"task-unified-xxx\",\"image_number\":0,\"canvas\":{\"width\":1024,\"height\":1024},\"img_pos\":{\"width\":512,\"height\":512,\"x\":256,\"y\":256},\"speed\":\"fast\"}}},\"mj-v8.1-remix\":{\"model\":\"mj-v8.1-remix\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"Midjourney V8.1 Remix Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v8-1-remix\",\"required\":[\"prompt\",\"model_params\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"New prompt describing desired adjustment, supports Midjourney parameter syntax\",\"maxLength\":1024,\"required\":true},\"model_params\":{\"type\":\"object\",\"description\":\"Model parameters\",\"properties\":{\"task_id\":{\"type\":\"string\",\"description\":\"Source task ID\",\"required\":true},\"image_number\":{\"type\":\"integer\",\"description\":\"Select which image (0-3)\",\"enum\":[0,1,2,3],\"default\":0},\"mode\":{\"type\":\"string\",\"description\":\"Remix strength; strong: Major adjustment; subtle: Minor adjustment\",\"enum\":[\"strong\",\"subtle\"],\"default\":\"strong\"},\"speed\":{\"type\":\"string\",\"description\":\"Speed mode\",\"enum\":[\"fast\"],\"default\":\"fast\"}},\"required\":true}},\"example\":{\"prompt\":\"Convert to oil painting style --ar 1:1\",\"model_params\":{\"task_id\":\"task-unified-xxx\",\"image_number\":0,\"mode\":\"strong\",\"speed\":\"fast\"}}},\"mj-v8.1-remove-bg\":{\"model\":\"mj-v8.1-remove-bg\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"mj-v8.1-remove-bg Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v8-1-remove-bg\",\"required\":[\"image_urls\"],\"params\":{\"image_urls\":{\"type\":\"array\",\"description\":\"Input image URL (uses the first one) Supported formats: .png, .gif, .webp, .jpg, .jpeg\",\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true}},\"example\":{\"image_urls\":[\"https://example.com/photo.jpg\"]}},\"mj-v8.1-retexture\":{\"model\":\"mj-v8.1-retexture\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"mj-v8.1-retexture Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v8-1-retexture\",\"required\":[\"prompt\",\"image_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Describe target texture/style\",\"maxLength\":1024,\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Input image URL (uses the first one)\",\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"model_params\":{\"type\":\"object\",\"description\":\"Model parameters\",\"properties\":{\"speed\":{\"type\":\"string\",\"description\":\"Speed mode\",\"enum\":[\"fast\"],\"default\":\"fast\"}}}},\"example\":{\"prompt\":\"Cyberpunk neon style\",\"image_urls\":[\"https://example.com/photo.jpg\"],\"model_params\":{\"speed\":\"fast\"}}},\"mj-v8.1-upload-paint\":{\"model\":\"mj-v8.1-upload-paint\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"mj-v8.1-upload-paint Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v8-1-upload-paint\",\"required\":[\"prompt\",\"image_urls\",\"model_params\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Edit prompt\",\"maxLength\":1024,\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Input image URL (first one is used)\",\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"model_params\":{\"type\":\"object\",\"description\":\"Advanced edit parameters\",\"properties\":{\"mask\":{\"type\":\"object\",\"description\":\"Masked region to repaint (polygon coordinates or mask image) Method 1 - Polygon coordinates: json { \\\"areas\\\": [{ \\\"width\\\": 100, \\\"height\\\": 100, \\\"points\\\": [10, 10, 10, 100, 100, 100, 100, 10] }] } Method 2 - Mask image (alpha channel: opaque = repaint, transparent = keep, opposite of typical inpaint masks): json { \\\"url\\\": \\\"https://example.com/mask.png\\\" }\",\"properties\":{\"areas\":{\"type\":\"array\",\"description\":\"Polygon region list\",\"items\":{\"type\":\"object\",\"properties\":{\"width\":{\"type\":\"integer\",\"description\":\"Region width\"},\"height\":{\"type\":\"integer\",\"description\":\"Region height\"},\"points\":{\"type\":\"array\",\"description\":\"Polygon vertex coordinates (x1,y1,x2,y2,...)\",\"items\":{\"type\":\"integer\"}}}}},\"url\":{\"type\":\"string\",\"description\":\"Mask image URL (alpha channel: opaque = repaint, transparent = keep, opposite of typical inpaint masks). Must match the reference image pixel dimensions.\",\"format\":\"uri\"}},\"required\":true},\"canvas\":{\"type\":\"object\",\"description\":\"Canvas size. Canvas aspect ratio (width/height) MUST match the uploaded image aspect ratio, otherwise the task fails (status: failed, execution error).\",\"properties\":{\"width\":{\"type\":\"integer\",\"description\":\"Canvas width\",\"required\":true},\"height\":{\"type\":\"integer\",\"description\":\"Canvas height\",\"required\":true}},\"required\":true},\"img_pos\":{\"type\":\"object\",\"description\":\"Image position and size within the canvas. Image fills the canvas (img W/H = canvas W/H) = pure edit/repaint; image smaller than canvas = outpaint (the surrounding blank area is generated from the prompt).\",\"properties\":{\"width\":{\"type\":\"integer\",\"description\":\"Render width\",\"required\":true},\"height\":{\"type\":\"integer\",\"description\":\"Render height\",\"required\":true},\"x\":{\"type\":\"integer\",\"description\":\"Top-left horizontal offset\",\"required\":true},\"y\":{\"type\":\"integer\",\"description\":\"Top-left vertical offset\",\"required\":true}},\"required\":true},\"speed\":{\"type\":\"string\",\"description\":\"Speed mode\",\"enum\":[\"fast\"],\"default\":\"fast\"}},\"required\":true}},\"example\":{\"prompt\":\"Beautiful mountain scenery background\",\"image_urls\":[\"https://example.com/photo.jpg\"],\"model_params\":{\"mask\":{\"areas\":[{\"width\":100,\"height\":100,\"points\":[10,10,10,100,100,100,100,10]}]},\"canvas\":{\"width\":1024,\"height\":1024},\"img_pos\":{\"width\":512,\"height\":512,\"x\":256,\"y\":256},\"speed\":\"fast\"}}},\"mj-v8.1-variation\":{\"model\":\"mj-v8.1-variation\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"Midjourney V8.1 Variation Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v8-1-variation\",\"required\":[\"model_params\"],\"params\":{\"model_params\":{\"type\":\"object\",\"description\":\"Model parameters\",\"properties\":{\"task_id\":{\"type\":\"string\",\"description\":\"Source task ID, must be a completed mj-v8.1 series task, and must belong to the current user\",\"required\":true},\"image_number\":{\"type\":\"integer\",\"description\":\"Select which of 4 source images (0-3)\",\"enum\":[0,1,2,3],\"default\":0},\"type\":{\"type\":\"string\",\"description\":\"Variation strength; subtle: Subtle variation; strong: Strong variation\",\"enum\":[\"subtle\",\"strong\"],\"default\":\"subtle\"}},\"required\":true}},\"example\":{\"model_params\":{\"task_id\":\"task-unified-xxx\",\"image_number\":2,\"type\":\"strong\"}}},\"mj-v8.2\":{\"model\":\"mj-v8.2\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"Midjourney V8.2 Image Generation Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v8-2-image-generate\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt, supports all Midjourney V8.2 native parameter syntax (e.g. --ar 16:9 --s 500). Image-to-Image: Place image URLs at the beginning of the prompt. Supported formats: .png, .gif, .webp, .jpg, .jpeg Image-to-Image Rules: 1 image + no text = invalid (will return error); 1 image + text description = valid; 2+ images + no text = valid; 2+ images + text description = valid Unsupported parameters: parameters the upstream does not support (e.g. --oref, --cref, --stop) are passed through and explicitly rejected by the upstream: the task fails with a parameter error (invalid_parameters) and reserv…\",\"maxLength\":2048,\"required\":true},\"quality\":{\"type\":\"string\",\"description\":\"Output quality; standard: Standard resolution (default), 1x multiplier; hd: Native HD output, 1.5x multiplier. Mutually exclusive with speed: draft Pricing note: the quality multiplier is combined (multiplied) with the speed multiplier.\",\"enum\":[\"standard\",\"hd\"],\"default\":\"standard\"},\"model_params\":{\"type\":\"object\",\"description\":\"Model parameters\",\"properties\":{\"speed\":{\"type\":\"string\",\"description\":\"Speed mode; draft: Sketch mode. Returns 24 lightweight 0.5K sketch images in a single run (instead of 4), ideal for quickly exploring composition ideas. Mutually exclusive with quality: hd; fast: Standard mode (default)\",\"enum\":[\"draft\",\"fast\"],\"default\":\"fast\"}}}},\"example\":{\"prompt\":\"A cinematic shot of a Maine Coon cat on a neon-lit balcony --ar 16:9 --s 500\",\"quality\":\"standard\",\"model_params\":{\"speed\":\"fast\"}}},\"mj-v8.2-edit\":{\"model\":\"mj-v8.2-edit\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"mj-v8.2-edit Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v8-2-edit\",\"required\":[\"prompt\",\"model_params\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Describe the desired fill content\",\"maxLength\":8100,\"required\":true},\"model_params\":{\"type\":\"object\",\"description\":\"Canvas edit parameters\",\"properties\":{\"task_id\":{\"type\":\"string\",\"description\":\"Source task ID, must be a completed mj-v8.2 series task (image generation, variation, remix or edit) that belongs to the current user\",\"required\":true},\"image_number\":{\"type\":\"integer\",\"description\":\"Select which image from the source task: 0-3 for a fast source task, 0-23 for a draft source task\",\"default\":0,\"minimum\":0,\"maximum\":23},\"canvas\":{\"type\":\"object\",\"description\":\"Canvas size. It can be any size: the area outside the image is generated (outpaint), and if the canvas is smaller than the image, the part outside the canvas is cropped.\",\"properties\":{\"width\":{\"type\":\"integer\",\"description\":\"Canvas width\",\"required\":true},\"height\":{\"type\":\"integer\",\"description\":\"Canvas height\",\"required\":true}},\"required\":true},\"img_pos\":{\"type\":\"object\",\"description\":\"Image position and size within the canvas. width / height must keep the source image's aspect ratio (the simplest is the source image's pixel size); if the ratio differs too much, the task fails and the reserved credits are refunded. Image fills the canvas (img W/H = canvas W/H) = pure edit/repaint; image smaller than canvas = outpaint (the surrounding blank area is generated from the prompt).\",\"properties\":{\"width\":{\"type\":\"integer\",\"description\":\"Render width\",\"required\":true},\"height\":{\"type\":\"integer\",\"description\":\"Render height\",\"required\":true},\"x\":{\"type\":\"integer\",\"description\":\"Top-left horizontal offset\",\"required\":true},\"y\":{\"type\":\"integer\",\"description\":\"Top-left vertical offset\",\"required\":true}},\"required\":true},\"mask\":{\"type\":\"object\",\"description\":\"Optional masked region to repaint within the placed image (polygon coordinates or mask image) Method 1 - Polygon coordinates (width / height are usually the source image's pixel size; the numbers below are only an illustration; points are listed clockwise): json { \\\"areas\\\": [{ \\\"width\\\": 100, \\\"height\\\": 100, \\\"points\\\": [10, 10, 100, 10, 100, 100, 10, 100] }] } Method 2 - Mask image (black-and-white, white = repaint; same size as the source; URL or base64 data URI): json { \\\"url\\\": \\\"https://cdn.evolink.ai/model-cards/midjourney-v8-2/midjourney-v8-2-og-v1.jpg\\\" } (The URL above is a placeholder — repla…\",\"properties\":{\"areas\":{\"type\":\"array\",\"description\":\"Polygon region list\",\"items\":{\"type\":\"object\",\"properties\":{\"width\":{\"type\":\"integer\",\"description\":\"Basis width in source-image pixels (the coordinate space of points)\"},\"height\":{\"type\":\"integer\",\"description\":\"Basis height in source-image pixels (the coordinate space of points)\"},\"points\":{\"type\":\"array\",\"description\":\"Polygon vertex coordinates (x1,y1,x2,y2,...), in source-image pixels, listed clockwise starting from the top-left origin\",\"items\":{\"type\":\"integer\"}}}}},\"url\":{\"type\":\"string\",\"description\":\"Mask image URL or data URI. A black-and-white binary image with the same pixel size as the source image: white = repaint, black = keep. Base64 is accepted as a data URI (data:image/png;base64,...). Do not use PNG transparency for the mask: transparent pixels are treated as white (repaint).\",\"format\":\"uri\"}}},\"speed\":{\"type\":\"string\",\"description\":\"Speed mode; fast: Standard mode (default), 1x\",\"enum\":[\"fast\"],\"default\":\"fast\"}},\"required\":true}},\"example\":{\"prompt\":\"Beautiful mountain scenery background\",\"model_params\":{\"task_id\":\"task-unified-xxx\",\"image_number\":0,\"canvas\":{\"width\":1024,\"height\":1024},\"img_pos\":{\"width\":912,\"height\":512,\"x\":56,\"y\":256},\"speed\":\"fast\"}}},\"mj-v8.2-remix\":{\"model\":\"mj-v8.2-remix\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"Midjourney V8.2 Remix Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v8-2-remix\",\"required\":[\"prompt\",\"model_params\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"New prompt describing desired adjustment, supports Midjourney parameter syntax\",\"maxLength\":8100,\"required\":true},\"model_params\":{\"type\":\"object\",\"description\":\"Model parameters\",\"properties\":{\"task_id\":{\"type\":\"string\",\"description\":\"Source task ID\",\"required\":true},\"image_number\":{\"type\":\"integer\",\"description\":\"Select which source image: 0-3 for a fast source task, 0-23 for a draft source task (all 24 sketches are valid sources)\",\"default\":0,\"minimum\":0,\"maximum\":23},\"mode\":{\"type\":\"string\",\"description\":\"Remix strength; strong: Major adjustment; subtle: Minor adjustment\",\"enum\":[\"strong\",\"subtle\"],\"default\":\"strong\"},\"speed\":{\"type\":\"string\",\"description\":\"Speed mode; fast: Standard mode (default), 1x\",\"enum\":[\"fast\"],\"default\":\"fast\"}},\"required\":true}},\"example\":{\"prompt\":\"Convert to oil painting style --ar 1:1\",\"model_params\":{\"task_id\":\"task-unified-xxx\",\"image_number\":0,\"mode\":\"strong\",\"speed\":\"fast\"}}},\"mj-v8.2-remove-bg\":{\"model\":\"mj-v8.2-remove-bg\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"mj-v8.2-remove-bg Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v8-2-remove-bg\",\"required\":[\"image_urls\"],\"params\":{\"image_urls\":{\"type\":\"array\",\"description\":\"Input image URL (uses the first one) Supported formats: .png, .jpg, .jpeg\",\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true}},\"example\":{\"image_urls\":[\"https://cdn.evolink.ai/model-cards/midjourney-v8-2/midjourney-v8-2-og-v1.jpg\"]}},\"mj-v8.2-retexture\":{\"model\":\"mj-v8.2-retexture\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"mj-v8.2-retexture Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v8-2-retexture\",\"required\":[\"prompt\",\"image_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Describe target texture/style\",\"maxLength\":8100,\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Input image URL (uses the first one). Public HTTP(S) URL of at most 1024 characters; formats .png, .gif, .webp, .jpg, .jpeg\",\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"model_params\":{\"type\":\"object\",\"description\":\"Model parameters\",\"properties\":{\"speed\":{\"type\":\"string\",\"description\":\"Speed mode; fast: Standard mode (default), 1x\",\"enum\":[\"fast\"],\"default\":\"fast\"}}}},\"example\":{\"prompt\":\"Cyberpunk neon style\",\"image_urls\":[\"https://cdn.evolink.ai/model-cards/midjourney-v8-2/midjourney-v8-2-og-v1.jpg\"],\"model_params\":{\"speed\":\"fast\"}}},\"mj-v8.2-upload-paint\":{\"model\":\"mj-v8.2-upload-paint\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"mj-v8.2-upload-paint Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v8-2-upload-paint\",\"required\":[\"prompt\",\"image_urls\",\"model_params\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Edit prompt\",\"maxLength\":8100,\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Input image URL (first one is used). Public HTTP(S) URL of at most 1024 characters; formats .png, .gif, .webp, .jpg, .jpeg\",\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"model_params\":{\"type\":\"object\",\"description\":\"Advanced edit parameters\",\"properties\":{\"mask\":{\"type\":\"object\",\"description\":\"Masked region to repaint (polygon coordinates or mask image) Method 1 - Polygon coordinates (width / height are usually the source image's pixel size; the numbers below are only an illustration; points are listed clockwise): json { \\\"areas\\\": [{ \\\"width\\\": 100, \\\"height\\\": 100, \\\"points\\\": [10, 10, 100, 10, 100, 100, 10, 100] }] } Method 2 - Mask image (black-and-white, white = repaint; same size as the source; URL or base64 data URI): json { \\\"url\\\": \\\"https://cdn.evolink.ai/model-cards/midjourney-v8-2/midjourney-v8-2-og-v1.jpg\\\" } (The URL above is a placeholder — replace it with your own black-and-whi…\",\"properties\":{\"areas\":{\"type\":\"array\",\"description\":\"Polygon region list\",\"items\":{\"type\":\"object\",\"properties\":{\"width\":{\"type\":\"integer\",\"description\":\"Basis width in source-image pixels (the coordinate space of points)\"},\"height\":{\"type\":\"integer\",\"description\":\"Basis height in source-image pixels (the coordinate space of points)\"},\"points\":{\"type\":\"array\",\"description\":\"Polygon vertex coordinates (x1,y1,x2,y2,...), in source-image pixels, listed clockwise starting from the top-left origin\",\"items\":{\"type\":\"integer\"}}}}},\"url\":{\"type\":\"string\",\"description\":\"Mask image URL or data URI. A black-and-white binary image with the same pixel size as the source image: white = repaint, black = keep. Base64 is accepted as a data URI (data:image/png;base64,...). Do not use PNG transparency for the mask: transparent pixels are treated as white (repaint).\",\"format\":\"uri\"}},\"required\":true},\"canvas\":{\"type\":\"object\",\"description\":\"Canvas size. It can be any size: the area outside the image is generated (outpaint), and if the canvas is smaller than the image, the part outside the canvas is cropped.\",\"properties\":{\"width\":{\"type\":\"integer\",\"description\":\"Canvas width\",\"required\":true},\"height\":{\"type\":\"integer\",\"description\":\"Canvas height\",\"required\":true}},\"required\":true},\"img_pos\":{\"type\":\"object\",\"description\":\"Image position and size within the canvas. width / height must keep the uploaded image's aspect ratio (the simplest is its pixel size); if the ratio differs too much, the task fails and the reserved credits are refunded. Image fills the canvas (img W/H = canvas W/H) = pure edit/repaint; image smaller than canvas = outpaint (the surrounding blank area is generated from the prompt).\",\"properties\":{\"width\":{\"type\":\"integer\",\"description\":\"Render width\",\"required\":true},\"height\":{\"type\":\"integer\",\"description\":\"Render height\",\"required\":true},\"x\":{\"type\":\"integer\",\"description\":\"Top-left horizontal offset\",\"required\":true},\"y\":{\"type\":\"integer\",\"description\":\"Top-left vertical offset\",\"required\":true}},\"required\":true},\"speed\":{\"type\":\"string\",\"description\":\"Speed mode; fast: Standard mode (default), 1x\",\"enum\":[\"fast\"],\"default\":\"fast\"}},\"required\":true}},\"example\":{\"prompt\":\"Beautiful mountain scenery background\",\"image_urls\":[\"https://cdn.evolink.ai/model-cards/midjourney-v8-2/midjourney-v8-2-og-v1.jpg\"],\"model_params\":{\"mask\":{\"areas\":[{\"width\":1200,\"height\":630,\"points\":[100,100,400,100,400,400,100,400]}]},\"canvas\":{\"width\":1200,\"height\":630},\"img_pos\":{\"width\":1200,\"height\":630,\"x\":0,\"y\":0},\"speed\":\"fast\"}}},\"mj-v8.2-variation\":{\"model\":\"mj-v8.2-variation\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"Midjourney V8.2 Variation Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v8-2-variation\",\"required\":[\"model_params\"],\"params\":{\"model_params\":{\"type\":\"object\",\"description\":\"Model parameters\",\"properties\":{\"task_id\":{\"type\":\"string\",\"description\":\"Source task ID, must be a completed mj-v8.2 series task (image generation, variation, remix or edit) that belongs to the current user\",\"required\":true},\"image_number\":{\"type\":\"integer\",\"description\":\"Select which source image: 0-3 for a fast source task, 0-23 for a draft source task (all 24 sketches are valid sources)\",\"default\":0,\"minimum\":0,\"maximum\":23},\"type\":{\"type\":\"string\",\"description\":\"Variation strength; subtle: Subtle variation; strong: Strong variation\",\"enum\":[\"subtle\",\"strong\"],\"default\":\"subtle\"}},\"required\":true}},\"example\":{\"model_params\":{\"task_id\":\"task-unified-xxx\",\"image_number\":2,\"type\":\"strong\"}}},\"nano-banana-2-beta\":{\"model\":\"nano-banana-2-beta\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"Nano Banana 2 Beta Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/nanobanana/nanobanana-2-beta-image-generate\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the image to be generated, or describing how to edit the input image, limited to 2000 tokens\",\"maxLength\":2000,\"required\":true},\"size\":{\"type\":\"string\",\"description\":\"Aspect ratio of the generated image, default is auto\",\"enum\":[\"auto\",\"1:1\",\"1:4\",\"4:1\",\"1:8\",\"8:1\",\"2:3\",\"3:2\",\"3:4\",\"4:3\",\"4:5\",\"5:4\",\"9:16\",\"16:9\",\"21:9\"]},\"quality\":{\"type\":\"string\",\"description\":\"Quality of the generated image, default is 2K Note: Different quality levels have different pricing\",\"enum\":[\"1K\",\"2K\",\"4K\"]},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL list for image-to-image and image editing functions Note: Maximum number of input images per request: 14; Image size: not exceeding 10MB; Supported file formats: .jpeg, .jpg, .png, .webp; Image URLs must be directly accessible by the server, or the image URL should directly download when accessed (typically these URLs end with image file extensions, such as .png, .jpg); Maximum of 4 real person images can be uploaded\",\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"model_params\":{\"type\":\"object\",\"description\":\"Model extension parameters\",\"properties\":{\"thinking_level\":{\"type\":\"string\",\"description\":\"Thinking level, controls the depth of reasoning the model performs before generating images, defaults to auto; auto: Automatically selects thinking level; min: Minimal reasoning, fastest; high: Deep reasoning, best quality\",\"enum\":[\"auto\",\"min\",\"high\"]}}}},\"example\":{\"prompt\":\"A cat playing on the grass\"}},\"nano-banana-2-lite-beta\":{\"model\":\"nano-banana-2-lite-beta\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"Nano Banana 2 Lite Beta Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/nanobanana/nanobanana-2-lite-beta-image-generate\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the image to be generated, or describing how to edit the input image, limited to 2000 tokens\",\"maxLength\":2000,\"required\":true},\"size\":{\"type\":\"string\",\"description\":\"Aspect ratio of the generated image, default is auto\",\"enum\":[\"auto\",\"1:1\",\"1:4\",\"4:1\",\"1:8\",\"8:1\",\"2:3\",\"3:2\",\"3:4\",\"4:3\",\"4:5\",\"5:4\",\"9:16\",\"16:9\",\"21:9\"]},\"quality\":{\"type\":\"string\",\"description\":\"Quality of the generated image, default is 1K; currently only 1K is supported\",\"enum\":[\"1K\"]},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL list for image-to-image and image editing functions Note: Maximum number of input images per request: 14; Image size: not exceeding 20MB; Supported file formats: .jpeg, .jpg, .png, .webp; Image URLs must be directly accessible by the server, or the image URL should directly download when accessed (typically these URLs end with image file extensions, such as .png, .jpg)\",\"items\":{\"type\":\"string\",\"format\":\"uri\"}}},\"example\":{\"prompt\":\"A cat playing on the grass\"}},\"nano-banana-beta\":{\"model\":\"nano-banana-beta\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"nano-banana Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/nanobanana/nanobanana-image-generate\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the image to be generated, or describing how to edit the input image, limited to 2000 tokens\",\"maxLength\":2000,\"required\":true},\"size\":{\"type\":\"string\",\"description\":\"Aspect ratio of the generated image, default value is auto\",\"enum\":[\"auto\",\"1:1\",\"2:3\",\"3:2\",\"4:3\",\"3:4\",\"16:9\",\"9:16\"]},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL list for image-to-image and image editing functions Note: Maximum number of input images per request: 5; Image size: not exceeding 10MB; Supported file formats: .jpeg, .jpg, .png, .webp; Image URLs must be directly accessible by the server, or the image URL should directly download when accessed (typically these URLs end with image file extensions, such as .png, .jpg)\",\"items\":{\"type\":\"string\",\"format\":\"uri\"}}},\"example\":{\"prompt\":\"A cat playing on the grass\"}},\"nano-banana-pro-beta\":{\"model\":\"nano-banana-pro-beta\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"Nano Banana Pro Beta Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/nanobanana/nanobanana-pro-beta-image-generate\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the image you want to generate, or describing how to edit the input image, limited to 2000 tokens\",\"maxLength\":2000,\"required\":true},\"size\":{\"type\":\"string\",\"description\":\"Aspect ratio of generated image, default is auto\",\"enum\":[\"auto\",\"1:1\",\"2:3\",\"3:2\",\"3:4\",\"4:3\",\"4:5\",\"5:4\",\"9:16\",\"16:9\",\"21:9\"]},\"quality\":{\"type\":\"string\",\"description\":\"Quality of generated image, default is 2K Note: 4K quality will incur additional charges\",\"enum\":[\"1K\",\"2K\",\"4K\"]},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL list for image-to-image and image editing features Note: Single request supports input image quantity: 10 images; Image size: no more than 10MB; Supported file formats: .jpeg, .jpg, .png, .webp; Image URLs must be directly viewable by the server, or the image URL should trigger direct download when accessed (typically these URLs end with image file extensions, such as .png, .jpg); Maximum 5 real person images can be uploaded\",\"items\":{\"type\":\"string\",\"format\":\"uri\"}}},\"example\":{\"prompt\":\"A cat playing on the grass\"}},\"omnihuman-1.5\":{\"model\":\"omnihuman-1.5\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"OmniHuman-1.5 Digital Human Video Generation\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/omnihuman/omnihuman-1.5-video-generate\",\"required\":[\"audio_url\",\"image_urls\"],\"params\":{\"audio_url\":{\"type\":\"string\",\"description\":\"Audio URL for driving lip-sync and body movements Note: Maximum audio duration: 35 seconds; Supported formats: .mp3, .wav; Audio URLs must be directly accessible by the server; Billing is based on audio duration (rounded up to the nearest second)\",\"format\":\"uri\",\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL list containing the person to animate Note: Number of images per request: 1; Image should contain a clear human figure; Image size: no more than 10MB; Supported file formats: .jpg, .jpeg, .png, .webp; Image URLs must be directly viewable by the server\",\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"prompt\":{\"type\":\"string\",\"description\":\"Optional text prompt to guide the generation style, only supports Chinese, English, Japanese, Korean, Mexican Spanish, and Indonesian\"},\"pe_fast_mode\":{\"type\":\"boolean\",\"description\":\"Enable fast processing mode Note: true: Faster generation with potentially lower quality; false: Standard quality processing (default)\",\"default\":false},\"mask_url\":{\"type\":\"array\",\"description\":\"Mask URL array for specifying animation regions Note: Optional parameter for advanced control; Mask images should match the reference image dimensions\",\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"seed\":{\"type\":\"integer\",\"description\":\"Random seed as the basis for determining the initial diffusion state, default random. If the seed is the same positive integer and all other parameters are consistent, the generated content may have consistent results\"},\"subject_check\":{\"type\":\"boolean\",\"description\":\"Enable subject detection to verify human presence in the image Note: true: Enable subject detection, request initiation time will increase; false: Skip subject detection (default)\",\"default\":false},\"auto_mask\":{\"type\":\"boolean\",\"description\":\"Enable automatic mask generation Note: true: Automatically detect and mask the human figure, request initiation time will increase. This parameter is ignored when mask_url has a value; false: Use provided mask_url or no mask (default)\",\"default\":false}},\"example\":{\"audio_url\":\"https://example.com/audio.mp3\",\"image_urls\":[\"https://example.com/person.jpg\"]}},\"qwen-image-3.0\":{\"model\":\"qwen-image-3.0\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"qwen-image-3.0 Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/qwen/qwen-image-3.0\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the image to generate (text-to-image), or how to edit the input image (image editing). Limited to 4500 tokens\",\"maxLength\":4500,\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL list (optional). Not provided or empty array = text-to-image (T2I); provide 1-3 images = image editing (I2I) Note: Number of input images supported per request: 0-3 images, more than 3 will return an error; Only public http/https image URLs are supported, base64 / data-url is not supported; Image width and height must both be within the [384-3072] pixel range; Supported file formats: .jpg, .jpeg, .png, .bmp, .webp, .tiff; Image URLs must be directly accessible by the server, or the image URL should directly download when accessed (typically these URLs end with image file e…\",\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"n\":{\"type\":\"integer\",\"description\":\"Specifies the number of images to generate, supports any integer value between [1,6] Note: Each request will be pre-charged based on the value of n, actual charges are based on the number of images generated; The reference image (image_urls) charge is billed once per uploaded image and does not scale with n\",\"default\":1,\"minimum\":1,\"maximum\":6},\"negative_prompt\":{\"type\":\"string\",\"description\":\"Negative prompt to describe content you don't want to see in the image, used to constrain the output Note: Supports Chinese and English, maximum length of 500 characters, each Chinese character/letter counts as one character, excess will be automatically truncated\",\"maxLength\":500},\"size\":{\"type\":\"string\",\"description\":\"Dimensions of the generated image. Three approaches are supported: Option 1 - Auto (default): auto: the model automatically selects an appropriate output size based on the prompt (in this case quality has no effect) Option 2 - Aspect-ratio format: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9, 9:21; Used together with the quality parameter; the system automatically converts to the pixels corresponding to the chosen ratio and resolution, with no need to specify them manually Option 3 - Pixel format: width×height, e.g. 1024x1024, 2048x2048, 2720x1530, etc.; Total pixel range: [262144, 419…\",\"default\":\"auto\"},\"quality\":{\"type\":\"string\",\"description\":\"Resolution tier, used together with the aspect-ratio format of size; defaults to 1K (has no effect under auto or the pixel format). | Ratio | 1K | 2K | |---|---|---| | 1:1 | 1024×1024 | 2048×2048 | | 2:3 | 832×1248 | 1664×2496 | | 3:2 | 1248×832 | 2496×1664 | | 3:4 | 864×1152 | 1770×2360 | | 4:3 | 1152×864 | 2360×1770 | | 4:5 | 896×1120 | 1792×2240 | | 5:4 | 1120×896 | 2240×1792 | | 9:16 | 800×1424 | 1530×2720 | | 16:9 | 1424×800 | 2720×1530 | | 21:9 | 1568×672 | 3122×1338 | | 9:21 | 672×1568 | 1338×3122 |\",\"enum\":[\"1K\",\"2K\"],\"default\":\"1K\"},\"prompt_extend\":{\"type\":\"boolean\",\"description\":\"Whether to enable intelligent prompt rewriting. Default value is false (does not rewrite the user's prompt without permission); only when explicitly set to true will a large model be used to optimize the positive prompt, with noticeable improvement for insufficiently descriptive or simpler prompts\",\"default\":false},\"watermark\":{\"type\":\"boolean\",\"description\":\"Whether to add \\\"Qwen-Image\\\" watermark to the bottom right corner of the image. Default value is false\",\"default\":false},\"seed\":{\"type\":\"integer\",\"description\":\"Random seed, range [0, 2147483647], using the same seed value can keep generated content relatively stable Note: If not provided, the algorithm will automatically use a random seed; Model generation process is probabilistic, even with the same seed, results cannot be guaranteed to be completely identical each time\",\"minimum\":0,\"maximum\":2147483647}},\"example\":{\"prompt\":\"An orange cat wearing an astronaut helmet, cyberpunk neon background\",\"size\":\"16:9\",\"quality\":\"2K\"}},\"qwen-image-3.0-pro\":{\"model\":\"qwen-image-3.0-pro\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"qwen-image-3.0-pro Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/qwen/qwen-image-3.0-pro\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the image to generate (text-to-image), or how to edit the input image (image editing). Limited to 4500 tokens\",\"maxLength\":4500,\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL list (optional). Not provided or empty array = text-to-image (T2I); provide 1-3 images = image editing (I2I) Note: Number of input images supported per request: 0-3 images, more than 3 will return an error; Only public http/https image URLs are supported, base64 / data-url is not supported; Image width and height must both be within the [384-3072] pixel range; Supported file formats: .jpg, .jpeg, .png, .bmp, .webp, .tiff; Image URLs must be directly accessible by the server, or the image URL should directly download when accessed (typically these URLs end with image file e…\",\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"n\":{\"type\":\"integer\",\"description\":\"Specifies the number of images to generate, supports any integer value between [1,6] Note: Each request will be pre-charged based on the value of n, actual charges are based on the number of images generated; The reference image (image_urls) charge is billed once per uploaded image and does not scale with n\",\"default\":1,\"minimum\":1,\"maximum\":6},\"negative_prompt\":{\"type\":\"string\",\"description\":\"Negative prompt to describe content you don't want to see in the image, used to constrain the output Note: Supports Chinese and English, maximum length of 500 characters, each Chinese character/letter counts as one character, excess will be automatically truncated\",\"maxLength\":500},\"size\":{\"type\":\"string\",\"description\":\"Dimensions of the generated image. Three approaches are supported: Option 1 - Auto (default): auto: the model automatically selects an appropriate output size based on the prompt (in this case quality has no effect) Option 2 - Aspect-ratio format: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9, 9:21; Used together with the quality parameter; the system automatically converts to the pixels corresponding to the chosen ratio and resolution, with no need to specify them manually Option 3 - Pixel format: width×height, e.g. 1024x1024, 2048x2048, 2720x1530, etc.; Total pixel range: [262144, 419…\",\"default\":\"auto\"},\"quality\":{\"type\":\"string\",\"description\":\"Resolution tier, used together with the aspect-ratio format of size; defaults to 1K (has no effect under auto or the pixel format). | Ratio | 1K | 2K | |---|---|---| | 1:1 | 1024×1024 | 2048×2048 | | 2:3 | 832×1248 | 1664×2496 | | 3:2 | 1248×832 | 2496×1664 | | 3:4 | 864×1152 | 1770×2360 | | 4:3 | 1152×864 | 2360×1770 | | 4:5 | 896×1120 | 1792×2240 | | 5:4 | 1120×896 | 2240×1792 | | 9:16 | 800×1424 | 1530×2720 | | 16:9 | 1424×800 | 2720×1530 | | 21:9 | 1568×672 | 3122×1338 | | 9:21 | 672×1568 | 1338×3122 |\",\"enum\":[\"1K\",\"2K\"],\"default\":\"1K\"},\"prompt_extend\":{\"type\":\"boolean\",\"description\":\"Whether to enable intelligent prompt rewriting. Default value is false (does not rewrite the user's prompt without permission); only when explicitly set to true will a large model be used to optimize the positive prompt, with noticeable improvement for insufficiently descriptive or simpler prompts\",\"default\":false},\"watermark\":{\"type\":\"boolean\",\"description\":\"Whether to add \\\"Qwen-Image\\\" watermark to the bottom right corner of the image. Default value is false\",\"default\":false},\"seed\":{\"type\":\"integer\",\"description\":\"Random seed, range [0, 2147483647], using the same seed value can keep generated content relatively stable Note: If not provided, the algorithm will automatically use a random seed; Model generation process is probabilistic, even with the same seed, results cannot be guaranteed to be completely identical each time\",\"minimum\":0,\"maximum\":2147483647}},\"example\":{\"prompt\":\"An orange cat wearing an astronaut helmet, cyberpunk neon background\",\"size\":\"16:9\",\"quality\":\"2K\"}},\"qwen-image-edit\":{\"model\":\"qwen-image-edit\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"qwen-image-edit Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/qwen/qwen-image-edit\",\"required\":[\"prompt\",\"image_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the image to generate or how to edit the input image, limited to 2000 tokens\",\"maxLength\":2000,\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL list Note: Maximum number of input images per request: 3 images; Image width and height must be within [384-3072] pixel range; Supported file formats: .jpg, .jpeg, .png, .bmp, .webp, .tiff; Image URLs must be directly accessible by the server, or the image URL should directly download when accessed (typically these URLs end with image file extensions, such as .png, .jpg)\",\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true}},\"example\":{\"prompt\":\"Replace the background of this image\",\"image_urls\":[\"https://example.com/image1.png\"]}},\"qwen-image-edit-plus\":{\"model\":\"qwen-image-edit-plus\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"qwen-image-edit-plus Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/qwen/qwen-image-edit-plus\",\"required\":[\"prompt\",\"image_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the image to generate or how to edit the input image, limited to 2000 tokens\",\"maxLength\":2000,\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL list Note: Maximum number of input images per request: 3 images; Image width and height must be within [384-3072] pixel range; Supported file formats: .jpg, .jpeg, .png, .bmp, .webp, .tiff; Image URLs must be directly accessible by the server, or the image URL should directly download when accessed (typically these URLs end with image file extensions, such as .png, .jpg)\",\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"n\":{\"type\":\"integer\",\"description\":\"Specifies the number of images to generate, supports any integer value between [1,6] Note: Each request will be pre-charged based on the value of n, actual charges are based on the number of images generated\",\"default\":1,\"minimum\":1,\"maximum\":6},\"negative_prompt\":{\"type\":\"string\",\"description\":\"Negative prompt to describe content you don't want to see in the image, used to constrain the output Note: Supports Chinese and English, maximum length of 500 characters, each Chinese character/letter counts as one character, excess will be automatically truncated\",\"maxLength\":500},\"size\":{\"type\":\"string\",\"description\":\"Generated image size, supports pixel format: Width x Height, such as: 1024x1024, 1024x1536, 1536x1024 and other values within range; Width and height range: [512, 2048] pixels; If not set, output image will maintain aspect ratio similar to original image, close to 1024x1024 resolution Note: This parameter is only available when the number of output images n is 1, otherwise an error will be returned\"},\"prompt_extend\":{\"type\":\"boolean\",\"description\":\"Whether to enable intelligent prompt rewriting. When enabled, uses a large model to optimize the positive prompt, significantly improving results for simple or insufficiently descriptive prompts. Default value is true\",\"default\":true},\"watermark\":{\"type\":\"boolean\",\"description\":\"Whether to add \\\"Qwen-Image\\\" watermark to the bottom right corner of the image. Default value is false\",\"default\":false},\"seed\":{\"type\":\"integer\",\"description\":\"Random seed, range [0, 2147483647], using the same seed value can keep generated content relatively stable Note: If not provided, the algorithm will automatically use a random seed; Model generation process is probabilistic, even with the same seed, results cannot be guaranteed to be completely identical each time\",\"minimum\":0,\"maximum\":2147483647}},\"example\":{\"prompt\":\"Replace the background of this image\",\"image_urls\":[\"https://example.com/image1.png\"]}},\"qwen-voice-design\":{\"model\":\"qwen-voice-design\",\"kind\":\"audio\",\"path\":\"/v1/audios/generations\",\"title\":\"Qwen Voice Design\",\"docs\":\"https://evolink.ai/docs/en/api-manual/audio-series/qwen-tts/qwen-voice-design\",\"required\":[\"voice_prompt\",\"preview_text\",\"preferred_name\"],\"params\":{\"voice_prompt\":{\"type\":\"string\",\"description\":\"A text description of the voice characteristics used to define the voice profile Constraints: Maximum 2048 characters; Supports Chinese and English only Suggested dimensions: Gender: male, female, neutral; Age: child (5-12), teen (13-18), young adult (19-35), middle-aged (36-55), senior (55+); Pitch: high, medium, low; Pace: fast, moderate, slow; Emotion: cheerful, calm, gentle, serious, lively, composed; Character: magnetic, crisp, husky, mellow, sweet, deep; Use case: news broadcasting, commercial narration, audiobook, animation character, voice assistant Example descriptions: A calm middle…\",\"maxLength\":2048,\"required\":true},\"preview_text\":{\"type\":\"string\",\"description\":\"Preview text used to generate a sample audio clip Constraints: Maximum 1024 characters; Supports 10 languages: Chinese, English, Japanese, Korean, German, French, Italian, Russian, Portuguese, Spanish; Recommended to match the language field\",\"maxLength\":1024,\"required\":true},\"preferred_name\":{\"type\":\"string\",\"description\":\"Voice name prefix Constraints: Only digits, English letters, and underscores; No more than 16 characters The generated full voice name format: qwen-tts-vd-{preferred_name}-voice-{timestamp} For example, passing announcer results in a voice name like: qwen-tts-vd-announcer-voice-20260402-a1b2\",\"maxLength\":16,\"required\":true},\"language\":{\"type\":\"string\",\"description\":\"Language preference for the voice profile; recommended to match preview_text Defaults to zh if not provided\",\"enum\":[\"zh\",\"en\",\"ja\",\"ko\",\"de\",\"fr\",\"it\",\"ru\",\"pt\",\"es\"]},\"sample_rate\":{\"type\":\"integer\",\"description\":\"Preview audio sample rate (Hz) Defaults to 24000 if not provided\",\"enum\":[8000,16000,24000,48000]},\"response_format\":{\"type\":\"string\",\"description\":\"Preview audio format Defaults to wav if not provided\",\"enum\":[\"pcm\",\"wav\",\"mp3\",\"opus\"]},\"target_model\":{\"type\":\"string\",\"description\":\"The TTS model that will drive the created voice Important: The target_model specified when creating the voice must match the model used in subsequent speech synthesis; otherwise synthesis will fail | Value | Description | |-----|------| | qwen3-tts-vd-2026-01-26 | Qwen3-TTS-VD non-streaming (default) | | qwen3-tts-vd-realtime-2026-01-15 | Qwen3-TTS-VD-Realtime bidirectional streaming (new) | | qwen3-tts-vd-realtime-2025-12-16 | Qwen3-TTS-VD-Realtime bidirectional streaming (legacy) | > Currently this platform supports qwen3-tts-vd-2026-01-26 (non-streaming); realtime models are not yet integr…\",\"enum\":[\"qwen3-tts-vd-2026-01-26\",\"qwen3-tts-vd-realtime-2026-01-15\",\"qwen3-tts-vd-realtime-2025-12-16\"],\"default\":\"qwen3-tts-vd-2026-01-26\"}},\"example\":{\"voice_prompt\":\"A calm middle-aged male news anchor with a deep, resonant voice, rich in magnetism, steady pace, and clear articulation\",\"preview_text\":\"Good evening, listeners. Welcome to the evening news broadcast.\",\"preferred_name\":\"announcer\"}},\"qwen3-tts-vd\":{\"model\":\"qwen3-tts-vd\",\"kind\":\"audio\",\"path\":\"/v1/audios/generations\",\"title\":\"Qwen3 TTS VD Speech Synthesis\",\"docs\":\"https://evolink.ai/docs/en/api-manual/audio-series/qwen-tts/qwen3-tts-vd\",\"required\":[\"prompt\",\"voice\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text to synthesize Constraints: Maximum 600 characters\",\"maxLength\":600,\"required\":true},\"voice\":{\"type\":\"string\",\"description\":\"Voice name; Must first create a voice via [Qwen Voice Design](/en/api-manual/audio-series/qwen-tts/qwen-voice-design); Obtain the value from result_data.voice in the Voice Design task result; System built-in voices are not supported\",\"required\":true},\"language_type\":{\"type\":\"string\",\"description\":\"Language hint to help the model select pronunciation rules Auto-detected if not provided\",\"enum\":[\"Auto\",\"Chinese\",\"English\",\"Japanese\",\"Korean\",\"French\",\"German\",\"Spanish\",\"Italian\",\"Russian\",\"Portuguese\"]}},\"example\":{\"prompt\":\"Good evening, listeners. Welcome to the evening news broadcast.\",\"voice\":\"qwen-tts-vd-announcer-voice-20260402-a1b2\"}},\"seedance-1.5-pro\":{\"model\":\"seedance-1.5-pro\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"seedance-1.5-pro API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/seedance1.5/seedance-1.5-pro-video-generate\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the video you want to generate, limited to 2000 tokens\",\"maxLength\":2000,\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL list for image-to-video functionality Mode Detection: 0 images = text-to-video; 1 image = image-to-video; 2 images = first-last-frame Note: Number of images supported per request: 2 images; Image size: Not exceeding 10MB; Supported file formats: .jpg, .jpeg, .png, .webp; Aspect ratio (width/height): 0.4 ~ 2.5; Width and height: 300 ~ 6000 px; Image URLs must be directly viewable by the server, or the URL should trigger a direct download when accessed (typically these URLs end with image extensions like .png, .jpg)\",\"maxItems\":2,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"duration\":{\"type\":\"integer\",\"description\":\"Specifies the duration of the generated video (in seconds), defaults to 5 seconds Note: Supports any integer value between 4 and 12 seconds; Billing for a single request is based on the duration value; longer durations result in higher costs\",\"minimum\":4,\"maximum\":12},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution, defaults to 720p Note: 480p: Lower resolution, lower pricing; 720p: Standard definition, standard pricing, this is the default value; 1080p: High definition, higher pricing\",\"enum\":[\"480p\",\"720p\",\"1080p\"]},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio Supported values: 16:9 (landscape), 9:16 (portrait), 1:1 (square), 4:3, 3:4, 21:9 (ultra-wide), adaptive; Default value: 16:9\"},\"generate_audio\":{\"type\":\"boolean\",\"description\":\"Whether to generate audio, enabling will increase cost, defaults to true Options: true: Model output video includes synchronized audio. Seedance 1.5 Pro can automatically generate matching voice, sound effects, and background music based on text prompts and visual content. It is recommended to place dialogue within double quotes to optimize audio generation. Example: The man stopped the woman and said: \\\"Remember, you must never point at the moon with your finger.\\\"; false: Model output video is silent\",\"default\":true}},\"example\":{\"prompt\":\"A cat playing piano\"}},\"seedance-2.0-fast-image-to-video\":{\"model\":\"seedance-2.0-fast-image-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Seedance 2.0 Fast Image-to-Video\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/seedance2.0/seedance-2.0-fast-image-to-video\",\"required\":[\"prompt\",\"image_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing the desired video. Supports both Chinese and English, recommended no more than 500 characters for Chinese or 1000 words for English. Maximum prompt length: 10000 tokens Note: This model does not support video_urls or audio_urls input\",\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Image URL array, 1–2 images Image count and behavior: | Image Count | Behavior | Role | |:--------:|------|------| | 1 image | First-frame image-to-video | Automatically set as first_frame | | 2 images | First-last-frame image-to-video | 1st image → first_frame, 2nd image → last_frame | Image requirements: Supported formats: .jpeg, .png, .webp; Aspect ratio (width/height): 0.4 ~ 2.5; Width/height pixels: 300 ~ 6000 px; Max size per image: 30MB; Total request body size must not exceed 64MB, do not use Base64 encoding for large files; When providing first and last frames, both images can be ide…\",\"minItems\":1,\"maxItems\":2,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds), defaults to 5 seconds Details: Supports any integer value between 4–15 seconds; Duration directly affects billing\",\"default\":5,\"minimum\":4,\"maximum\":15},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution, defaults to 720p Options: 480p: Lower clarity, lower cost; 720p: Standard clarity, this is the default; 1080p: Ultra HD clarity, coming soon\",\"enum\":[\"480p\",\"720p\"],\"default\":\"720p\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio, defaults to adaptive Options: 16:9 (landscape), 9:16 (portrait), 1:1 (square), 4:3, 3:4, 21:9 (ultrawide); adaptive: Automatically selects the closest aspect ratio based on the first-frame image proportions Pixel values per resolution: | Aspect Ratio | 480p | 720p | |:------:|:----:|:----:| | 16:9 | 864×496 | 1280×720 | | 4:3 | 752×560 | 1112×834 | | 1:1 | 640×640 | 960×960 | | 3:4 | 560×752 | 834×1112 | | 9:16 | 496×864 | 720×1280 | | 21:9 | 992×432 | 1470×630 |\",\"enum\":[\"16:9\",\"9:16\",\"1:1\",\"4:3\",\"3:4\",\"21:9\",\"adaptive\"],\"default\":\"adaptive\"},\"generate_audio\":{\"type\":\"boolean\",\"description\":\"Whether to generate synchronized audio, defaults to true Options: true: Video includes synchronized audio at no additional charge; false: Output silent video\",\"default\":true},\"content_filter\":{\"type\":\"boolean\",\"description\":\"Content filter, enabled by default true Options: true: Standard content safety check, this is the default; false: Relaxes content restrictions, billed at +10% (1.1x). Illegal and prohibited content is always enforced regardless of this setting Mutually exclusive with web search: content_filter: false and model_params.web_search: true cannot be used together; sending both returns a 400 parameter error; Keep content_filter: true (the default) when web search is needed\",\"default\":true}},\"example\":{\"prompt\":\"The camera slowly zooms in, the scene gradually comes to life\",\"image_urls\":[\"https://example.com/first-frame.jpg\"],\"duration\":5,\"aspect_ratio\":\"adaptive\"}},\"seedance-2.0-fast-reference-to-video\":{\"model\":\"seedance-2.0-fast-reference-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Seedance 2.0 Fast Reference-to-Video\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/seedance2.0/seedance-2.0-fast-reference-to-video\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing the desired video. Supports both Chinese and English, recommended no more than 500 characters for Chinese. Maximum prompt length: 10000 tokens Details: When referring to input materials in the prompt, prefer explicit tags such as @image1, @video1, and @audio1 instead of relying only on natural-language references such as \\\"image 1\\\", \\\"video 1\\\", or \\\"audio 1\\\"; Tag numbers follow the order of the corresponding URL array and start at 1: the first image_urls item is @image1, the first video_urls item is @video1, and the first audio_urls item is @audio1; Natural-language number…\",\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL array, 0–9 images Role description: | Media Type | Role | Typical Usage | |---------|------|----------| | Image | reference_image | Style reference, product image, character appearance, first/last frame (specified via prompt) | Image requirements: Supported formats: .jpeg, .png, .webp; Aspect ratio (width/height): 0.4 ~ 2.5; Width/height pixels: 300 ~ 6000 px; Max size per image: 30MB; Total request body size must not exceed 64MB, do not use Base64 encoding; Image URLs must be directly accessible by the server Note: You cannot provide only audio_urls; at least 1 image (ima…\",\"maxItems\":9,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"video_urls\":{\"type\":\"array\",\"description\":\"Reference video URL array, 0–3 videos Role description: | Media Type | Role | Typical Usage | |---------|------|----------| | Video | reference_video | Camera movement reference, motion reference, original video for editing/extension | Video requirements: Supported formats: .mp4, .mov; Resolution: 480p, 720p, 1080p; Duration per video: 2 ~ 15 seconds, max 3 videos, total duration of all videos ≤ 15 seconds; Aspect ratio (width/height): 0.4 ~ 2.5; Width/height pixels: 300 ~ 6000 px; Frame pixels (width × height): 409,600 ~ 2,086,876 (e.g., 640×640 ~ 2206×946); Max size per video: 50MB; Frame r…\",\"maxItems\":3,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"audio_urls\":{\"type\":\"array\",\"description\":\"Reference audio URL array, 0–3 clips Role description: | Media Type | Role | Typical Usage | |---------|------|----------| | Audio | reference_audio | Background music, sound effects, voice/dialogue reference | Audio requirements: Supported formats: .wav, .mp3; Duration per clip: 2 ~ 15 seconds, max 3 clips, total duration of all audio ≤ 15 seconds; Max size per clip: 15MB; Total request body size must not exceed 64MB, do not use Base64 encoding; Audio URLs must be directly accessible by the server Note: Audio cannot be provided alone; at least 1 reference video or image must be included\",\"maxItems\":3,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"duration\":{\"type\":\"integer\",\"description\":\"Output video duration (seconds), defaults to 5 seconds Details: Supports any integer value between 4–15 seconds; Duration directly affects billing\",\"default\":5,\"minimum\":4,\"maximum\":15},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution, defaults to 720p Options: 480p: Lower clarity, lower cost; 720p: Standard clarity, this is the default; 1080p: Ultra HD clarity, coming soon\",\"enum\":[\"480p\",\"720p\"],\"default\":\"720p\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio, defaults to adaptive Options: 16:9 (landscape), 9:16 (portrait), 1:1 (square), 4:3, 3:4, 21:9 (ultrawide); adaptive: Determined based on prompt intent, priority: video > image > prompt Pixel values per resolution: | Aspect Ratio | 480p | 720p | |:------:|:----:|:----:| | 16:9 | 864×496 | 1280×720 | | 4:3 | 752×560 | 1112×834 | | 1:1 | 640×640 | 960×960 | | 3:4 | 560×752 | 834×1112 | | 9:16 | 496×864 | 720×1280 | | 21:9 | 992×432 | 1470×630 |\",\"enum\":[\"16:9\",\"9:16\",\"1:1\",\"4:3\",\"3:4\",\"21:9\",\"adaptive\"],\"default\":\"adaptive\"},\"generate_audio\":{\"type\":\"boolean\",\"description\":\"Whether to generate synchronized audio, defaults to true Options: true: Video includes synchronized audio at no additional charge; false: Output silent video\",\"default\":true},\"content_filter\":{\"type\":\"boolean\",\"description\":\"Content filter, enabled by default true Options: true: Standard content safety check, this is the default; false: Relaxes content restrictions, billed at +10% (1.1x). Illegal and prohibited content is always enforced regardless of this setting Mutually exclusive with web search: content_filter: false and model_params.web_search: true cannot be used together; sending both returns a 400 parameter error; Keep content_filter: true (the default) when web search is needed\",\"default\":true}},\"example\":{\"prompt\":\"Use the first-person perspective framing of @video1 throughout, and use @audio1 as background music throughout. First-person perspective fruit tea promotional video...\",\"image_urls\":[\"https://example.com/ref1.jpg\",\"https://example.com/ref2.jpg\"],\"video_urls\":[\"https://example.com/reference.mp4\"],\"audio_urls\":[\"https://example.com/bgm.mp3\"],\"duration\":10,\"quality\":\"720p\",\"aspect_ratio\":\"16:9\",\"generate_audio\":true,\"content_filter\":true}},\"seedance-2.0-fast-text-to-video\":{\"model\":\"seedance-2.0-fast-text-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Seedance 2.0 Fast Text-to-Video\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/seedance2.0/seedance-2.0-fast-text-to-video\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing the desired video. Supports both Chinese and English, recommended no more than 500 characters for Chinese or 1000 words for English. Maximum prompt length: 10000 tokens Note: This model is text-to-video only and does not support image_urls, video_urls, or audio_urls input\",\"required\":true},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds), defaults to 5 seconds Details: Supports any integer value between 4–15 seconds; Duration directly affects billing\",\"default\":5,\"minimum\":4,\"maximum\":15},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution, defaults to 720p Options: 480p: Lower clarity, lower cost; 720p: Standard clarity, this is the default; 1080p: Ultra HD clarity, coming soon\",\"enum\":[\"480p\",\"720p\"],\"default\":\"720p\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio, defaults to adaptive Options: 16:9 (landscape), 9:16 (portrait), 1:1 (square), 4:3, 3:4, 21:9 (ultrawide); adaptive: The model intelligently selects the best aspect ratio based on the prompt Pixel values per resolution: | Aspect Ratio | 480p | 720p | |:------:|:----:|:----:| | 16:9 | 864×496 | 1280×720 | | 4:3 | 752×560 | 1112×834 | | 1:1 | 640×640 | 960×960 | | 3:4 | 560×752 | 834×1112 | | 9:16 | 496×864 | 720×1280 | | 21:9 | 992×432 | 1470×630 |\",\"enum\":[\"16:9\",\"9:16\",\"1:1\",\"4:3\",\"3:4\",\"21:9\",\"adaptive\"],\"default\":\"adaptive\"},\"generate_audio\":{\"type\":\"boolean\",\"description\":\"Whether to generate synchronized audio, defaults to true Options: true: Video includes synchronized audio (voice, sound effects, background music) at no additional charge. It is recommended to place dialogue within double quotes to optimize audio generation; false: Output silent video\",\"default\":true},\"content_filter\":{\"type\":\"boolean\",\"description\":\"Content filter, enabled by default true Options: true: Standard content safety check, this is the default; false: Relaxes content restrictions, billed at +10% (1.1x). Illegal and prohibited content is always enforced regardless of this setting Mutually exclusive with web search: content_filter: false and model_params.web_search: true cannot be used together; sending both returns a 400 parameter error; Keep content_filter: true (the default) when web search is needed\",\"default\":true},\"model_params\":{\"type\":\"object\",\"description\":\"Model extension parameters\",\"properties\":{\"web_search\":{\"type\":\"boolean\",\"description\":\"Web search, defaults to false Details: When enabled, the model autonomously decides whether to search internet content (e.g., products, weather) based on the prompt, improving timeliness; May increase latency; Fees are only charged when searches are actually triggered; multiple searches may occur once enabled Mutually exclusive with the content filter: Keep content_filter: true when web search is enabled; using it together with content_filter: false returns a 400 parameter error\",\"default\":false}}}},\"example\":{\"prompt\":\"A macro lens focuses on a green glass frog on a leaf. The focus gradually shifts from its smooth skin to its completely transparent abdomen, where a bright red heart is beating powerfully and rhythmically.\",\"duration\":8,\"quality\":\"720p\",\"aspect_ratio\":\"16:9\",\"generate_audio\":true,\"content_filter\":true}},\"seedance-2.0-image-to-video\":{\"model\":\"seedance-2.0-image-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Seedance 2.0 Image-to-Video\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/seedance2.0/seedance-2.0-image-to-video\",\"required\":[\"prompt\",\"image_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing the desired video. Supports both Chinese and English, recommended no more than 500 characters for Chinese or 1000 words for English. Maximum prompt length: 10000 tokens Note: This model does not support video_urls or audio_urls input\",\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Image URL array, 1–2 images Image count and behavior: | Image Count | Behavior | Role | |:--------:|------|------| | 1 image | First-frame image-to-video | Automatically set as first_frame | | 2 images | First-last-frame image-to-video | 1st image → first_frame, 2nd image → last_frame | Image requirements: Supported formats: .jpeg, .png, .webp; Aspect ratio (width/height): 0.4 ~ 2.5; Width/height pixels: 300 ~ 6000 px; Max size per image: 30MB; Total request body size must not exceed 64MB; When providing first and last frames, both images can be identical. If aspect ratios differ, the first f…\",\"minItems\":1,\"maxItems\":2,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds), defaults to 5 seconds Details: Supports any integer value between 4–15 seconds; Duration directly affects billing\",\"default\":5,\"minimum\":4,\"maximum\":15},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution, defaults to 720p Options: 480p: Lower clarity, lower cost; 720p: Standard clarity, this is the default; 1080p: Ultra HD clarity; 4k: 4K Ultra HD clarity\",\"enum\":[\"480p\",\"720p\",\"1080p\",\"4k\"],\"default\":\"720p\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio, defaults to adaptive Options: 16:9 (landscape), 9:16 (portrait), 1:1 (square), 4:3, 3:4, 21:9 (ultrawide); adaptive: Automatically selects the closest aspect ratio based on the first-frame image proportions Pixel values per resolution: | Aspect Ratio | 480p | 720p | 1080p | 4K | |:------:|:----:|:----:|:-----:|:----:| | 16:9 | 864×496 | 1280×720 | 1920×1080 | 3840×2160 | | 4:3 | 752×560 | 1112×834 | 1664×1248 | 3326×2494 | | 1:1 | 640×640 | 960×960 | 1440×1440 | 2880×2880 | | 3:4 | 560×752 | 834×1112 | 1248×1664 | 2494×3326 | | 9:16 | 496×864 | 720×1280 | 1080×1920 | 2160×…\",\"enum\":[\"16:9\",\"9:16\",\"1:1\",\"4:3\",\"3:4\",\"21:9\",\"adaptive\"],\"default\":\"adaptive\"},\"generate_audio\":{\"type\":\"boolean\",\"description\":\"Whether to generate synchronized audio, defaults to true Options: true: Video includes synchronized audio at no additional charge; false: Output silent video\",\"default\":true},\"content_filter\":{\"type\":\"boolean\",\"description\":\"Content filter, enabled by default true Options: true: Standard content safety check, this is the default; false: Relaxes content restrictions, billed at +10% (1.1x). Illegal and prohibited content is always enforced regardless of this setting Mutually exclusive with web search: content_filter: false and model_params.web_search: true cannot be used together; sending both returns a 400 parameter error; Keep content_filter: true (the default) when web search is needed\",\"default\":true}},\"example\":{\"prompt\":\"The camera slowly zooms in, the scene gradually comes to life\",\"image_urls\":[\"https://example.com/first-frame.jpg\"],\"duration\":5,\"aspect_ratio\":\"adaptive\"}},\"seedance-2.0-mini-image-to-video\":{\"model\":\"seedance-2.0-mini-image-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Seedance 2.0 Mini Image-to-Video\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/seedance2.0/seedance-2.0-mini-image-to-video\",\"required\":[\"prompt\",\"image_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing the desired video. Supports both Chinese and English, recommended no more than 500 characters for Chinese or 1000 words for English. Maximum prompt length: 10000 tokens Note: This model does not support video_urls or audio_urls input\",\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Image URL array, 1–2 images Image count and behavior: | Image Count | Behavior | Role | |:--------:|------|------| | 1 image | First-frame image-to-video | Automatically set as first_frame | | 2 images | First-last-frame image-to-video | 1st image → first_frame, 2nd image → last_frame | Image requirements: Supported formats: .jpeg, .png, .webp; Aspect ratio (width/height): 0.4 ~ 2.5; Width/height pixels: 300 ~ 6000 px; Max size per image: 30MB; Total request body size must not exceed 64MB; When providing first and last frames, both images can be identical. If aspect ratios differ, the first f…\",\"minItems\":1,\"maxItems\":2,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds), defaults to 5 seconds Details: Supports any integer value between 4–15 seconds; Duration directly affects billing\",\"default\":5,\"minimum\":4,\"maximum\":15},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution, defaults to 720p Options: 480p: Lower clarity, lower cost; 720p: Standard clarity, this is the default; 1080p: Ultra HD clarity, coming soon\",\"enum\":[\"480p\",\"720p\"],\"default\":\"720p\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio, defaults to adaptive Options: 16:9 (landscape), 9:16 (portrait), 1:1 (square), 4:3, 3:4, 21:9 (ultrawide); adaptive: Automatically selects the closest aspect ratio based on the first-frame image proportions Pixel values per resolution: | Aspect Ratio | 480p | 720p | |:------:|:----:|:----:| | 16:9 | 864×496 | 1280×720 | | 4:3 | 752×560 | 1112×834 | | 1:1 | 640×640 | 960×960 | | 3:4 | 560×752 | 834×1112 | | 9:16 | 496×864 | 720×1280 | | 21:9 | 992×432 | 1470×630 |\",\"enum\":[\"16:9\",\"9:16\",\"1:1\",\"4:3\",\"3:4\",\"21:9\",\"adaptive\"],\"default\":\"adaptive\"},\"generate_audio\":{\"type\":\"boolean\",\"description\":\"Whether to generate synchronized audio, defaults to true Options: true: Video includes synchronized audio at no additional charge; false: Output silent video\",\"default\":true},\"content_filter\":{\"type\":\"boolean\",\"description\":\"Content filter, enabled by default true Options: true: Standard content safety check, this is the default; false: Relaxes content restrictions, billed at +10% (1.1x). Illegal and prohibited content is always enforced regardless of this setting Mutually exclusive with web search: content_filter: false and model_params.web_search: true cannot be used together; sending both returns a 400 parameter error; Keep content_filter: true (the default) when web search is needed\",\"default\":true}},\"example\":{\"prompt\":\"The camera slowly zooms in, the scene gradually comes to life\",\"image_urls\":[\"https://example.com/first-frame.jpg\"],\"duration\":5,\"aspect_ratio\":\"adaptive\"}},\"seedance-2.0-mini-reference-to-video\":{\"model\":\"seedance-2.0-mini-reference-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Seedance 2.0 Mini Reference-to-Video\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/seedance2.0/seedance-2.0-mini-reference-to-video\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing the desired video. Supports both Chinese and English, recommended no more than 500 characters for Chinese. Maximum prompt length: 10000 tokens Details: When referring to input materials in the prompt, prefer explicit tags such as @image1, @video1, and @audio1 instead of relying only on natural-language references such as \\\"image 1\\\", \\\"video 1\\\", or \\\"audio 1\\\"; Tag numbers follow the order of the corresponding URL array and start at 1: the first image_urls item is @image1, the first video_urls item is @video1, and the first audio_urls item is @audio1; Natural-language number…\",\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL array, 0–9 images Role description: | Media Type | Role | Typical Usage | |---------|------|----------| | Image | reference_image | Style reference, product image, first/last frame (specified via prompt) | Image requirements: Supported formats: .jpeg, .png, .webp; Aspect ratio (width/height): 0.4 ~ 2.5; Width/height pixels: 300 ~ 6000 px; Max size per image: 30MB; Total request body size must not exceed 64MB, do not use Base64 encoding; Image URLs must be directly accessible by the server Note: You cannot provide only audio_urls; at least 1 image (image_urls) or 1 video (v…\",\"maxItems\":9,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"video_urls\":{\"type\":\"array\",\"description\":\"Reference video URL array, 0–3 videos Role description: | Media Type | Role | Typical Usage | |---------|------|----------| | Video | reference_video | Camera movement reference, motion reference, original video for editing/extension | Video requirements: Supported formats: .mp4, .mov; Resolution: 480p, 720p, 1080p; Duration per video: 2 ~ 15 seconds, max 3 videos, total duration of all videos ≤ 15 seconds; Aspect ratio (width/height): 0.4 ~ 2.5; Width/height pixels: 300 ~ 6000 px; Frame pixels (width × height): 409,600 ~ 2,086,876 (e.g., 640×640 ~ 2206×946); Max size per video: 50MB; Frame r…\",\"maxItems\":3,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"audio_urls\":{\"type\":\"array\",\"description\":\"Reference audio URL array, 0–3 clips Role description: | Media Type | Role | Typical Usage | |---------|------|----------| | Audio | reference_audio | Background music, sound effects, voice/dialogue reference | Audio requirements: Supported formats: .wav, .mp3; Duration per clip: 2 ~ 15 seconds, max 3 clips, total duration of all audio ≤ 15 seconds; Max size per clip: 15MB; Total request body size must not exceed 64MB, do not use Base64 encoding; Audio URLs must be directly accessible by the server Note: Audio cannot be provided alone; at least 1 reference video or image must be included\",\"maxItems\":3,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"duration\":{\"type\":\"integer\",\"description\":\"Output video duration (seconds), defaults to 5 seconds Details: Supports any integer value between 4–15 seconds; Duration directly affects billing\",\"default\":5,\"minimum\":4,\"maximum\":15},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution, defaults to 720p Options: 480p: Lower clarity, lower cost; 720p: Standard clarity, this is the default; 1080p: Ultra HD clarity, coming soon\",\"enum\":[\"480p\",\"720p\"],\"default\":\"720p\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio, defaults to adaptive Options: 16:9 (landscape), 9:16 (portrait), 1:1 (square), 4:3, 3:4, 21:9 (ultrawide); adaptive: Determined based on prompt intent, priority: video > image > prompt Pixel values per resolution: | Aspect Ratio | 480p | 720p | |:------:|:----:|:----:| | 16:9 | 864×496 | 1280×720 | | 4:3 | 752×560 | 1112×834 | | 1:1 | 640×640 | 960×960 | | 3:4 | 560×752 | 834×1112 | | 9:16 | 496×864 | 720×1280 | | 21:9 | 992×432 | 1470×630 |\",\"enum\":[\"16:9\",\"9:16\",\"1:1\",\"4:3\",\"3:4\",\"21:9\",\"adaptive\"],\"default\":\"adaptive\"},\"generate_audio\":{\"type\":\"boolean\",\"description\":\"Whether to generate synchronized audio, defaults to true Options: true: Video includes synchronized audio at no additional charge; false: Output silent video\",\"default\":true},\"content_filter\":{\"type\":\"boolean\",\"description\":\"Content filter, enabled by default true Options: true: Standard content safety check, this is the default; false: Relaxes content restrictions, billed at +10% (1.1x). Illegal and prohibited content is always enforced regardless of this setting Mutually exclusive with web search: content_filter: false and model_params.web_search: true cannot be used together; sending both returns a 400 parameter error; Keep content_filter: true (the default) when web search is needed\",\"default\":true}},\"example\":{\"prompt\":\"Use the first-person perspective framing of @video1 throughout, and use @audio1 as background music throughout. First-person perspective fruit tea promotional video...\",\"image_urls\":[\"https://example.com/ref1.jpg\",\"https://example.com/ref2.jpg\"],\"video_urls\":[\"https://example.com/reference.mp4\"],\"audio_urls\":[\"https://example.com/bgm.mp3\"],\"duration\":10,\"quality\":\"720p\",\"aspect_ratio\":\"16:9\",\"generate_audio\":true,\"content_filter\":true}},\"seedance-2.0-mini-text-to-video\":{\"model\":\"seedance-2.0-mini-text-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Seedance 2.0 Mini Text-to-Video\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/seedance2.0/seedance-2.0-mini-text-to-video\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing the desired video. Supports both Chinese and English, recommended no more than 500 characters for Chinese or 1000 words for English. Maximum prompt length: 10000 tokens Note: This model is text-to-video only and does not support image_urls, video_urls, or audio_urls input\",\"required\":true},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds), defaults to 5 seconds Details: Supports any integer value between 4–15 seconds; Duration directly affects billing\",\"default\":5,\"minimum\":4,\"maximum\":15},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution, defaults to 720p Options: 480p: Lower clarity, lower cost; 720p: Standard clarity, this is the default; 1080p: Ultra HD clarity, coming soon\",\"enum\":[\"480p\",\"720p\"],\"default\":\"720p\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio, defaults to adaptive Options: 16:9 (landscape), 9:16 (portrait), 1:1 (square), 4:3, 3:4, 21:9 (ultrawide); adaptive: The model intelligently selects the best aspect ratio based on the prompt Pixel values per resolution: | Aspect Ratio | 480p | 720p | |:------:|:----:|:----:| | 16:9 | 864×496 | 1280×720 | | 4:3 | 752×560 | 1112×834 | | 1:1 | 640×640 | 960×960 | | 3:4 | 560×752 | 834×1112 | | 9:16 | 496×864 | 720×1280 | | 21:9 | 992×432 | 1470×630 |\",\"enum\":[\"16:9\",\"9:16\",\"1:1\",\"4:3\",\"3:4\",\"21:9\",\"adaptive\"],\"default\":\"adaptive\"},\"generate_audio\":{\"type\":\"boolean\",\"description\":\"Whether to generate synchronized audio, defaults to true Options: true: Video includes synchronized audio (voice, sound effects, background music) at no additional charge. It is recommended to place dialogue within double quotes to optimize audio generation; false: Output silent video\",\"default\":true},\"content_filter\":{\"type\":\"boolean\",\"description\":\"Content filter, enabled by default true Options: true: Standard content safety check, this is the default; false: Relaxes content restrictions, billed at +10% (1.1x). Illegal and prohibited content is always enforced regardless of this setting Mutually exclusive with web search: content_filter: false and model_params.web_search: true cannot be used together; sending both returns a 400 parameter error; Keep content_filter: true (the default) when web search is needed\",\"default\":true}},\"example\":{\"prompt\":\"A macro lens focuses on a green glass frog on a leaf. The focus gradually shifts from its smooth skin to its completely transparent abdomen, where a bright red heart is beating powerfully and rhythmically.\",\"duration\":8,\"quality\":\"720p\",\"aspect_ratio\":\"16:9\",\"generate_audio\":true,\"content_filter\":true}},\"seedance-2.0-reference-to-video\":{\"model\":\"seedance-2.0-reference-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Seedance 2.0 Reference-to-Video\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/seedance2.0/seedance-2.0-reference-to-video\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing the desired video. Supports both Chinese and English, recommended no more than 500 characters for Chinese. Maximum prompt length: 10000 tokens Details: When referring to input materials in the prompt, prefer explicit tags such as @image1, @video1, and @audio1 instead of relying only on natural-language references such as \\\"image 1\\\", \\\"video 1\\\", or \\\"audio 1\\\"; Tag numbers follow the order of the corresponding URL array and start at 1: the first image_urls item is @image1, the first video_urls item is @video1, and the first audio_urls item is @audio1; Natural-language number…\",\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL array, 0–9 images Role description: | Media Type | Role | Typical Usage | |---------|------|----------| | Image | reference_image | Style reference, product image, first/last frame (specified via prompt) | Image requirements: Supported formats: .jpeg, .png, .webp; Aspect ratio (width/height): 0.4 ~ 2.5; Width/height pixels: 300 ~ 6000 px; Max size per image: 30MB; Total request body size must not exceed 64MB, do not use Base64 encoding; Image URLs must be directly accessible by the server Note: You cannot provide only audio_urls; at least 1 image (image_urls) or 1 video (v…\",\"maxItems\":9,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"video_urls\":{\"type\":\"array\",\"description\":\"Reference video URL array, 0–3 videos Role description: | Media Type | Role | Typical Usage | |---------|------|----------| | Video | reference_video | Camera movement reference, motion reference, original video for editing/extension | Video requirements: Supported formats: .mp4, .mov; Resolution: 480p, 720p, 1080p; Duration per video: 2 ~ 15 seconds, max 3 videos, total duration of all videos ≤ 15 seconds; Aspect ratio (width/height): 0.4 ~ 2.5; Width/height pixels: 300 ~ 6000 px; Frame pixels (width × height): 409,600 ~ 2,086,876 (e.g., 640×640 ~ 2206×946); Max size per video: 50MB; Frame r…\",\"maxItems\":3,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"audio_urls\":{\"type\":\"array\",\"description\":\"Reference audio URL array, 0–3 clips Role description: | Media Type | Role | Typical Usage | |---------|------|----------| | Audio | reference_audio | Background music, sound effects, voice/dialogue reference | Audio requirements: Supported formats: .wav, .mp3; Duration per clip: 2 ~ 15 seconds, max 3 clips, total duration of all audio ≤ 15 seconds; Max size per clip: 15MB; Total request body size must not exceed 64MB, do not use Base64 encoding; Audio URLs must be directly accessible by the server Note: Audio cannot be provided alone; at least 1 reference video or image must be included\",\"maxItems\":3,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"duration\":{\"type\":\"integer\",\"description\":\"Output video duration (seconds), defaults to 5 seconds Details: Supports any integer value between 4–15 seconds; Duration directly affects billing\",\"default\":5,\"minimum\":4,\"maximum\":15},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution, defaults to 720p Options: 480p: Lower clarity, lower cost; 720p: Standard clarity, this is the default; 1080p: Ultra HD clarity; 4k: 4K Ultra HD clarity\",\"enum\":[\"480p\",\"720p\",\"1080p\",\"4k\"],\"default\":\"720p\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio, defaults to adaptive Options: 16:9 (landscape), 9:16 (portrait), 1:1 (square), 4:3, 3:4, 21:9 (ultrawide); adaptive: Determined based on prompt intent, priority: video > image > prompt Pixel values per resolution: | Aspect Ratio | 480p | 720p | 1080p | 4K | |:------:|:----:|:----:|:-----:|:----:| | 16:9 | 864×496 | 1280×720 | 1920×1080 | 3840×2160 | | 4:3 | 752×560 | 1112×834 | 1664×1248 | 3326×2494 | | 1:1 | 640×640 | 960×960 | 1440×1440 | 2880×2880 | | 3:4 | 560×752 | 834×1112 | 1248×1664 | 2494×3326 | | 9:16 | 496×864 | 720×1280 | 1080×1920 | 2160×3840 | | 21:9 | 992×43…\",\"enum\":[\"16:9\",\"9:16\",\"1:1\",\"4:3\",\"3:4\",\"21:9\",\"adaptive\"],\"default\":\"adaptive\"},\"generate_audio\":{\"type\":\"boolean\",\"description\":\"Whether to generate synchronized audio, defaults to true Options: true: Video includes synchronized audio at no additional charge; false: Output silent video\",\"default\":true},\"content_filter\":{\"type\":\"boolean\",\"description\":\"Content filter, enabled by default true Options: true: Standard content safety check, this is the default; false: Relaxes content restrictions, billed at +10% (1.1x). Illegal and prohibited content is always enforced regardless of this setting Mutually exclusive with web search: content_filter: false and model_params.web_search: true cannot be used together; sending both returns a 400 parameter error; Keep content_filter: true (the default) when web search is needed\",\"default\":true}},\"example\":{\"prompt\":\"Use the first-person perspective framing of @video1 throughout, and use @audio1 as background music throughout. First-person perspective fruit tea promotional video...\",\"image_urls\":[\"https://example.com/ref1.jpg\",\"https://example.com/ref2.jpg\"],\"video_urls\":[\"https://example.com/reference.mp4\"],\"audio_urls\":[\"https://example.com/bgm.mp3\"],\"duration\":10,\"quality\":\"720p\",\"aspect_ratio\":\"16:9\",\"generate_audio\":true,\"content_filter\":true}},\"seedance-2.0-text-to-video\":{\"model\":\"seedance-2.0-text-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Seedance 2.0 Text-to-Video\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/seedance2.0/seedance-2.0-text-to-video\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing the desired video. Supports both Chinese and English, recommended no more than 500 characters for Chinese or 1000 words for English. Maximum prompt length: 10000 tokens Note: This model is text-to-video only and does not support image_urls, video_urls, or audio_urls input\",\"required\":true},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds), defaults to 5 seconds Details: Supports any integer value between 4–15 seconds; Duration directly affects billing\",\"default\":5,\"minimum\":4,\"maximum\":15},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution, defaults to 720p Options: 480p: Lower clarity, lower cost; 720p: Standard clarity, this is the default; 1080p: Ultra HD clarity; 4k: 4K Ultra HD clarity\",\"enum\":[\"480p\",\"720p\",\"1080p\",\"4k\"],\"default\":\"720p\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio, defaults to adaptive Options: 16:9 (landscape), 9:16 (portrait), 1:1 (square), 4:3, 3:4, 21:9 (ultrawide); adaptive: The model intelligently selects the best aspect ratio based on the prompt Pixel values per resolution: | Aspect Ratio | 480p | 720p | 1080p | 4K | |:------:|:----:|:----:|:-----:|:----:| | 16:9 | 864×496 | 1280×720 | 1920×1080 | 3840×2160 | | 4:3 | 752×560 | 1112×834 | 1664×1248 | 3326×2494 | | 1:1 | 640×640 | 960×960 | 1440×1440 | 2880×2880 | | 3:4 | 560×752 | 834×1112 | 1248×1664 | 2494×3326 | | 9:16 | 496×864 | 720×1280 | 1080×1920 | 2160×3840 | | 21:9 |…\",\"enum\":[\"16:9\",\"9:16\",\"1:1\",\"4:3\",\"3:4\",\"21:9\",\"adaptive\"],\"default\":\"adaptive\"},\"generate_audio\":{\"type\":\"boolean\",\"description\":\"Whether to generate synchronized audio, defaults to true Options: true: Video includes synchronized audio (voice, sound effects, background music) at no additional charge. It is recommended to place dialogue within double quotes to optimize audio generation; false: Output silent video\",\"default\":true},\"content_filter\":{\"type\":\"boolean\",\"description\":\"Content filter, enabled by default true Options: true: Standard content safety check, this is the default; false: Relaxes content restrictions, billed at +10% (1.1x). Illegal and prohibited content is always enforced regardless of this setting Mutually exclusive with web search: content_filter: false and model_params.web_search: true cannot be used together; sending both returns a 400 parameter error; Keep content_filter: true (the default) when web search is needed\",\"default\":true},\"model_params\":{\"type\":\"object\",\"description\":\"Model extension parameters\",\"properties\":{\"web_search\":{\"type\":\"boolean\",\"description\":\"Web search, defaults to false Details: When enabled, the model autonomously decides whether to search internet content (e.g., products, weather) based on the prompt, improving timeliness; May increase latency; Fees are only charged when searches are actually triggered; multiple searches may occur once enabled Mutually exclusive with the content filter: Keep content_filter: true when web search is enabled; using it together with content_filter: false returns a 400 parameter error\",\"default\":false}}}},\"example\":{\"prompt\":\"A macro lens focuses on a green glass frog on a leaf. The focus gradually shifts from its smooth skin to its completely transparent abdomen, where a bright red heart is beating powerfully and rhythmically.\",\"duration\":8,\"quality\":\"720p\",\"aspect_ratio\":\"16:9\",\"generate_audio\":true,\"content_filter\":true}},\"seedance-2.5-draft-to-video\":{\"model\":\"seedance-2.5-draft-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Seedance 2.5 Draft-to-Video\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/seedance2.5/seedance-2.5-draft-to-video\",\"required\":[\"source_task_id\"],\"params\":{\"source_task_id\":{\"type\":\"string\",\"description\":\"Task ID of a completed Seedance 2.5 draft Where to find it: The id field returned when creating a draft (draft: true) Requirements: 1. The task must belong to the current account 2. The task must use one of the five Seedance 2.5 generation models 3. The task must have been created with draft: true 4. The task status must be completed 5. The current time must be earlier than draft_expires_at in the task query response\",\"required\":true},\"output_format\":{\"type\":\"string\",\"description\":\"Output container format, defaults to mp4 Options: mp4: Default container format. This endpoint outputs 1080p video with 10-bit color depth and H.265/HEVC encoding. Playback requires support for 10-bit HEVC; H.264-only players may not play it; mov: H.264 + yuv444p chroma sampling + PCM audio for higher color fidelity, recommended for color grading, keying and compositing workflows. Browser inline playback may not support it; download and play with VLC / mpv / ffplay. No extra charge The draft's output format is not inherited. Specify mov here if required\",\"enum\":[\"mp4\",\"mov\"],\"default\":\"mp4\"}},\"example\":{\"source_task_id\":\"task-unified-1774857405-abc123\"}},\"seedance-2.5-image-to-video\":{\"model\":\"seedance-2.5-image-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Seedance 2.5 Image-to-Video\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/seedance2.5/seedance-2.5-image-to-video\",\"required\":[\"prompt\",\"image_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing the desired video. Supports both Chinese and English, recommended no more than 500 characters for Chinese or 1000 words for English. Maximum prompt length: 10000 tokens Note: This model does not support video_urls or audio_urls input\",\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Image URL array, 1–2 images Image count and behavior: | Image Count | Behavior | Role | |:--------:|------|------| | 1 image | First-frame image-to-video | Automatically set as first_frame | | 2 images | First-last-frame image-to-video | 1st image → first_frame, 2nd image → last_frame | Image requirements: Supported formats: .jpeg, .png, .webp; Aspect ratio (width/height): 0.4 ~ 2.5; Width/height pixels: 300 ~ 6000 px; Max size per image: 30MB; Total request body size must not exceed 64MB; When providing first and last frames, both images can be identical. If aspect ratios differ, the first f…\",\"minItems\":1,\"maxItems\":2,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds), defaults to 5 seconds Details: Supports any integer value between 4–30 seconds; -1: automatic duration, the model picks a length within 4–30 seconds and billing follows the actual output length; Duration directly affects billing\",\"default\":5},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution, defaults to 720p Options: 480p: Lower clarity, lower cost; 720p: Standard clarity, this is the default; 1080p: Ultra HD clarity Draft mode: When draft is true, only 480p is supported. If omitted, quality automatically defaults to 480p\",\"enum\":[\"480p\",\"720p\",\"1080p\"],\"default\":\"720p\"},\"draft\":{\"type\":\"boolean\",\"description\":\"Draft mode switch, defaults to false Details: true: Generate a 480p draft first, with faster turnaround and standard 480p billing; When enabled, quality must be 480p or omitted. Any other resolution returns a 400 parameter error; Must be a top-level request body field. Placing it inside model_params returns a 400 parameter error Convert to a final video: Once the draft is complete, [querying the task](/en/api-manual/task-management/get-task-detail) returns draft_expires_at; Before that time, pass the draft task ID to [Seedance 2.5 Draft-to-Video](/en/api-manual/video-series/seedance2.5/seedan…\",\"default\":false},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio, image-to-video only supports adaptive Options: adaptive: Automatically selects the closest aspect ratio based on the first-frame image proportions, the only value this model accepts; Fixed ratios such as 16:9 or 9:16 cannot be specified for this model\",\"enum\":[\"adaptive\"],\"default\":\"adaptive\"},\"generate_audio\":{\"type\":\"boolean\",\"description\":\"Whether to generate synchronized audio, defaults to true Options: true: Video includes synchronized audio at no additional charge; false: Output silent video\",\"default\":true},\"content_filter\":{\"type\":\"boolean\",\"description\":\"Content filter, enabled by default true Options: true: Standard content safety check, this is the default; false: Relaxes content restrictions, billed at +10% (1.1x). Illegal and prohibited content is always enforced regardless of this setting Mutually exclusive with web search: content_filter: false and model_params.web_search: true cannot be used together; sending both returns a 400 parameter error; Keep content_filter: true (the default) when web search is needed\",\"default\":true},\"output_format\":{\"type\":\"string\",\"description\":\"Output container format, defaults to mp4 Options: mp4: H.264 encoding with the best compatibility and standard color precision, this is the default; mov: H.264 + yuv444p chroma sampling + PCM audio for higher color fidelity, recommended for color grading, keying and compositing workflows. Browser inline playback may not support it; download and play with VLC / mpv / ffplay. No extra charge\",\"enum\":[\"mp4\",\"mov\"],\"default\":\"mp4\"}},\"example\":{\"prompt\":\"The camera slowly zooms in, the scene gradually comes to life\",\"image_urls\":[\"https://example.com/first-frame.jpg\"],\"duration\":5,\"quality\":\"720p\",\"aspect_ratio\":\"adaptive\"}},\"seedance-2.5-reference-to-video\":{\"model\":\"seedance-2.5-reference-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Seedance 2.5 Reference-to-Video\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/seedance2.5/seedance-2.5-reference-to-video\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing the desired video. Supports both Chinese and English, recommended no more than 500 characters for Chinese. Maximum prompt length: 10000 tokens Details: When referring to input materials in the prompt, prefer explicit tags such as @image1, @video1, and @audio1 instead of relying only on natural-language references such as \\\"image 1\\\", \\\"video 1\\\", or \\\"audio 1\\\"; Tag numbers follow the order of the corresponding URL array and start at 1: the first image_urls item is @image1, the first video_urls item is @video1, and the first audio_urls item is @audio1; Natural-language number…\",\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL array, optional; 1–30 images when provided Requirement: At least one of image_urls, video_urls, or audio_urls must be provided. Role description: | Media Type | Role | Typical Usage | |---------|------|----------| | Image | reference_image | Style reference, product image, first/last frame (specified via prompt) | Image requirements: Supported formats: .jpeg, .png, .webp; Aspect ratio (width/height): 0.4 ~ 2.5; Width/height pixels: 300 ~ 6000 px; Max size per image: 30MB; Total request body size must not exceed 64MB, do not use Base64 encoding; Image URLs must be directly…\",\"minItems\":1,\"maxItems\":30,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"video_urls\":{\"type\":\"array\",\"description\":\"Reference video URL array, optional; 1–10 videos when provided Requirement: At least one of image_urls, video_urls, or audio_urls must be provided. Role description: | Media Type | Role | Typical Usage | |---------|------|----------| | Video | reference_video | Camera movement reference, motion reference, original video for editing/extension | Video requirements: Supported formats: .mp4, .mov; Resolution: 480p, 720p, 1080p, 4K; Duration per video: 2 ~ 30 seconds, max 10 videos, total duration of all videos ≤ 30 seconds; Aspect ratio (width/height): 0.4 ~ 2.5; Width/height pixels: 300 ~ 6000 p…\",\"minItems\":1,\"maxItems\":10,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"audio_urls\":{\"type\":\"array\",\"description\":\"Reference audio URL array, optional; 1–10 clips when provided Requirement: At least one of image_urls, video_urls, or audio_urls must be provided. Role description: | Media Type | Role | Typical Usage | |---------|------|----------| | Audio | reference_audio | Background music, sound effects, voice/dialogue reference | Audio requirements: Supported formats: .wav, .mp3; Duration per clip: 2 ~ 30 seconds, max 10 clips, total duration of all audio ≤ 30 seconds; Max size per clip: 15MB; Total request body size must not exceed 64MB, do not use Base64 encoding; Audio URLs must be directly accessibl…\",\"minItems\":1,\"maxItems\":10,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"duration\":{\"type\":\"integer\",\"description\":\"Output video duration (seconds), defaults to 5 seconds Details: Supports any integer value between 4–30 seconds; -1: automatic duration, the model picks a length within 4–30 seconds and billing follows the actual output length; Duration directly affects billing If the prompt is classified as a video edit task, only -1 is accepted; an explicit number of seconds makes the task fail later, with no error at submission\",\"default\":5},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution, defaults to 720p Options: 480p: Lower clarity, lower cost; 720p: Standard clarity, this is the default; 1080p: Ultra HD clarity Draft mode: When draft is true, only 480p is supported. If omitted, quality automatically defaults to 480p\",\"enum\":[\"480p\",\"720p\",\"1080p\"],\"default\":\"720p\"},\"draft\":{\"type\":\"boolean\",\"description\":\"Draft mode switch, defaults to false Details: true: Generate a 480p draft first, with faster turnaround and standard 480p billing; When enabled, quality must be 480p or omitted. Any other resolution returns a 400 parameter error; Must be a top-level request body field. Placing it inside model_params returns a 400 parameter error Convert to a final video: Once the draft is complete, [querying the task](/en/api-manual/task-management/get-task-detail) returns draft_expires_at; Before that time, pass the draft task ID to [Seedance 2.5 Draft-to-Video](/en/api-manual/video-series/seedance2.5/seedan…\",\"default\":false},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio, defaults to adaptive Options: 16:9 (landscape), 9:16 (portrait), 1:1 (square), 4:3, 3:4, 21:9 (ultrawide); adaptive: Determined based on prompt intent, priority: video > image > prompt Pixel values per resolution: | Aspect Ratio | 480p | 720p | 1080p | |:------:|:----:|:----:|:----:| | 16:9 | 854×480 | 1280×720 | 1920×1080 | | 4:3 | 752×560 | 1112×834 | 1664×1248 | | 1:1 | 640×640 | 960×960 | 1440×1440 | | 3:4 | 560×752 | 834×1112 | 1248×1664 | | 9:16 | 480×854 | 720×1280 | 1080×1920 | | 21:9 | 992×432 | 1470×630 | 2206×946 | If the prompt is classified as a video edit / e…\",\"enum\":[\"16:9\",\"9:16\",\"1:1\",\"4:3\",\"3:4\",\"21:9\",\"adaptive\"],\"default\":\"adaptive\"},\"generate_audio\":{\"type\":\"boolean\",\"description\":\"Whether to generate synchronized audio, defaults to true Options: true: Video includes synchronized audio at no additional charge; false: Output silent video\",\"default\":true},\"content_filter\":{\"type\":\"boolean\",\"description\":\"Content filter, enabled by default true Options: true: Standard content safety check, this is the default; false: Relaxes content restrictions, billed at +10% (1.1x). Illegal and prohibited content is always enforced regardless of this setting Mutually exclusive with web search: content_filter: false and model_params.web_search: true cannot be used together; sending both returns a 400 parameter error; Keep content_filter: true (the default) when web search is needed\",\"default\":true},\"output_format\":{\"type\":\"string\",\"description\":\"Output container format, defaults to mp4 Options: mp4: H.264 encoding with the best compatibility and standard color precision, this is the default; mov: H.264 + yuv444p chroma sampling + PCM audio for higher color fidelity, recommended for color grading, keying and compositing workflows. Browser inline playback may not support it; download and play with VLC / mpv / ffplay. No extra charge\",\"enum\":[\"mp4\",\"mov\"],\"default\":\"mp4\"}},\"example\":{\"prompt\":\"Use the first-person perspective framing of @video1 throughout, and use @audio1 as background music throughout. First-person perspective fruit tea promotional video...\",\"image_urls\":[\"https://example.com/ref1.jpg\",\"https://example.com/ref2.jpg\"],\"video_urls\":[\"https://example.com/reference.mp4\"],\"audio_urls\":[\"https://example.com/bgm.mp3\"],\"duration\":10,\"quality\":\"720p\",\"aspect_ratio\":\"16:9\",\"generate_audio\":true,\"content_filter\":true}},\"seedance-2.5-text-to-video\":{\"model\":\"seedance-2.5-text-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Seedance 2.5 Text-to-Video\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/seedance2.5/seedance-2.5-text-to-video\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing the desired video. Supports both Chinese and English, recommended no more than 500 characters for Chinese or 1000 words for English. Maximum prompt length: 10000 tokens Note: This model is text-to-video only and does not support image_urls, video_urls, or audio_urls input\",\"required\":true},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds), defaults to 5 seconds Details: Supports any integer value between 4–30 seconds; -1: automatic duration, the model picks a length within 4–30 seconds and billing follows the actual output length; Duration directly affects billing\",\"default\":5},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution, defaults to 720p Options: 480p: Lower clarity, lower cost; 720p: Standard clarity, this is the default; 1080p: Ultra HD clarity Draft mode: When draft is true, only 480p is supported. If omitted, quality automatically defaults to 480p\",\"enum\":[\"480p\",\"720p\",\"1080p\"],\"default\":\"720p\"},\"draft\":{\"type\":\"boolean\",\"description\":\"Draft mode switch, defaults to false Details: true: Generate a 480p draft first, with faster turnaround and standard 480p billing; When enabled, quality must be 480p or omitted. Any other resolution returns a 400 parameter error; Must be a top-level request body field. Placing it inside model_params returns a 400 parameter error Convert to a final video: Once the draft is complete, [querying the task](/en/api-manual/task-management/get-task-detail) returns draft_expires_at; Before that time, pass the draft task ID to [Seedance 2.5 Draft-to-Video](/en/api-manual/video-series/seedance2.5/seedan…\",\"default\":false},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio, defaults to adaptive Options: 16:9 (landscape), 9:16 (portrait), 1:1 (square), 4:3, 3:4, 21:9 (ultrawide); adaptive: The model intelligently selects the best aspect ratio based on the prompt Pixel values per resolution: | Aspect Ratio | 480p | 720p | 1080p | |:------:|:----:|:----:|:----:| | 16:9 | 854×480 | 1280×720 | 1920×1080 | | 4:3 | 752×560 | 1112×834 | 1664×1248 | | 1:1 | 640×640 | 960×960 | 1440×1440 | | 3:4 | 560×752 | 834×1112 | 1248×1664 | | 9:16 | 480×854 | 720×1280 | 1080×1920 | | 21:9 | 992×432 | 1470×630 | 2206×946 |\",\"enum\":[\"16:9\",\"9:16\",\"1:1\",\"4:3\",\"3:4\",\"21:9\",\"adaptive\"],\"default\":\"adaptive\"},\"generate_audio\":{\"type\":\"boolean\",\"description\":\"Whether to generate synchronized audio, defaults to true Options: true: Video includes synchronized audio (voice, sound effects, background music) at no additional charge. It is recommended to place dialogue within double quotes to optimize audio generation; false: Output silent video\",\"default\":true},\"content_filter\":{\"type\":\"boolean\",\"description\":\"Content filter, enabled by default true Options: true: Standard content safety check, this is the default; false: Relaxes content restrictions, billed at +10% (1.1x). Illegal and prohibited content is always enforced regardless of this setting Mutually exclusive with web search: content_filter: false and model_params.web_search: true cannot be used together; sending both returns a 400 parameter error; Keep content_filter: true (the default) when web search is needed\",\"default\":true},\"output_format\":{\"type\":\"string\",\"description\":\"Output container format, defaults to mp4 Options: mp4: H.264 encoding with the best compatibility and standard color precision, this is the default; mov: H.264 + yuv444p chroma sampling + PCM audio for higher color fidelity, recommended for color grading, keying and compositing workflows. Browser inline playback may not support it; download and play with VLC / mpv / ffplay. No extra charge\",\"enum\":[\"mp4\",\"mov\"],\"default\":\"mp4\"},\"model_params\":{\"type\":\"object\",\"description\":\"Model extension parameters\",\"properties\":{\"web_search\":{\"type\":\"boolean\",\"description\":\"Web search, defaults to false Details: When enabled, the model autonomously decides whether to search internet content (e.g., products, weather) based on the prompt, improving timeliness; May increase latency; Fees are only charged when searches are actually triggered; multiple searches may occur once enabled Mutually exclusive with the content filter: Keep content_filter: true when web search is enabled; using it together with content_filter: false returns a 400 parameter error\",\"default\":false}}}},\"example\":{\"prompt\":\"A macro lens focuses on a green glass frog on a leaf. The focus gradually shifts from its smooth skin to its completely transparent abdomen, where a bright red heart is beating powerfully and rhythmically.\",\"duration\":8,\"quality\":\"720p\",\"aspect_ratio\":\"16:9\",\"generate_audio\":true,\"content_filter\":true}},\"seedance-2.5-video-edit\":{\"model\":\"seedance-2.5-video-edit\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Seedance 2.5 Video Edit\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/seedance2.5/seedance-2.5-video-edit\",\"required\":[\"prompt\",\"video_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing the desired edit. Supports both Chinese and English, recommended no more than 500 characters for Chinese. Maximum prompt length: 10000 tokens Details: The prompt must state the editing intent, e.g., \\\"Edit the video: remove the background music of @video1\\\"; You can use natural language to specify the purpose of each material, e.g., \\\"replace the character in @video1 with the person in @image1\\\"; The model will automatically understand the correspondence between material numbers and their intended uses\",\"required\":true},\"video_urls\":{\"type\":\"array\",\"description\":\"Input video URL array, required; 1–10 videos Requirement: At least 1 video required — the video to edit. The first video is the video being edited; additional videos serve as references. Role description: | Media Type | Role | Typical Usage | |---------|------|----------| | Video | reference_video | The video to edit (first video), camera movement or motion reference (additional videos) | Video requirements: Supported formats: .mp4, .mov; Resolution: 480p, 720p, 1080p, 4K; Duration per video: 4 ~ 30 seconds (the first video is the edit target), max 10 videos, total duration of all videos ≤ 30…\",\"minItems\":1,\"maxItems\":10,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL array, optional; 1–30 images when provided Requirement: video_urls is required for this model; images are optional supplementary references. Role description: | Media Type | Role | Typical Usage | |---------|------|----------| | Image | reference_image | Style reference, product image, replacement subject (specified via prompt) | Image requirements: Supported formats: .jpeg, .png, .webp; Aspect ratio (width/height): 0.4 ~ 2.5; Width/height pixels: 300 ~ 6000 px; Max size per image: 30MB; Total request body size must not exceed 64MB, do not use Base64 encoding; Image URLs m…\",\"minItems\":1,\"maxItems\":30,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"audio_urls\":{\"type\":\"array\",\"description\":\"Reference audio URL array, optional; 1–10 clips when provided Requirement: video_urls is required for this model; audio clips are optional supplementary references. Role description: | Media Type | Role | Typical Usage | |---------|------|----------| | Audio | reference_audio | Background music, sound effects, voice/dialogue reference | Audio requirements: Supported formats: .wav, .mp3; Duration per clip: 2 ~ 30 seconds, max 10 clips, total duration of all audio ≤ 30 seconds; Max size per clip: 15MB; Total request body size must not exceed 64MB, do not use Base64 encoding; Audio URLs must be…\",\"minItems\":1,\"maxItems\":10,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"duration\":{\"type\":\"integer\",\"description\":\"Output video duration (seconds), defaults to -1 Details: Only -1 is supported: the output length follows the input video (may be up to 0.4s shorter); Custom durations are rejected; Duration directly affects billing\",\"enum\":[-1],\"default\":-1},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution, defaults to 720p Options: 480p: Lower clarity, lower cost; 720p: Standard clarity, this is the default; 1080p: Ultra HD clarity Draft mode: When draft is true, only 480p is supported. If omitted, quality automatically defaults to 480p\",\"enum\":[\"480p\",\"720p\",\"1080p\"],\"default\":\"720p\"},\"draft\":{\"type\":\"boolean\",\"description\":\"Draft mode switch, defaults to false Details: true: Generate a 480p draft first, with faster turnaround and standard 480p billing; When enabled, quality must be 480p or omitted. Any other resolution returns a 400 parameter error; Must be a top-level request body field. Placing it inside model_params returns a 400 parameter error Convert to a final video: Once the draft is complete, [querying the task](/en/api-manual/task-management/get-task-detail) returns draft_expires_at; Before that time, pass the draft task ID to [Seedance 2.5 Draft-to-Video](/en/api-manual/video-series/seedance2.5/seedan…\",\"default\":false},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio, defaults to adaptive Options: adaptive: the output ratio follows the first input video, the only value this model accepts; Fixed ratios such as 16:9 or 9:16 are rejected\",\"enum\":[\"adaptive\"],\"default\":\"adaptive\"},\"generate_audio\":{\"type\":\"boolean\",\"description\":\"Whether to generate synchronized audio, defaults to true Options: true: Video includes synchronized audio at no additional charge; false: Output silent video\",\"default\":true},\"content_filter\":{\"type\":\"boolean\",\"description\":\"Content filter, enabled by default true Options: true: Standard content safety check, this is the default; false: Relaxes content restrictions, billed at +10% (1.1x). Illegal and prohibited content is always enforced regardless of this setting Mutually exclusive with web search: content_filter: false and model_params.web_search: true cannot be used together; sending both returns a 400 parameter error; Keep content_filter: true (the default) when web search is needed\",\"default\":true},\"output_format\":{\"type\":\"string\",\"description\":\"Output container format, defaults to mp4 Options: mp4: H.264 encoding with the best compatibility and standard color precision, this is the default; mov: H.264 + yuv444p chroma sampling + PCM audio for higher color fidelity, recommended for color grading, keying and compositing workflows. Browser inline playback may not support it; download and play with VLC / mpv / ffplay. No extra charge\",\"enum\":[\"mp4\",\"mov\"],\"default\":\"mp4\"}},\"example\":{\"prompt\":\"Edit the video: remove all passers-by in @video1, keep only the main character\",\"video_urls\":[\"https://example.com/original.mp4\"],\"quality\":\"720p\",\"generate_audio\":true,\"content_filter\":true}},\"seedance-2.5-video-extend\":{\"model\":\"seedance-2.5-video-extend\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Seedance 2.5 Video Extend\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/seedance2.5/seedance-2.5-video-extend\",\"required\":[\"prompt\",\"video_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing the desired extension. Supports both Chinese and English, recommended no more than 500 characters for Chinese. Maximum prompt length: 10000 tokens Details: The prompt must state the extension intent, e.g., \\\"Extend @video1 backward, the character walks out of the frame\\\"; You can use natural language to specify the purpose of each material, e.g., \\\"extend @video1 forward following the style of @image1\\\"; The model will automatically understand the correspondence between material numbers and their intended uses\",\"required\":true},\"video_urls\":{\"type\":\"array\",\"description\":\"Input video URL array, required; 1–10 videos Requirement: At least 1 video required — the video to extend. The first video is the video being extended; additional videos serve as references. Role description: | Media Type | Role | Typical Usage | |---------|------|----------| | Video | reference_video | The video to extend (first video), camera movement or motion reference (additional videos) | Video requirements: Supported formats: .mp4, .mov; Resolution: 480p, 720p, 1080p, 4K; Duration per video: 2 ~ 30 seconds, max 10 videos, total duration of all videos ≤ 30 seconds; Aspect ratio (width/h…\",\"minItems\":1,\"maxItems\":10,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL array, optional; 1–30 images when provided Requirement: video_urls is required for this model; images are optional supplementary references. Role description: | Media Type | Role | Typical Usage | |---------|------|----------| | Image | reference_image | Style reference, product image, scene reference (specified via prompt) | Image requirements: Supported formats: .jpeg, .png, .webp; Aspect ratio (width/height): 0.4 ~ 2.5; Width/height pixels: 300 ~ 6000 px; Max size per image: 30MB; Total request body size must not exceed 64MB, do not use Base64 encoding; Image URLs must…\",\"minItems\":1,\"maxItems\":30,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"audio_urls\":{\"type\":\"array\",\"description\":\"Reference audio URL array, optional; 1–10 clips when provided Requirement: video_urls is required for this model; audio clips are optional supplementary references. Role description: | Media Type | Role | Typical Usage | |---------|------|----------| | Audio | reference_audio | Background music, sound effects, voice/dialogue reference | Audio requirements: Supported formats: .wav, .mp3; Duration per clip: 2 ~ 30 seconds, max 10 clips, total duration of all audio ≤ 30 seconds; Max size per clip: 15MB; Total request body size must not exceed 64MB, do not use Base64 encoding; Audio URLs must be…\",\"minItems\":1,\"maxItems\":10,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"duration\":{\"type\":\"integer\",\"description\":\"Output video duration (seconds), defaults to 5 seconds Details: Supports any integer value between 4–30 seconds; -1: automatic duration, settled by actual output length; Duration directly affects billing\",\"default\":5},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution, defaults to 720p Options: 480p: Lower clarity, lower cost; 720p: Standard clarity, this is the default; 1080p: Ultra HD clarity Draft mode: When draft is true, only 480p is supported. If omitted, quality automatically defaults to 480p\",\"enum\":[\"480p\",\"720p\",\"1080p\"],\"default\":\"720p\"},\"draft\":{\"type\":\"boolean\",\"description\":\"Draft mode switch, defaults to false Details: true: Generate a 480p draft first, with faster turnaround and standard 480p billing; When enabled, quality must be 480p or omitted. Any other resolution returns a 400 parameter error; Must be a top-level request body field. Placing it inside model_params returns a 400 parameter error Convert to a final video: Once the draft is complete, [querying the task](/en/api-manual/task-management/get-task-detail) returns draft_expires_at; Before that time, pass the draft task ID to [Seedance 2.5 Draft-to-Video](/en/api-manual/video-series/seedance2.5/seedan…\",\"default\":false},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio, defaults to adaptive Options: adaptive: the output ratio follows the first input video, the only value this model accepts; Fixed ratios such as 16:9 or 9:16 are rejected\",\"enum\":[\"adaptive\"],\"default\":\"adaptive\"},\"generate_audio\":{\"type\":\"boolean\",\"description\":\"Whether to generate synchronized audio, defaults to true Options: true: Video includes synchronized audio at no additional charge; false: Output silent video\",\"default\":true},\"content_filter\":{\"type\":\"boolean\",\"description\":\"Content filter, enabled by default true Options: true: Standard content safety check, this is the default; false: Relaxes content restrictions, billed at +10% (1.1x). Illegal and prohibited content is always enforced regardless of this setting Mutually exclusive with web search: content_filter: false and model_params.web_search: true cannot be used together; sending both returns a 400 parameter error; Keep content_filter: true (the default) when web search is needed\",\"default\":true},\"output_format\":{\"type\":\"string\",\"description\":\"Output container format, defaults to mp4 Options: mp4: H.264 encoding with the best compatibility and standard color precision, this is the default; mov: H.264 + yuv444p chroma sampling + PCM audio for higher color fidelity, recommended for color grading, keying and compositing workflows. Browser inline playback may not support it; download and play with VLC / mpv / ffplay. No extra charge\",\"enum\":[\"mp4\",\"mov\"],\"default\":\"mp4\"}},\"example\":{\"prompt\":\"Extend @video1 backward: the character walks out of the frame, the camera slowly pulls back to reveal the empty street\",\"video_urls\":[\"https://example.com/original.mp4\"],\"duration\":12,\"quality\":\"720p\",\"generate_audio\":true,\"content_filter\":true}},\"sora-2-preview\":{\"model\":\"sora-2-preview\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Sora-2-Preview API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/sora2/sora-2-preview-video-generate\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the video to generate, max 5000 tokens\",\"maxLength\":5000,\"required\":true},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio. 1280x720 generates landscape video, 720x1280 generates portrait video\",\"enum\":[\"1280x720\",\"720x1280\",\"16:9\",\"9:16\"]},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds), default 4 Note: Only supports 4, 8, 12 seconds; Longer duration costs more\"},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URLs for image-to-video Note: Real person images not supported; Max 1 image per request; Max size: 10MB; Formats: .jpg, .jpeg, .png, .webp; Image pixel dimensions must exactly match the selected aspect_ratio (e.g., if aspect_ratio is 1280x720, the uploaded image must be exactly 1280x720 pixels); Image URL must be directly accessible by server, or trigger download when accessed (typically URLs ending with image extensions like .png, .jpg)\",\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"}}},\"example\":{\"prompt\":\"A cat playing piano\"}},\"sora-2-pro-preview\":{\"model\":\"sora-2-pro-preview\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"sora-2-pro-preview Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/sora2pro/sora-2-pro-preview-video-generate\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing what kind of video to generate, limited to 5000 tokens\",\"maxLength\":5000,\"required\":true},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio, 16:9 generates landscape video, 9:16 generates portrait video\",\"enum\":[\"16:9\",\"9:16\"]},\"duration\":{\"type\":\"integer\",\"description\":\"Specifies the generated video duration (seconds), supports 4, 8, 12 values, representing 4 seconds, 8 seconds, 12 seconds Note: Currently only supports 4, 8, 12 values; Billing is based on the duration value, longer duration costs more\"},\"quality\":{\"type\":\"string\",\"description\":\"Video quality Note: 720p: Standard quality, standard pricing; 1080p: High quality, pricing is 1.667x the standard price\",\"enum\":[\"720p\",\"1080p\"]},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL list for image-to-video feature Note: Images containing real human figures are not supported; Single request supports input image quantity: 1 image; Image size: no more than 10MB; Supported file formats: .jpg, .jpeg, .png, .webp; Image URLs must be directly viewable by the server, or the image URL should trigger direct download when accessed (typically these URLs end with image file extensions, such as .png, .jpg)\",\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"}}},\"example\":{\"prompt\":\"A cat playing piano\"}},\"suno-persona\":{\"model\":\"suno-persona\",\"kind\":\"audio\",\"path\":\"/v1/audios/generations\",\"title\":\"Suno Persona Creation API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/audio-series/suno/suno-persona-creation\",\"required\":[\"model_params\"],\"params\":{\"model_params\":{\"type\":\"object\",\"description\":\"Persona creation parameters\",\"properties\":{\"source_task_id\":{\"type\":\"string\",\"description\":\"Task ID of a completed Suno music generation task How to obtain: The id field returned from a music generation request Requirements: 1. Task must belong to the current user 2. Task status must be completed 3. Task model must be Suno series (suno-v4 or above) 4. Cannot be a suno-persona type task\",\"required\":true},\"result_id\":{\"type\":\"string\",\"description\":\"Unique identifier of a specific song from the source task results How to obtain: Via the [Query Task Detail](/en/api-manual/task-management/get-task-detail) API, find the target song's result_id in the result_data.songs[] array Limit: Each result_id can only create one Persona; duplicate creation will return an error\",\"format\":\"uuid\",\"required\":true},\"name\":{\"type\":\"string\",\"description\":\"Persona name, used for identification and subsequent reference\",\"required\":true},\"description\":{\"type\":\"string\",\"description\":\"Musical style description of the Persona\",\"required\":true},\"vocal_start\":{\"type\":\"number\",\"description\":\"Start time point for vocal extraction (seconds) Must be provided together with vocal_end; cannot provide only one. Value must be >= 0. The extraction window (vocal_end - vocal_start) must be between 10 - 30 seconds\",\"minimum\":0},\"vocal_end\":{\"type\":\"number\",\"description\":\"End time point for vocal extraction (seconds) Must be provided together with vocal_start; value must be strictly greater than vocal_start. The extraction window (vocal_end - vocal_start) must be between 10 - 30 seconds\",\"minimum\":0},\"style\":{\"type\":\"string\",\"description\":\"Style tags to annotate the musical style of the Persona. Free text, no strict format required; empty strings are ignored\"}},\"required\":true}},\"example\":{\"model_params\":{\"source_task_id\":\"task-unified-1774169216-ocqaqde7\",\"result_id\":\"4fcc4507-a7ae-4441-ad8a-465c2f61d5bb\",\"name\":\"Electronic Pop Singer\",\"description\":\"Modern electronic style with energetic beats and synthesizer tones for dance music\"}}},\"suno-v4-beta\":{\"model\":\"suno-v4-beta\",\"kind\":\"audio\",\"path\":\"/v1/audios/generations\",\"title\":\"Suno Music Generation API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/audio-series/suno/suno-music-generation\",\"required\":[],\"params\":{\"custom_mode\":{\"type\":\"boolean\",\"description\":\"Enable custom mode Description: false: Simple mode, only provide prompt, AI auto-generates lyrics and style; true: Custom mode, allows fine control over style, title, lyrics, etc. Required parameters in custom mode: style: Required; title: Required; prompt: Required when instrumental=false (used as lyrics) Simple mode (custom_mode=false) supports only prompt: style, title, negative_tags, vocal_gender, style_weight, weirdness_constraint, audio_weight, persona_id, persona_model, duration are all unsupported in this mode. The API is not guaranteed to reject them, but they have no effect whatsoev…\",\"default\":false},\"instrumental\":{\"type\":\"boolean\",\"description\":\"Generate instrumental music (no vocals) Description: false: Generate music with vocals; true: Generate instrumental/background music without vocals Note: In non-custom mode, this parameter doesn't affect required fields; In custom mode, when set to true, prompt becomes optional\",\"default\":false},\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the desired music content Non-custom mode (custom_mode=false): Required, serves as music description, AI auto-generates lyrics and style; Max length: 3000 characters Custom mode (custom_mode=true): Required when instrumental=false, used as exact lyrics; Optional when instrumental=true; Max length: 3000 characters for V4, 5000 characters for V4.5 and later (including the V6 family) Lyrics format suggestions: Use tags like [Verse], [Chorus], [Bridge] to organize lyrics structure\"},\"style\":{\"type\":\"string\",\"description\":\"Music style specification Description: Required in custom mode (custom_mode=true); Defines the genre, mood, or artistic direction of the music; Recommended to use comma-separated tags in English Character limits: V4: Max 200 characters; V4.5 and later (including the V6 family): Max 1000 characters Common style tags: Genres: pop, rock, jazz, classical, electronic, hip-hop, r&b, country, folk; Moods: happy, sad, energetic, calm, romantic, dark, uplifting; Instruments: piano, guitar, drums, bass, violin, saxophone, synthesizer; Vocals: male vocals, female vocals, choir, harmonies; Tempo: slow, f…\"},\"title\":{\"type\":\"string\",\"description\":\"Song title Description: Required in custom mode (custom_mode=true); Will be displayed in the player interface and filename; Max length: 80 characters Unsupported in simple mode (custom_mode=false): in that mode the title is generated automatically by the AI, so sending this parameter has no effect.\",\"maxLength\":80},\"negative_tags\":{\"type\":\"string\",\"description\":\"Excluded styles, specify music styles or features to avoid Description: Max length: 200 characters (same for all models) Examples: heavy metal, screaming, sad; rap, fast tempo Supported only when custom_mode=true; sending it in simple mode has no effect.\",\"maxLength\":200},\"vocal_gender\":{\"type\":\"string\",\"description\":\"Vocal gender preference Options: m: Male voice; f: Female voice Note: Only effective when custom_mode=true; This parameter only increases the probability, cannot guarantee the specified gender will be followed; Unsupported in simple mode (custom_mode=false); sending it has no effect\",\"enum\":[\"m\",\"f\"]},\"style_weight\":{\"type\":\"number\",\"description\":\"Style weight, controls adherence to the specified style Range: 0.0 ~ 1.0, up to two decimal places and a multiple of 0.01 Description: Higher values result in closer adherence to the specified style; 0 is a valid value, means no adherence to the specified style, and is sent to the model Supported only when custom_mode=true; sending it in simple mode has no effect.\",\"minimum\":0,\"maximum\":1},\"weirdness_constraint\":{\"type\":\"number\",\"description\":\"Weirdness constraint, controls the creativity/experimental degree of the output Range: 0.0 ~ 1.0, up to two decimal places and a multiple of 0.01 Description: Higher values result in more creative and experimental output; Lower values result in more traditional and conservative output; 0 is a valid value and is sent to the model Supported only when custom_mode=true; sending it in simple mode has no effect.\",\"minimum\":0,\"maximum\":1},\"audio_weight\":{\"type\":\"number\",\"description\":\"Audio weight, controls the weight of audio features Range: 0.0 ~ 1.0, up to two decimal places and a multiple of 0.01 Description: 0 is a valid value and is sent to the model Supported only when custom_mode=true; sending it in simple mode has no effect.\",\"minimum\":0,\"maximum\":1},\"persona_id\":{\"type\":\"string\",\"description\":\"Persona ID to apply a previously created Persona style to this music generation Only available when custom_mode=true. Obtained via the [Suno Persona Creation](/en/api-manual/audio-series/suno/suno-persona-creation) API, preserves consistent vocal and style characteristics How to obtain: After the Persona creation task completes, retrieve from result_data.persona_id Unsupported in simple mode (custom_mode=false). Only supported by V5- and V6-family models (suno-v5-beta / suno-v5.5-beta / suno-v6-beta / suno-v6-mini-beta / suno-v6-wild-beta, including their compatible non--beta names); sending…\"},\"persona_model\":{\"type\":\"string\",\"description\":\"Persona application mode Options: 1. style_persona: Style-oriented, emphasizing musical style characteristics (arrangement, rhythm, timbre) 2. voice_persona: Voice-oriented, emphasizing vocal characteristics (timbre, singing style, voice) Both modes are available only with V5- and V6-family models (suno-v5-beta / suno-v5.5-beta / suno-v6-beta / suno-v6-mini-beta / suno-v6-wild-beta, including their compatible non--beta names) and require custom_mode=true. It must be used together with persona_id: sending persona_model on its own without persona_id has no effect (persona_id may be used on its…\",\"enum\":[\"style_persona\",\"voice_persona\"]},\"duration\":{\"type\":\"integer\",\"description\":\"Desired audio duration in seconds Available only when custom_mode=true and the model is suno-v5.5-beta, suno-v6-beta, suno-v6-mini-beta or suno-v6-wild-beta (or the corresponding compatible name without -beta). The value must be an integer from 10 to 360. Other models and simple mode do not support this parameter; sending it returns a parameter error. Duration control varies by model (best effort, exact duration is not guaranteed): suno-v6-wild-beta, suno-v5.5-beta: Generally follow the requested duration; suno-v6-beta: Set at least 60 seconds; requests below 60 seconds typically still produc…\",\"minimum\":10,\"maximum\":360}},\"example\":{\"prompt\":\"A cheerful summer pop song about road trips and freedom\"}},\"suno-v4.5-beta\":{\"model\":\"suno-v4.5-beta\",\"kind\":\"audio\",\"path\":\"/v1/audios/generations\",\"title\":\"Suno Music Generation API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/audio-series/suno/suno-music-generation\",\"required\":[],\"params\":{\"custom_mode\":{\"type\":\"boolean\",\"description\":\"Enable custom mode Description: false: Simple mode, only provide prompt, AI auto-generates lyrics and style; true: Custom mode, allows fine control over style, title, lyrics, etc. Required parameters in custom mode: style: Required; title: Required; prompt: Required when instrumental=false (used as lyrics) Simple mode (custom_mode=false) supports only prompt: style, title, negative_tags, vocal_gender, style_weight, weirdness_constraint, audio_weight, persona_id, persona_model, duration are all unsupported in this mode. The API is not guaranteed to reject them, but they have no effect whatsoev…\",\"default\":false},\"instrumental\":{\"type\":\"boolean\",\"description\":\"Generate instrumental music (no vocals) Description: false: Generate music with vocals; true: Generate instrumental/background music without vocals Note: In non-custom mode, this parameter doesn't affect required fields; In custom mode, when set to true, prompt becomes optional\",\"default\":false},\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the desired music content Non-custom mode (custom_mode=false): Required, serves as music description, AI auto-generates lyrics and style; Max length: 3000 characters Custom mode (custom_mode=true): Required when instrumental=false, used as exact lyrics; Optional when instrumental=true; Max length: 3000 characters for V4, 5000 characters for V4.5 and later (including the V6 family) Lyrics format suggestions: Use tags like [Verse], [Chorus], [Bridge] to organize lyrics structure\"},\"style\":{\"type\":\"string\",\"description\":\"Music style specification Description: Required in custom mode (custom_mode=true); Defines the genre, mood, or artistic direction of the music; Recommended to use comma-separated tags in English Character limits: V4: Max 200 characters; V4.5 and later (including the V6 family): Max 1000 characters Common style tags: Genres: pop, rock, jazz, classical, electronic, hip-hop, r&b, country, folk; Moods: happy, sad, energetic, calm, romantic, dark, uplifting; Instruments: piano, guitar, drums, bass, violin, saxophone, synthesizer; Vocals: male vocals, female vocals, choir, harmonies; Tempo: slow, f…\"},\"title\":{\"type\":\"string\",\"description\":\"Song title Description: Required in custom mode (custom_mode=true); Will be displayed in the player interface and filename; Max length: 80 characters Unsupported in simple mode (custom_mode=false): in that mode the title is generated automatically by the AI, so sending this parameter has no effect.\",\"maxLength\":80},\"negative_tags\":{\"type\":\"string\",\"description\":\"Excluded styles, specify music styles or features to avoid Description: Max length: 200 characters (same for all models) Examples: heavy metal, screaming, sad; rap, fast tempo Supported only when custom_mode=true; sending it in simple mode has no effect.\",\"maxLength\":200},\"vocal_gender\":{\"type\":\"string\",\"description\":\"Vocal gender preference Options: m: Male voice; f: Female voice Note: Only effective when custom_mode=true; This parameter only increases the probability, cannot guarantee the specified gender will be followed; Unsupported in simple mode (custom_mode=false); sending it has no effect\",\"enum\":[\"m\",\"f\"]},\"style_weight\":{\"type\":\"number\",\"description\":\"Style weight, controls adherence to the specified style Range: 0.0 ~ 1.0, up to two decimal places and a multiple of 0.01 Description: Higher values result in closer adherence to the specified style; 0 is a valid value, means no adherence to the specified style, and is sent to the model Supported only when custom_mode=true; sending it in simple mode has no effect.\",\"minimum\":0,\"maximum\":1},\"weirdness_constraint\":{\"type\":\"number\",\"description\":\"Weirdness constraint, controls the creativity/experimental degree of the output Range: 0.0 ~ 1.0, up to two decimal places and a multiple of 0.01 Description: Higher values result in more creative and experimental output; Lower values result in more traditional and conservative output; 0 is a valid value and is sent to the model Supported only when custom_mode=true; sending it in simple mode has no effect.\",\"minimum\":0,\"maximum\":1},\"audio_weight\":{\"type\":\"number\",\"description\":\"Audio weight, controls the weight of audio features Range: 0.0 ~ 1.0, up to two decimal places and a multiple of 0.01 Description: 0 is a valid value and is sent to the model Supported only when custom_mode=true; sending it in simple mode has no effect.\",\"minimum\":0,\"maximum\":1},\"persona_id\":{\"type\":\"string\",\"description\":\"Persona ID to apply a previously created Persona style to this music generation Only available when custom_mode=true. Obtained via the [Suno Persona Creation](/en/api-manual/audio-series/suno/suno-persona-creation) API, preserves consistent vocal and style characteristics How to obtain: After the Persona creation task completes, retrieve from result_data.persona_id Unsupported in simple mode (custom_mode=false). Only supported by V5- and V6-family models (suno-v5-beta / suno-v5.5-beta / suno-v6-beta / suno-v6-mini-beta / suno-v6-wild-beta, including their compatible non--beta names); sending…\"},\"persona_model\":{\"type\":\"string\",\"description\":\"Persona application mode Options: 1. style_persona: Style-oriented, emphasizing musical style characteristics (arrangement, rhythm, timbre) 2. voice_persona: Voice-oriented, emphasizing vocal characteristics (timbre, singing style, voice) Both modes are available only with V5- and V6-family models (suno-v5-beta / suno-v5.5-beta / suno-v6-beta / suno-v6-mini-beta / suno-v6-wild-beta, including their compatible non--beta names) and require custom_mode=true. It must be used together with persona_id: sending persona_model on its own without persona_id has no effect (persona_id may be used on its…\",\"enum\":[\"style_persona\",\"voice_persona\"]},\"duration\":{\"type\":\"integer\",\"description\":\"Desired audio duration in seconds Available only when custom_mode=true and the model is suno-v5.5-beta, suno-v6-beta, suno-v6-mini-beta or suno-v6-wild-beta (or the corresponding compatible name without -beta). The value must be an integer from 10 to 360. Other models and simple mode do not support this parameter; sending it returns a parameter error. Duration control varies by model (best effort, exact duration is not guaranteed): suno-v6-wild-beta, suno-v5.5-beta: Generally follow the requested duration; suno-v6-beta: Set at least 60 seconds; requests below 60 seconds typically still produc…\",\"minimum\":10,\"maximum\":360}},\"example\":{\"prompt\":\"A cheerful summer pop song about road trips and freedom\"}},\"suno-v4.5all-beta\":{\"model\":\"suno-v4.5all-beta\",\"kind\":\"audio\",\"path\":\"/v1/audios/generations\",\"title\":\"Suno Music Generation API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/audio-series/suno/suno-music-generation\",\"required\":[],\"params\":{\"custom_mode\":{\"type\":\"boolean\",\"description\":\"Enable custom mode Description: false: Simple mode, only provide prompt, AI auto-generates lyrics and style; true: Custom mode, allows fine control over style, title, lyrics, etc. Required parameters in custom mode: style: Required; title: Required; prompt: Required when instrumental=false (used as lyrics) Simple mode (custom_mode=false) supports only prompt: style, title, negative_tags, vocal_gender, style_weight, weirdness_constraint, audio_weight, persona_id, persona_model, duration are all unsupported in this mode. The API is not guaranteed to reject them, but they have no effect whatsoev…\",\"default\":false},\"instrumental\":{\"type\":\"boolean\",\"description\":\"Generate instrumental music (no vocals) Description: false: Generate music with vocals; true: Generate instrumental/background music without vocals Note: In non-custom mode, this parameter doesn't affect required fields; In custom mode, when set to true, prompt becomes optional\",\"default\":false},\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the desired music content Non-custom mode (custom_mode=false): Required, serves as music description, AI auto-generates lyrics and style; Max length: 3000 characters Custom mode (custom_mode=true): Required when instrumental=false, used as exact lyrics; Optional when instrumental=true; Max length: 3000 characters for V4, 5000 characters for V4.5 and later (including the V6 family) Lyrics format suggestions: Use tags like [Verse], [Chorus], [Bridge] to organize lyrics structure\"},\"style\":{\"type\":\"string\",\"description\":\"Music style specification Description: Required in custom mode (custom_mode=true); Defines the genre, mood, or artistic direction of the music; Recommended to use comma-separated tags in English Character limits: V4: Max 200 characters; V4.5 and later (including the V6 family): Max 1000 characters Common style tags: Genres: pop, rock, jazz, classical, electronic, hip-hop, r&b, country, folk; Moods: happy, sad, energetic, calm, romantic, dark, uplifting; Instruments: piano, guitar, drums, bass, violin, saxophone, synthesizer; Vocals: male vocals, female vocals, choir, harmonies; Tempo: slow, f…\"},\"title\":{\"type\":\"string\",\"description\":\"Song title Description: Required in custom mode (custom_mode=true); Will be displayed in the player interface and filename; Max length: 80 characters Unsupported in simple mode (custom_mode=false): in that mode the title is generated automatically by the AI, so sending this parameter has no effect.\",\"maxLength\":80},\"negative_tags\":{\"type\":\"string\",\"description\":\"Excluded styles, specify music styles or features to avoid Description: Max length: 200 characters (same for all models) Examples: heavy metal, screaming, sad; rap, fast tempo Supported only when custom_mode=true; sending it in simple mode has no effect.\",\"maxLength\":200},\"vocal_gender\":{\"type\":\"string\",\"description\":\"Vocal gender preference Options: m: Male voice; f: Female voice Note: Only effective when custom_mode=true; This parameter only increases the probability, cannot guarantee the specified gender will be followed; Unsupported in simple mode (custom_mode=false); sending it has no effect\",\"enum\":[\"m\",\"f\"]},\"style_weight\":{\"type\":\"number\",\"description\":\"Style weight, controls adherence to the specified style Range: 0.0 ~ 1.0, up to two decimal places and a multiple of 0.01 Description: Higher values result in closer adherence to the specified style; 0 is a valid value, means no adherence to the specified style, and is sent to the model Supported only when custom_mode=true; sending it in simple mode has no effect.\",\"minimum\":0,\"maximum\":1},\"weirdness_constraint\":{\"type\":\"number\",\"description\":\"Weirdness constraint, controls the creativity/experimental degree of the output Range: 0.0 ~ 1.0, up to two decimal places and a multiple of 0.01 Description: Higher values result in more creative and experimental output; Lower values result in more traditional and conservative output; 0 is a valid value and is sent to the model Supported only when custom_mode=true; sending it in simple mode has no effect.\",\"minimum\":0,\"maximum\":1},\"audio_weight\":{\"type\":\"number\",\"description\":\"Audio weight, controls the weight of audio features Range: 0.0 ~ 1.0, up to two decimal places and a multiple of 0.01 Description: 0 is a valid value and is sent to the model Supported only when custom_mode=true; sending it in simple mode has no effect.\",\"minimum\":0,\"maximum\":1},\"persona_id\":{\"type\":\"string\",\"description\":\"Persona ID to apply a previously created Persona style to this music generation Only available when custom_mode=true. Obtained via the [Suno Persona Creation](/en/api-manual/audio-series/suno/suno-persona-creation) API, preserves consistent vocal and style characteristics How to obtain: After the Persona creation task completes, retrieve from result_data.persona_id Unsupported in simple mode (custom_mode=false). Only supported by V5- and V6-family models (suno-v5-beta / suno-v5.5-beta / suno-v6-beta / suno-v6-mini-beta / suno-v6-wild-beta, including their compatible non--beta names); sending…\"},\"persona_model\":{\"type\":\"string\",\"description\":\"Persona application mode Options: 1. style_persona: Style-oriented, emphasizing musical style characteristics (arrangement, rhythm, timbre) 2. voice_persona: Voice-oriented, emphasizing vocal characteristics (timbre, singing style, voice) Both modes are available only with V5- and V6-family models (suno-v5-beta / suno-v5.5-beta / suno-v6-beta / suno-v6-mini-beta / suno-v6-wild-beta, including their compatible non--beta names) and require custom_mode=true. It must be used together with persona_id: sending persona_model on its own without persona_id has no effect (persona_id may be used on its…\",\"enum\":[\"style_persona\",\"voice_persona\"]},\"duration\":{\"type\":\"integer\",\"description\":\"Desired audio duration in seconds Available only when custom_mode=true and the model is suno-v5.5-beta, suno-v6-beta, suno-v6-mini-beta or suno-v6-wild-beta (or the corresponding compatible name without -beta). The value must be an integer from 10 to 360. Other models and simple mode do not support this parameter; sending it returns a parameter error. Duration control varies by model (best effort, exact duration is not guaranteed): suno-v6-wild-beta, suno-v5.5-beta: Generally follow the requested duration; suno-v6-beta: Set at least 60 seconds; requests below 60 seconds typically still produc…\",\"minimum\":10,\"maximum\":360}},\"example\":{\"prompt\":\"A cheerful summer pop song about road trips and freedom\"}},\"suno-v4.5plus-beta\":{\"model\":\"suno-v4.5plus-beta\",\"kind\":\"audio\",\"path\":\"/v1/audios/generations\",\"title\":\"Suno Music Generation API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/audio-series/suno/suno-music-generation\",\"required\":[],\"params\":{\"custom_mode\":{\"type\":\"boolean\",\"description\":\"Enable custom mode Description: false: Simple mode, only provide prompt, AI auto-generates lyrics and style; true: Custom mode, allows fine control over style, title, lyrics, etc. Required parameters in custom mode: style: Required; title: Required; prompt: Required when instrumental=false (used as lyrics) Simple mode (custom_mode=false) supports only prompt: style, title, negative_tags, vocal_gender, style_weight, weirdness_constraint, audio_weight, persona_id, persona_model, duration are all unsupported in this mode. The API is not guaranteed to reject them, but they have no effect whatsoev…\",\"default\":false},\"instrumental\":{\"type\":\"boolean\",\"description\":\"Generate instrumental music (no vocals) Description: false: Generate music with vocals; true: Generate instrumental/background music without vocals Note: In non-custom mode, this parameter doesn't affect required fields; In custom mode, when set to true, prompt becomes optional\",\"default\":false},\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the desired music content Non-custom mode (custom_mode=false): Required, serves as music description, AI auto-generates lyrics and style; Max length: 3000 characters Custom mode (custom_mode=true): Required when instrumental=false, used as exact lyrics; Optional when instrumental=true; Max length: 3000 characters for V4, 5000 characters for V4.5 and later (including the V6 family) Lyrics format suggestions: Use tags like [Verse], [Chorus], [Bridge] to organize lyrics structure\"},\"style\":{\"type\":\"string\",\"description\":\"Music style specification Description: Required in custom mode (custom_mode=true); Defines the genre, mood, or artistic direction of the music; Recommended to use comma-separated tags in English Character limits: V4: Max 200 characters; V4.5 and later (including the V6 family): Max 1000 characters Common style tags: Genres: pop, rock, jazz, classical, electronic, hip-hop, r&b, country, folk; Moods: happy, sad, energetic, calm, romantic, dark, uplifting; Instruments: piano, guitar, drums, bass, violin, saxophone, synthesizer; Vocals: male vocals, female vocals, choir, harmonies; Tempo: slow, f…\"},\"title\":{\"type\":\"string\",\"description\":\"Song title Description: Required in custom mode (custom_mode=true); Will be displayed in the player interface and filename; Max length: 80 characters Unsupported in simple mode (custom_mode=false): in that mode the title is generated automatically by the AI, so sending this parameter has no effect.\",\"maxLength\":80},\"negative_tags\":{\"type\":\"string\",\"description\":\"Excluded styles, specify music styles or features to avoid Description: Max length: 200 characters (same for all models) Examples: heavy metal, screaming, sad; rap, fast tempo Supported only when custom_mode=true; sending it in simple mode has no effect.\",\"maxLength\":200},\"vocal_gender\":{\"type\":\"string\",\"description\":\"Vocal gender preference Options: m: Male voice; f: Female voice Note: Only effective when custom_mode=true; This parameter only increases the probability, cannot guarantee the specified gender will be followed; Unsupported in simple mode (custom_mode=false); sending it has no effect\",\"enum\":[\"m\",\"f\"]},\"style_weight\":{\"type\":\"number\",\"description\":\"Style weight, controls adherence to the specified style Range: 0.0 ~ 1.0, up to two decimal places and a multiple of 0.01 Description: Higher values result in closer adherence to the specified style; 0 is a valid value, means no adherence to the specified style, and is sent to the model Supported only when custom_mode=true; sending it in simple mode has no effect.\",\"minimum\":0,\"maximum\":1},\"weirdness_constraint\":{\"type\":\"number\",\"description\":\"Weirdness constraint, controls the creativity/experimental degree of the output Range: 0.0 ~ 1.0, up to two decimal places and a multiple of 0.01 Description: Higher values result in more creative and experimental output; Lower values result in more traditional and conservative output; 0 is a valid value and is sent to the model Supported only when custom_mode=true; sending it in simple mode has no effect.\",\"minimum\":0,\"maximum\":1},\"audio_weight\":{\"type\":\"number\",\"description\":\"Audio weight, controls the weight of audio features Range: 0.0 ~ 1.0, up to two decimal places and a multiple of 0.01 Description: 0 is a valid value and is sent to the model Supported only when custom_mode=true; sending it in simple mode has no effect.\",\"minimum\":0,\"maximum\":1},\"persona_id\":{\"type\":\"string\",\"description\":\"Persona ID to apply a previously created Persona style to this music generation Only available when custom_mode=true. Obtained via the [Suno Persona Creation](/en/api-manual/audio-series/suno/suno-persona-creation) API, preserves consistent vocal and style characteristics How to obtain: After the Persona creation task completes, retrieve from result_data.persona_id Unsupported in simple mode (custom_mode=false). Only supported by V5- and V6-family models (suno-v5-beta / suno-v5.5-beta / suno-v6-beta / suno-v6-mini-beta / suno-v6-wild-beta, including their compatible non--beta names); sending…\"},\"persona_model\":{\"type\":\"string\",\"description\":\"Persona application mode Options: 1. style_persona: Style-oriented, emphasizing musical style characteristics (arrangement, rhythm, timbre) 2. voice_persona: Voice-oriented, emphasizing vocal characteristics (timbre, singing style, voice) Both modes are available only with V5- and V6-family models (suno-v5-beta / suno-v5.5-beta / suno-v6-beta / suno-v6-mini-beta / suno-v6-wild-beta, including their compatible non--beta names) and require custom_mode=true. It must be used together with persona_id: sending persona_model on its own without persona_id has no effect (persona_id may be used on its…\",\"enum\":[\"style_persona\",\"voice_persona\"]},\"duration\":{\"type\":\"integer\",\"description\":\"Desired audio duration in seconds Available only when custom_mode=true and the model is suno-v5.5-beta, suno-v6-beta, suno-v6-mini-beta or suno-v6-wild-beta (or the corresponding compatible name without -beta). The value must be an integer from 10 to 360. Other models and simple mode do not support this parameter; sending it returns a parameter error. Duration control varies by model (best effort, exact duration is not guaranteed): suno-v6-wild-beta, suno-v5.5-beta: Generally follow the requested duration; suno-v6-beta: Set at least 60 seconds; requests below 60 seconds typically still produc…\",\"minimum\":10,\"maximum\":360}},\"example\":{\"prompt\":\"A cheerful summer pop song about road trips and freedom\"}},\"suno-v5-beta\":{\"model\":\"suno-v5-beta\",\"kind\":\"audio\",\"path\":\"/v1/audios/generations\",\"title\":\"Suno Music Generation API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/audio-series/suno/suno-music-generation\",\"required\":[],\"params\":{\"custom_mode\":{\"type\":\"boolean\",\"description\":\"Enable custom mode Description: false: Simple mode, only provide prompt, AI auto-generates lyrics and style; true: Custom mode, allows fine control over style, title, lyrics, etc. Required parameters in custom mode: style: Required; title: Required; prompt: Required when instrumental=false (used as lyrics) Simple mode (custom_mode=false) supports only prompt: style, title, negative_tags, vocal_gender, style_weight, weirdness_constraint, audio_weight, persona_id, persona_model, duration are all unsupported in this mode. The API is not guaranteed to reject them, but they have no effect whatsoev…\",\"default\":false},\"instrumental\":{\"type\":\"boolean\",\"description\":\"Generate instrumental music (no vocals) Description: false: Generate music with vocals; true: Generate instrumental/background music without vocals Note: In non-custom mode, this parameter doesn't affect required fields; In custom mode, when set to true, prompt becomes optional\",\"default\":false},\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the desired music content Non-custom mode (custom_mode=false): Required, serves as music description, AI auto-generates lyrics and style; Max length: 3000 characters Custom mode (custom_mode=true): Required when instrumental=false, used as exact lyrics; Optional when instrumental=true; Max length: 3000 characters for V4, 5000 characters for V4.5 and later (including the V6 family) Lyrics format suggestions: Use tags like [Verse], [Chorus], [Bridge] to organize lyrics structure\"},\"style\":{\"type\":\"string\",\"description\":\"Music style specification Description: Required in custom mode (custom_mode=true); Defines the genre, mood, or artistic direction of the music; Recommended to use comma-separated tags in English Character limits: V4: Max 200 characters; V4.5 and later (including the V6 family): Max 1000 characters Common style tags: Genres: pop, rock, jazz, classical, electronic, hip-hop, r&b, country, folk; Moods: happy, sad, energetic, calm, romantic, dark, uplifting; Instruments: piano, guitar, drums, bass, violin, saxophone, synthesizer; Vocals: male vocals, female vocals, choir, harmonies; Tempo: slow, f…\"},\"title\":{\"type\":\"string\",\"description\":\"Song title Description: Required in custom mode (custom_mode=true); Will be displayed in the player interface and filename; Max length: 80 characters Unsupported in simple mode (custom_mode=false): in that mode the title is generated automatically by the AI, so sending this parameter has no effect.\",\"maxLength\":80},\"negative_tags\":{\"type\":\"string\",\"description\":\"Excluded styles, specify music styles or features to avoid Description: Max length: 200 characters (same for all models) Examples: heavy metal, screaming, sad; rap, fast tempo Supported only when custom_mode=true; sending it in simple mode has no effect.\",\"maxLength\":200},\"vocal_gender\":{\"type\":\"string\",\"description\":\"Vocal gender preference Options: m: Male voice; f: Female voice Note: Only effective when custom_mode=true; This parameter only increases the probability, cannot guarantee the specified gender will be followed; Unsupported in simple mode (custom_mode=false); sending it has no effect\",\"enum\":[\"m\",\"f\"]},\"style_weight\":{\"type\":\"number\",\"description\":\"Style weight, controls adherence to the specified style Range: 0.0 ~ 1.0, up to two decimal places and a multiple of 0.01 Description: Higher values result in closer adherence to the specified style; 0 is a valid value, means no adherence to the specified style, and is sent to the model Supported only when custom_mode=true; sending it in simple mode has no effect.\",\"minimum\":0,\"maximum\":1},\"weirdness_constraint\":{\"type\":\"number\",\"description\":\"Weirdness constraint, controls the creativity/experimental degree of the output Range: 0.0 ~ 1.0, up to two decimal places and a multiple of 0.01 Description: Higher values result in more creative and experimental output; Lower values result in more traditional and conservative output; 0 is a valid value and is sent to the model Supported only when custom_mode=true; sending it in simple mode has no effect.\",\"minimum\":0,\"maximum\":1},\"audio_weight\":{\"type\":\"number\",\"description\":\"Audio weight, controls the weight of audio features Range: 0.0 ~ 1.0, up to two decimal places and a multiple of 0.01 Description: 0 is a valid value and is sent to the model Supported only when custom_mode=true; sending it in simple mode has no effect.\",\"minimum\":0,\"maximum\":1},\"persona_id\":{\"type\":\"string\",\"description\":\"Persona ID to apply a previously created Persona style to this music generation Only available when custom_mode=true. Obtained via the [Suno Persona Creation](/en/api-manual/audio-series/suno/suno-persona-creation) API, preserves consistent vocal and style characteristics How to obtain: After the Persona creation task completes, retrieve from result_data.persona_id Unsupported in simple mode (custom_mode=false). Only supported by V5- and V6-family models (suno-v5-beta / suno-v5.5-beta / suno-v6-beta / suno-v6-mini-beta / suno-v6-wild-beta, including their compatible non--beta names); sending…\"},\"persona_model\":{\"type\":\"string\",\"description\":\"Persona application mode Options: 1. style_persona: Style-oriented, emphasizing musical style characteristics (arrangement, rhythm, timbre) 2. voice_persona: Voice-oriented, emphasizing vocal characteristics (timbre, singing style, voice) Both modes are available only with V5- and V6-family models (suno-v5-beta / suno-v5.5-beta / suno-v6-beta / suno-v6-mini-beta / suno-v6-wild-beta, including their compatible non--beta names) and require custom_mode=true. It must be used together with persona_id: sending persona_model on its own without persona_id has no effect (persona_id may be used on its…\",\"enum\":[\"style_persona\",\"voice_persona\"]},\"duration\":{\"type\":\"integer\",\"description\":\"Desired audio duration in seconds Available only when custom_mode=true and the model is suno-v5.5-beta, suno-v6-beta, suno-v6-mini-beta or suno-v6-wild-beta (or the corresponding compatible name without -beta). The value must be an integer from 10 to 360. Other models and simple mode do not support this parameter; sending it returns a parameter error. Duration control varies by model (best effort, exact duration is not guaranteed): suno-v6-wild-beta, suno-v5.5-beta: Generally follow the requested duration; suno-v6-beta: Set at least 60 seconds; requests below 60 seconds typically still produc…\",\"minimum\":10,\"maximum\":360}},\"example\":{\"prompt\":\"A cheerful summer pop song about road trips and freedom\"}},\"suno-v5.5-beta\":{\"model\":\"suno-v5.5-beta\",\"kind\":\"audio\",\"path\":\"/v1/audios/generations\",\"title\":\"Suno Music Generation API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/audio-series/suno/suno-music-generation\",\"required\":[],\"params\":{\"custom_mode\":{\"type\":\"boolean\",\"description\":\"Enable custom mode Description: false: Simple mode, only provide prompt, AI auto-generates lyrics and style; true: Custom mode, allows fine control over style, title, lyrics, etc. Required parameters in custom mode: style: Required; title: Required; prompt: Required when instrumental=false (used as lyrics) Simple mode (custom_mode=false) supports only prompt: style, title, negative_tags, vocal_gender, style_weight, weirdness_constraint, audio_weight, persona_id, persona_model, duration are all unsupported in this mode. The API is not guaranteed to reject them, but they have no effect whatsoev…\",\"default\":false},\"instrumental\":{\"type\":\"boolean\",\"description\":\"Generate instrumental music (no vocals) Description: false: Generate music with vocals; true: Generate instrumental/background music without vocals Note: In non-custom mode, this parameter doesn't affect required fields; In custom mode, when set to true, prompt becomes optional\",\"default\":false},\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the desired music content Non-custom mode (custom_mode=false): Required, serves as music description, AI auto-generates lyrics and style; Max length: 3000 characters Custom mode (custom_mode=true): Required when instrumental=false, used as exact lyrics; Optional when instrumental=true; Max length: 3000 characters for V4, 5000 characters for V4.5 and later (including the V6 family) Lyrics format suggestions: Use tags like [Verse], [Chorus], [Bridge] to organize lyrics structure\"},\"style\":{\"type\":\"string\",\"description\":\"Music style specification Description: Required in custom mode (custom_mode=true); Defines the genre, mood, or artistic direction of the music; Recommended to use comma-separated tags in English Character limits: V4: Max 200 characters; V4.5 and later (including the V6 family): Max 1000 characters Common style tags: Genres: pop, rock, jazz, classical, electronic, hip-hop, r&b, country, folk; Moods: happy, sad, energetic, calm, romantic, dark, uplifting; Instruments: piano, guitar, drums, bass, violin, saxophone, synthesizer; Vocals: male vocals, female vocals, choir, harmonies; Tempo: slow, f…\"},\"title\":{\"type\":\"string\",\"description\":\"Song title Description: Required in custom mode (custom_mode=true); Will be displayed in the player interface and filename; Max length: 80 characters Unsupported in simple mode (custom_mode=false): in that mode the title is generated automatically by the AI, so sending this parameter has no effect.\",\"maxLength\":80},\"negative_tags\":{\"type\":\"string\",\"description\":\"Excluded styles, specify music styles or features to avoid Description: Max length: 200 characters (same for all models) Examples: heavy metal, screaming, sad; rap, fast tempo Supported only when custom_mode=true; sending it in simple mode has no effect.\",\"maxLength\":200},\"vocal_gender\":{\"type\":\"string\",\"description\":\"Vocal gender preference Options: m: Male voice; f: Female voice Note: Only effective when custom_mode=true; This parameter only increases the probability, cannot guarantee the specified gender will be followed; Unsupported in simple mode (custom_mode=false); sending it has no effect\",\"enum\":[\"m\",\"f\"]},\"style_weight\":{\"type\":\"number\",\"description\":\"Style weight, controls adherence to the specified style Range: 0.0 ~ 1.0, up to two decimal places and a multiple of 0.01 Description: Higher values result in closer adherence to the specified style; 0 is a valid value, means no adherence to the specified style, and is sent to the model Supported only when custom_mode=true; sending it in simple mode has no effect.\",\"minimum\":0,\"maximum\":1},\"weirdness_constraint\":{\"type\":\"number\",\"description\":\"Weirdness constraint, controls the creativity/experimental degree of the output Range: 0.0 ~ 1.0, up to two decimal places and a multiple of 0.01 Description: Higher values result in more creative and experimental output; Lower values result in more traditional and conservative output; 0 is a valid value and is sent to the model Supported only when custom_mode=true; sending it in simple mode has no effect.\",\"minimum\":0,\"maximum\":1},\"audio_weight\":{\"type\":\"number\",\"description\":\"Audio weight, controls the weight of audio features Range: 0.0 ~ 1.0, up to two decimal places and a multiple of 0.01 Description: 0 is a valid value and is sent to the model Supported only when custom_mode=true; sending it in simple mode has no effect.\",\"minimum\":0,\"maximum\":1},\"persona_id\":{\"type\":\"string\",\"description\":\"Persona ID to apply a previously created Persona style to this music generation Only available when custom_mode=true. Obtained via the [Suno Persona Creation](/en/api-manual/audio-series/suno/suno-persona-creation) API, preserves consistent vocal and style characteristics How to obtain: After the Persona creation task completes, retrieve from result_data.persona_id Unsupported in simple mode (custom_mode=false). Only supported by V5- and V6-family models (suno-v5-beta / suno-v5.5-beta / suno-v6-beta / suno-v6-mini-beta / suno-v6-wild-beta, including their compatible non--beta names); sending…\"},\"persona_model\":{\"type\":\"string\",\"description\":\"Persona application mode Options: 1. style_persona: Style-oriented, emphasizing musical style characteristics (arrangement, rhythm, timbre) 2. voice_persona: Voice-oriented, emphasizing vocal characteristics (timbre, singing style, voice) Both modes are available only with V5- and V6-family models (suno-v5-beta / suno-v5.5-beta / suno-v6-beta / suno-v6-mini-beta / suno-v6-wild-beta, including their compatible non--beta names) and require custom_mode=true. It must be used together with persona_id: sending persona_model on its own without persona_id has no effect (persona_id may be used on its…\",\"enum\":[\"style_persona\",\"voice_persona\"]},\"duration\":{\"type\":\"integer\",\"description\":\"Desired audio duration in seconds Available only when custom_mode=true and the model is suno-v5.5-beta, suno-v6-beta, suno-v6-mini-beta or suno-v6-wild-beta (or the corresponding compatible name without -beta). The value must be an integer from 10 to 360. Other models and simple mode do not support this parameter; sending it returns a parameter error. Duration control varies by model (best effort, exact duration is not guaranteed): suno-v6-wild-beta, suno-v5.5-beta: Generally follow the requested duration; suno-v6-beta: Set at least 60 seconds; requests below 60 seconds typically still produc…\",\"minimum\":10,\"maximum\":360}},\"example\":{\"prompt\":\"A cheerful summer pop song about road trips and freedom\"}},\"suno-v6-beta\":{\"model\":\"suno-v6-beta\",\"kind\":\"audio\",\"path\":\"/v1/audios/generations\",\"title\":\"Suno Music Generation API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/audio-series/suno/suno-music-generation\",\"required\":[],\"params\":{\"custom_mode\":{\"type\":\"boolean\",\"description\":\"Enable custom mode Description: false: Simple mode, only provide prompt, AI auto-generates lyrics and style; true: Custom mode, allows fine control over style, title, lyrics, etc. Required parameters in custom mode: style: Required; title: Required; prompt: Required when instrumental=false (used as lyrics) Simple mode (custom_mode=false) supports only prompt: style, title, negative_tags, vocal_gender, style_weight, weirdness_constraint, audio_weight, persona_id, persona_model, duration are all unsupported in this mode. The API is not guaranteed to reject them, but they have no effect whatsoev…\",\"default\":false},\"instrumental\":{\"type\":\"boolean\",\"description\":\"Generate instrumental music (no vocals) Description: false: Generate music with vocals; true: Generate instrumental/background music without vocals Note: In non-custom mode, this parameter doesn't affect required fields; In custom mode, when set to true, prompt becomes optional\",\"default\":false},\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the desired music content Non-custom mode (custom_mode=false): Required, serves as music description, AI auto-generates lyrics and style; Max length: 3000 characters Custom mode (custom_mode=true): Required when instrumental=false, used as exact lyrics; Optional when instrumental=true; Max length: 3000 characters for V4, 5000 characters for V4.5 and later (including the V6 family) Lyrics format suggestions: Use tags like [Verse], [Chorus], [Bridge] to organize lyrics structure\"},\"style\":{\"type\":\"string\",\"description\":\"Music style specification Description: Required in custom mode (custom_mode=true); Defines the genre, mood, or artistic direction of the music; Recommended to use comma-separated tags in English Character limits: V4: Max 200 characters; V4.5 and later (including the V6 family): Max 1000 characters Common style tags: Genres: pop, rock, jazz, classical, electronic, hip-hop, r&b, country, folk; Moods: happy, sad, energetic, calm, romantic, dark, uplifting; Instruments: piano, guitar, drums, bass, violin, saxophone, synthesizer; Vocals: male vocals, female vocals, choir, harmonies; Tempo: slow, f…\"},\"title\":{\"type\":\"string\",\"description\":\"Song title Description: Required in custom mode (custom_mode=true); Will be displayed in the player interface and filename; Max length: 80 characters Unsupported in simple mode (custom_mode=false): in that mode the title is generated automatically by the AI, so sending this parameter has no effect.\",\"maxLength\":80},\"negative_tags\":{\"type\":\"string\",\"description\":\"Excluded styles, specify music styles or features to avoid Description: Max length: 200 characters (same for all models) Examples: heavy metal, screaming, sad; rap, fast tempo Supported only when custom_mode=true; sending it in simple mode has no effect.\",\"maxLength\":200},\"vocal_gender\":{\"type\":\"string\",\"description\":\"Vocal gender preference Options: m: Male voice; f: Female voice Note: Only effective when custom_mode=true; This parameter only increases the probability, cannot guarantee the specified gender will be followed; Unsupported in simple mode (custom_mode=false); sending it has no effect\",\"enum\":[\"m\",\"f\"]},\"style_weight\":{\"type\":\"number\",\"description\":\"Style weight, controls adherence to the specified style Range: 0.0 ~ 1.0, up to two decimal places and a multiple of 0.01 Description: Higher values result in closer adherence to the specified style; 0 is a valid value, means no adherence to the specified style, and is sent to the model Supported only when custom_mode=true; sending it in simple mode has no effect.\",\"minimum\":0,\"maximum\":1},\"weirdness_constraint\":{\"type\":\"number\",\"description\":\"Weirdness constraint, controls the creativity/experimental degree of the output Range: 0.0 ~ 1.0, up to two decimal places and a multiple of 0.01 Description: Higher values result in more creative and experimental output; Lower values result in more traditional and conservative output; 0 is a valid value and is sent to the model Supported only when custom_mode=true; sending it in simple mode has no effect.\",\"minimum\":0,\"maximum\":1},\"audio_weight\":{\"type\":\"number\",\"description\":\"Audio weight, controls the weight of audio features Range: 0.0 ~ 1.0, up to two decimal places and a multiple of 0.01 Description: 0 is a valid value and is sent to the model Supported only when custom_mode=true; sending it in simple mode has no effect.\",\"minimum\":0,\"maximum\":1},\"persona_id\":{\"type\":\"string\",\"description\":\"Persona ID to apply a previously created Persona style to this music generation Only available when custom_mode=true. Obtained via the [Suno Persona Creation](/en/api-manual/audio-series/suno/suno-persona-creation) API, preserves consistent vocal and style characteristics How to obtain: After the Persona creation task completes, retrieve from result_data.persona_id Unsupported in simple mode (custom_mode=false). Only supported by V5- and V6-family models (suno-v5-beta / suno-v5.5-beta / suno-v6-beta / suno-v6-mini-beta / suno-v6-wild-beta, including their compatible non--beta names); sending…\"},\"persona_model\":{\"type\":\"string\",\"description\":\"Persona application mode Options: 1. style_persona: Style-oriented, emphasizing musical style characteristics (arrangement, rhythm, timbre) 2. voice_persona: Voice-oriented, emphasizing vocal characteristics (timbre, singing style, voice) Both modes are available only with V5- and V6-family models (suno-v5-beta / suno-v5.5-beta / suno-v6-beta / suno-v6-mini-beta / suno-v6-wild-beta, including their compatible non--beta names) and require custom_mode=true. It must be used together with persona_id: sending persona_model on its own without persona_id has no effect (persona_id may be used on its…\",\"enum\":[\"style_persona\",\"voice_persona\"]},\"duration\":{\"type\":\"integer\",\"description\":\"Desired audio duration in seconds Available only when custom_mode=true and the model is suno-v5.5-beta, suno-v6-beta, suno-v6-mini-beta or suno-v6-wild-beta (or the corresponding compatible name without -beta). The value must be an integer from 10 to 360. Other models and simple mode do not support this parameter; sending it returns a parameter error. Duration control varies by model (best effort, exact duration is not guaranteed): suno-v6-wild-beta, suno-v5.5-beta: Generally follow the requested duration; suno-v6-beta: Set at least 60 seconds; requests below 60 seconds typically still produc…\",\"minimum\":10,\"maximum\":360}},\"example\":{\"prompt\":\"A cheerful summer pop song about road trips and freedom\"}},\"suno-v6-mini-beta\":{\"model\":\"suno-v6-mini-beta\",\"kind\":\"audio\",\"path\":\"/v1/audios/generations\",\"title\":\"Suno Music Generation API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/audio-series/suno/suno-music-generation\",\"required\":[],\"params\":{\"custom_mode\":{\"type\":\"boolean\",\"description\":\"Enable custom mode Description: false: Simple mode, only provide prompt, AI auto-generates lyrics and style; true: Custom mode, allows fine control over style, title, lyrics, etc. Required parameters in custom mode: style: Required; title: Required; prompt: Required when instrumental=false (used as lyrics) Simple mode (custom_mode=false) supports only prompt: style, title, negative_tags, vocal_gender, style_weight, weirdness_constraint, audio_weight, persona_id, persona_model, duration are all unsupported in this mode. The API is not guaranteed to reject them, but they have no effect whatsoev…\",\"default\":false},\"instrumental\":{\"type\":\"boolean\",\"description\":\"Generate instrumental music (no vocals) Description: false: Generate music with vocals; true: Generate instrumental/background music without vocals Note: In non-custom mode, this parameter doesn't affect required fields; In custom mode, when set to true, prompt becomes optional\",\"default\":false},\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the desired music content Non-custom mode (custom_mode=false): Required, serves as music description, AI auto-generates lyrics and style; Max length: 3000 characters Custom mode (custom_mode=true): Required when instrumental=false, used as exact lyrics; Optional when instrumental=true; Max length: 3000 characters for V4, 5000 characters for V4.5 and later (including the V6 family) Lyrics format suggestions: Use tags like [Verse], [Chorus], [Bridge] to organize lyrics structure\"},\"style\":{\"type\":\"string\",\"description\":\"Music style specification Description: Required in custom mode (custom_mode=true); Defines the genre, mood, or artistic direction of the music; Recommended to use comma-separated tags in English Character limits: V4: Max 200 characters; V4.5 and later (including the V6 family): Max 1000 characters Common style tags: Genres: pop, rock, jazz, classical, electronic, hip-hop, r&b, country, folk; Moods: happy, sad, energetic, calm, romantic, dark, uplifting; Instruments: piano, guitar, drums, bass, violin, saxophone, synthesizer; Vocals: male vocals, female vocals, choir, harmonies; Tempo: slow, f…\"},\"title\":{\"type\":\"string\",\"description\":\"Song title Description: Required in custom mode (custom_mode=true); Will be displayed in the player interface and filename; Max length: 80 characters Unsupported in simple mode (custom_mode=false): in that mode the title is generated automatically by the AI, so sending this parameter has no effect.\",\"maxLength\":80},\"negative_tags\":{\"type\":\"string\",\"description\":\"Excluded styles, specify music styles or features to avoid Description: Max length: 200 characters (same for all models) Examples: heavy metal, screaming, sad; rap, fast tempo Supported only when custom_mode=true; sending it in simple mode has no effect.\",\"maxLength\":200},\"vocal_gender\":{\"type\":\"string\",\"description\":\"Vocal gender preference Options: m: Male voice; f: Female voice Note: Only effective when custom_mode=true; This parameter only increases the probability, cannot guarantee the specified gender will be followed; Unsupported in simple mode (custom_mode=false); sending it has no effect\",\"enum\":[\"m\",\"f\"]},\"style_weight\":{\"type\":\"number\",\"description\":\"Style weight, controls adherence to the specified style Range: 0.0 ~ 1.0, up to two decimal places and a multiple of 0.01 Description: Higher values result in closer adherence to the specified style; 0 is a valid value, means no adherence to the specified style, and is sent to the model Supported only when custom_mode=true; sending it in simple mode has no effect.\",\"minimum\":0,\"maximum\":1},\"weirdness_constraint\":{\"type\":\"number\",\"description\":\"Weirdness constraint, controls the creativity/experimental degree of the output Range: 0.0 ~ 1.0, up to two decimal places and a multiple of 0.01 Description: Higher values result in more creative and experimental output; Lower values result in more traditional and conservative output; 0 is a valid value and is sent to the model Supported only when custom_mode=true; sending it in simple mode has no effect.\",\"minimum\":0,\"maximum\":1},\"audio_weight\":{\"type\":\"number\",\"description\":\"Audio weight, controls the weight of audio features Range: 0.0 ~ 1.0, up to two decimal places and a multiple of 0.01 Description: 0 is a valid value and is sent to the model Supported only when custom_mode=true; sending it in simple mode has no effect.\",\"minimum\":0,\"maximum\":1},\"persona_id\":{\"type\":\"string\",\"description\":\"Persona ID to apply a previously created Persona style to this music generation Only available when custom_mode=true. Obtained via the [Suno Persona Creation](/en/api-manual/audio-series/suno/suno-persona-creation) API, preserves consistent vocal and style characteristics How to obtain: After the Persona creation task completes, retrieve from result_data.persona_id Unsupported in simple mode (custom_mode=false). Only supported by V5- and V6-family models (suno-v5-beta / suno-v5.5-beta / suno-v6-beta / suno-v6-mini-beta / suno-v6-wild-beta, including their compatible non--beta names); sending…\"},\"persona_model\":{\"type\":\"string\",\"description\":\"Persona application mode Options: 1. style_persona: Style-oriented, emphasizing musical style characteristics (arrangement, rhythm, timbre) 2. voice_persona: Voice-oriented, emphasizing vocal characteristics (timbre, singing style, voice) Both modes are available only with V5- and V6-family models (suno-v5-beta / suno-v5.5-beta / suno-v6-beta / suno-v6-mini-beta / suno-v6-wild-beta, including their compatible non--beta names) and require custom_mode=true. It must be used together with persona_id: sending persona_model on its own without persona_id has no effect (persona_id may be used on its…\",\"enum\":[\"style_persona\",\"voice_persona\"]},\"duration\":{\"type\":\"integer\",\"description\":\"Desired audio duration in seconds Available only when custom_mode=true and the model is suno-v5.5-beta, suno-v6-beta, suno-v6-mini-beta or suno-v6-wild-beta (or the corresponding compatible name without -beta). The value must be an integer from 10 to 360. Other models and simple mode do not support this parameter; sending it returns a parameter error. Duration control varies by model (best effort, exact duration is not guaranteed): suno-v6-wild-beta, suno-v5.5-beta: Generally follow the requested duration; suno-v6-beta: Set at least 60 seconds; requests below 60 seconds typically still produc…\",\"minimum\":10,\"maximum\":360}},\"example\":{\"prompt\":\"A cheerful summer pop song about road trips and freedom\"}},\"suno-v6-wild-beta\":{\"model\":\"suno-v6-wild-beta\",\"kind\":\"audio\",\"path\":\"/v1/audios/generations\",\"title\":\"Suno Music Generation API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/audio-series/suno/suno-music-generation\",\"required\":[],\"params\":{\"custom_mode\":{\"type\":\"boolean\",\"description\":\"Enable custom mode Description: false: Simple mode, only provide prompt, AI auto-generates lyrics and style; true: Custom mode, allows fine control over style, title, lyrics, etc. Required parameters in custom mode: style: Required; title: Required; prompt: Required when instrumental=false (used as lyrics) Simple mode (custom_mode=false) supports only prompt: style, title, negative_tags, vocal_gender, style_weight, weirdness_constraint, audio_weight, persona_id, persona_model, duration are all unsupported in this mode. The API is not guaranteed to reject them, but they have no effect whatsoev…\",\"default\":false},\"instrumental\":{\"type\":\"boolean\",\"description\":\"Generate instrumental music (no vocals) Description: false: Generate music with vocals; true: Generate instrumental/background music without vocals Note: In non-custom mode, this parameter doesn't affect required fields; In custom mode, when set to true, prompt becomes optional\",\"default\":false},\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the desired music content Non-custom mode (custom_mode=false): Required, serves as music description, AI auto-generates lyrics and style; Max length: 3000 characters Custom mode (custom_mode=true): Required when instrumental=false, used as exact lyrics; Optional when instrumental=true; Max length: 3000 characters for V4, 5000 characters for V4.5 and later (including the V6 family) Lyrics format suggestions: Use tags like [Verse], [Chorus], [Bridge] to organize lyrics structure\"},\"style\":{\"type\":\"string\",\"description\":\"Music style specification Description: Required in custom mode (custom_mode=true); Defines the genre, mood, or artistic direction of the music; Recommended to use comma-separated tags in English Character limits: V4: Max 200 characters; V4.5 and later (including the V6 family): Max 1000 characters Common style tags: Genres: pop, rock, jazz, classical, electronic, hip-hop, r&b, country, folk; Moods: happy, sad, energetic, calm, romantic, dark, uplifting; Instruments: piano, guitar, drums, bass, violin, saxophone, synthesizer; Vocals: male vocals, female vocals, choir, harmonies; Tempo: slow, f…\"},\"title\":{\"type\":\"string\",\"description\":\"Song title Description: Required in custom mode (custom_mode=true); Will be displayed in the player interface and filename; Max length: 80 characters Unsupported in simple mode (custom_mode=false): in that mode the title is generated automatically by the AI, so sending this parameter has no effect.\",\"maxLength\":80},\"negative_tags\":{\"type\":\"string\",\"description\":\"Excluded styles, specify music styles or features to avoid Description: Max length: 200 characters (same for all models) Examples: heavy metal, screaming, sad; rap, fast tempo Supported only when custom_mode=true; sending it in simple mode has no effect.\",\"maxLength\":200},\"vocal_gender\":{\"type\":\"string\",\"description\":\"Vocal gender preference Options: m: Male voice; f: Female voice Note: Only effective when custom_mode=true; This parameter only increases the probability, cannot guarantee the specified gender will be followed; Unsupported in simple mode (custom_mode=false); sending it has no effect\",\"enum\":[\"m\",\"f\"]},\"style_weight\":{\"type\":\"number\",\"description\":\"Style weight, controls adherence to the specified style Range: 0.0 ~ 1.0, up to two decimal places and a multiple of 0.01 Description: Higher values result in closer adherence to the specified style; 0 is a valid value, means no adherence to the specified style, and is sent to the model Supported only when custom_mode=true; sending it in simple mode has no effect.\",\"minimum\":0,\"maximum\":1},\"weirdness_constraint\":{\"type\":\"number\",\"description\":\"Weirdness constraint, controls the creativity/experimental degree of the output Range: 0.0 ~ 1.0, up to two decimal places and a multiple of 0.01 Description: Higher values result in more creative and experimental output; Lower values result in more traditional and conservative output; 0 is a valid value and is sent to the model Supported only when custom_mode=true; sending it in simple mode has no effect.\",\"minimum\":0,\"maximum\":1},\"audio_weight\":{\"type\":\"number\",\"description\":\"Audio weight, controls the weight of audio features Range: 0.0 ~ 1.0, up to two decimal places and a multiple of 0.01 Description: 0 is a valid value and is sent to the model Supported only when custom_mode=true; sending it in simple mode has no effect.\",\"minimum\":0,\"maximum\":1},\"persona_id\":{\"type\":\"string\",\"description\":\"Persona ID to apply a previously created Persona style to this music generation Only available when custom_mode=true. Obtained via the [Suno Persona Creation](/en/api-manual/audio-series/suno/suno-persona-creation) API, preserves consistent vocal and style characteristics How to obtain: After the Persona creation task completes, retrieve from result_data.persona_id Unsupported in simple mode (custom_mode=false). Only supported by V5- and V6-family models (suno-v5-beta / suno-v5.5-beta / suno-v6-beta / suno-v6-mini-beta / suno-v6-wild-beta, including their compatible non--beta names); sending…\"},\"persona_model\":{\"type\":\"string\",\"description\":\"Persona application mode Options: 1. style_persona: Style-oriented, emphasizing musical style characteristics (arrangement, rhythm, timbre) 2. voice_persona: Voice-oriented, emphasizing vocal characteristics (timbre, singing style, voice) Both modes are available only with V5- and V6-family models (suno-v5-beta / suno-v5.5-beta / suno-v6-beta / suno-v6-mini-beta / suno-v6-wild-beta, including their compatible non--beta names) and require custom_mode=true. It must be used together with persona_id: sending persona_model on its own without persona_id has no effect (persona_id may be used on its…\",\"enum\":[\"style_persona\",\"voice_persona\"]},\"duration\":{\"type\":\"integer\",\"description\":\"Desired audio duration in seconds Available only when custom_mode=true and the model is suno-v5.5-beta, suno-v6-beta, suno-v6-mini-beta or suno-v6-wild-beta (or the corresponding compatible name without -beta). The value must be an integer from 10 to 360. Other models and simple mode do not support this parameter; sending it returns a parameter error. Duration control varies by model (best effort, exact duration is not guaranteed): suno-v6-wild-beta, suno-v5.5-beta: Generally follow the requested duration; suno-v6-beta: Set at least 60 seconds; requests below 60 seconds typically still produc…\",\"minimum\":10,\"maximum\":360}},\"example\":{\"prompt\":\"A cheerful summer pop song about road trips and freedom\"}},\"tencent-video-upscale\":{\"model\":\"tencent-video-upscale\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"tencent-video-upscale API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/tencent/tencent-video-upscale\",\"required\":[\"video_urls\"],\"params\":{\"video_urls\":{\"type\":\"array\",\"description\":\"Input video URL list Notes: Only 1 video is supported per request (if more are provided, only the first is used); The video URL must be directly accessible by the server (public or presigned URL); Supported formats: .mp4, .mov; Maximum duration: 60 seconds; Maximum source resolution: 4K (short side no greater than 2160 pixels); On submission, the server reads the video duration, resolution, and frame rate. A read failure returns video_probe_failed\",\"minItems\":1,\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"mode\":{\"type\":\"string\",\"description\":\"Enhancement style. Choose based on the video content Options: realistic - General realistic: live-action footage and other typical scenes — default; realistic_distant - Realistic, distant shots: optimized for small faces in distant footage; animation - General animation: animation, anime, and cartoons; animation_distant - Animation, distant shots: optimized for small faces in animated scenes with distant characters; face_fidelity - Facial fidelity: preserves the original facial features as much as possible; detail_boost - Detail enhancement: makes textures and edges more pronounced; soft - So…\",\"enum\":[\"realistic\",\"realistic_distant\",\"animation\",\"animation_distant\",\"face_fidelity\",\"detail_boost\",\"soft\"],\"default\":\"realistic\"},\"quality\":{\"type\":\"string\",\"description\":\"Target resolution, measured by the video's short side Options: 720p - Short side of 720 pixels; 1080p - Short side of 1080 pixels — default; 2k - Short side of 1440 pixels; 4k - Short side of 2160 pixels Notes: The target resolution cannot be lower than the source. For example, a 1080p source can use 1080p, 2k, or 4k; 720p is rejected; Choosing the lowest tier that is at least as high as the source keeps the image size largely unchanged\",\"enum\":[\"720p\",\"1080p\",\"2k\",\"4k\"],\"default\":\"1080p\"},\"model_params\":{\"type\":\"object\",\"description\":\"Model-specific parameters\",\"properties\":{\"max_fps\":{\"type\":\"string\",\"description\":\"Maximum output frame rate. Defaults to \\\"source\\\", preserving the source frame rate; omitting this parameter is equivalent to \\\"source\\\" Options: \\\"source\\\" - Preserve the source frame rate — default; \\\"30\\\" - Output frame rate no greater than 30 fps; \\\"60\\\" - Output frame rate no greater than 60 fps; \\\"120\\\" - Output frame rate no greater than 120 fps Behavior: Preserves the source frame rate if it does not exceed the cap; does not interpolate frames. Higher frame rates are reduced to the cap; With \\\"source\\\" or when omitted, source frame rates above 120 fps are still reduced to 120 fps Accepted types: St…\",\"enum\":[\"source\",\"30\",\"60\",\"120\"],\"default\":\"source\"}}}},\"example\":{\"video_urls\":[\"https://example.com/my-video.mp4\"]}},\"topaz-video-upscale\":{\"model\":\"topaz-video-upscale\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"topaz-video-upscale API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/topaz/topaz-video-upscale\",\"required\":[\"video_urls\"],\"params\":{\"video_urls\":{\"type\":\"array\",\"description\":\"Input video URL list for upscaling Note: Only 1 video per request; Video URL must be directly accessible by the server (public URL or pre-signed URL); The server will automatically detect the input video duration for billing; Supported formats: .mp4; Maximum file size: 50.0MB\",\"minItems\":1,\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"model_params\":{\"type\":\"object\",\"description\":\"Model-specific parameters for controlling upscale behavior\",\"properties\":{\"upscale_factor\":{\"type\":\"string\",\"description\":\"Video upscale factor, controls the output resolution multiplier Available options: \\\"1\\\" - Enhancement only (no resolution change, AI quality boost); \\\"2\\\" - 2x upscale (e.g. 720p to 1440p) — default; \\\"4\\\" - 4x upscale (e.g. 720p to 2880p) Billing impact: Pricing varies by upscale factor, higher factors cost more Type handling: Accepts both string (\\\"4\\\") and number (4) formats; Invalid values silently fall back to \\\"2\\\" (default)\",\"enum\":[\"1\",\"2\",\"4\"],\"default\":\"2\"}}}},\"example\":{\"video_urls\":[\"https://example.com/my-video.mp4\"]}},\"veo-3.1-fast-generate-preview\":{\"model\":\"veo-3.1-fast-generate-preview\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Veo-3.1-Fast-Generate-Preview API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/veo3.1/veo-3.1-fast-generate-preview-generate\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the video, max 2000 tokens\",\"maxLength\":2000,\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URLs, max 3 images (FIRST&LAST mode supports 1-2, REFERENCE mode supports up to 3), max 10MB each\",\"maxItems\":3,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"generation_type\":{\"type\":\"string\",\"description\":\"Generation mode: TEXT: Text-to-video; FIRST&LAST: First-last frame, 1-2 images; REFERENCE: Reference image, max 3 images, duration fixed at 8s, aspect ratio fixed at 16:9, except generate_audio, other advanced params not supported\",\"enum\":[\"TEXT\",\"FIRST&LAST\",\"REFERENCE\"]},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio. When set to auto: image-to-video will automatically select based on the input image ratio, text-to-video will automatically select based on the prompt content\",\"enum\":[\"auto\",\"16:9\",\"9:16\"]},\"generate_audio\":{\"type\":\"boolean\",\"description\":\"Generate audio (extra cost), default true\"},\"duration\":{\"type\":\"integer\",\"description\":\"Duration (seconds), default 4\",\"enum\":[4,6,8]},\"n\":{\"type\":\"integer\",\"description\":\"Number of videos, default 1\",\"minimum\":1,\"maximum\":4},\"quality\":{\"type\":\"string\",\"description\":\"Resolution, default 720p\",\"enum\":[\"720p\",\"1080p\",\"4k\"]},\"seed\":{\"type\":\"integer\",\"minimum\":1,\"maximum\":4294967295},\"negative_prompt\":{\"type\":\"string\"},\"person_generation\":{\"type\":\"string\",\"description\":\"Person generation control, default allow_adult\",\"enum\":[\"allow_adult\",\"dont_allow\"]},\"resize_mode\":{\"type\":\"string\",\"description\":\"Resize mode (I2V only), default pad\",\"enum\":[\"pad\",\"crop\"]}},\"example\":{\"prompt\":\"A cat playing piano\"}},\"veo-3.1-generate-preview\":{\"model\":\"veo-3.1-generate-preview\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Veo-3.1-Generate-Preview API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/veo3.1/veo-3.1-generate-preview-generate\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt, max 2000 tokens\",\"maxLength\":2000,\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference images, max 3, max 10MB each\",\"maxItems\":3,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"generation_type\":{\"type\":\"string\",\"description\":\"Mode: TEXT: Text-to-video; FIRST&LAST: First-last frame, 1-2 images; REFERENCE: Reference image, max 3 images, duration fixed at 8s, aspect ratio fixed at 16:9, except generate_audio, other advanced params not supported\",\"enum\":[\"TEXT\",\"FIRST&LAST\",\"REFERENCE\"]},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio. When set to auto: image-to-video will automatically select based on the input image ratio, text-to-video will automatically select based on the prompt content\",\"enum\":[\"auto\",\"16:9\",\"9:16\"]},\"generate_audio\":{\"type\":\"boolean\",\"description\":\"Generate audio (extra cost), default true\"},\"duration\":{\"type\":\"integer\",\"description\":\"Duration (seconds), default 4\",\"enum\":[4,6,8]},\"n\":{\"type\":\"integer\",\"description\":\"Number of videos, default 1\",\"minimum\":1,\"maximum\":4},\"quality\":{\"type\":\"string\",\"description\":\"Resolution, default 720p\",\"enum\":[\"720p\",\"1080p\",\"4k\"]},\"seed\":{\"type\":\"integer\",\"minimum\":1,\"maximum\":4294967295},\"negative_prompt\":{\"type\":\"string\"},\"person_generation\":{\"type\":\"string\",\"description\":\"Person generation control, default allow_adult. allow_adult: allow adults only; dont_allow: no people/faces\",\"enum\":[\"allow_adult\",\"dont_allow\"]},\"resize_mode\":{\"type\":\"string\",\"description\":\"Resize mode (I2V only), default pad\",\"enum\":[\"pad\",\"crop\"]}},\"example\":{\"prompt\":\"A cat playing piano\"}},\"veo3.1-fast-beta\":{\"model\":\"veo3.1-fast-beta\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"veo3.1-fast Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/veo3.1/veo3.1-fast-video-generate\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing what kind of video to generate, limited to 2000 tokens\",\"maxLength\":2000,\"required\":true},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio. When set to auto: image-to-video will automatically select based on the input image ratio, text-to-video will automatically select based on the prompt content\",\"enum\":[\"auto\",\"16:9\",\"9:16\"],\"default\":\"auto\"},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL list for image-to-video feature Note: Single request supports input image quantity: 3 images (1 image for first-frame video generation, 2 images for first-and-last-frame video generation); Image size: no more than 10MB; Supported file formats: .jpg, .jpeg, .png, .webp; Image URLs must be directly viewable by the server, or the image URL should trigger direct download when accessed (typically these URLs end with image file extensions, such as .png, .jpg)\",\"maxItems\":3,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution, default is 720p\",\"enum\":[\"720p\"]},\"generation_type\":{\"type\":\"string\",\"description\":\"Video generation mode, default matches based on image count, manual selection recommended. Available modes: TEXT: Text to video; FIRST&LAST: First and last frame to video, supports 1~2 images; REFERENCE: Reference image to video, supports up to 3 images\",\"enum\":[\"TEXT\",\"FIRST&LAST\",\"REFERENCE\"]},\"enhance_prompt\":{\"type\":\"boolean\",\"description\":\"Whether to automatically translate the prompt to English. When enabled, non-English prompts will be automatically translated to English for better generation results\",\"default\":true}},\"example\":{\"prompt\":\"A cat playing piano\"}},\"veo3.1-pro-beta\":{\"model\":\"veo3.1-pro-beta\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"veo3.1-pro Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/veo3.1/veo3.1-pro-video-generate\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing what kind of video to generate, limited to 2000 tokens\",\"maxLength\":2000,\"required\":true},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio. When set to auto: image-to-video will automatically select based on the input image ratio, text-to-video will automatically select based on the prompt content\",\"enum\":[\"auto\",\"16:9\",\"9:16\"],\"default\":\"auto\"},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL list for image-to-video feature Note: Single request supports up to 2 images (1 image for first-frame video generation, 2 images for first-and-last-frame video generation); Image size: no more than 10MB; Supported file formats: .jpg, .jpeg, .png, .webp; Image URLs must be directly viewable by the server, or the image URL should trigger direct download when accessed (typically these URLs end with image file extensions, such as .png, .jpg)\",\"maxItems\":2,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution, default is 720p\",\"enum\":[\"720p\"]},\"generation_type\":{\"type\":\"string\",\"description\":\"Video generation mode, default matches based on image count, manual selection recommended. Available modes: TEXT: Text to video; FIRST&LAST: First and last frame to video, supports 1~2 images\",\"enum\":[\"TEXT\",\"FIRST&LAST\"]},\"enhance_prompt\":{\"type\":\"boolean\",\"description\":\"Whether to automatically translate the prompt to English. When enabled, non-English prompts will be automatically translated to English for better generation results\",\"default\":true}},\"example\":{\"prompt\":\"A cat playing piano\"}},\"videoretalk\":{\"model\":\"videoretalk\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"VideoRetalk Lip-Sync Video Generation\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/videoretalk/videoretalk-video-generate\",\"required\":[\"video_url\",\"audio_url\"],\"params\":{\"video_url\":{\"type\":\"string\",\"description\":\"Input video URL containing the person whose lip movements will be replaced Requirements: Publicly accessible video URL; Formats: MP4, MOV, and other common formats; The video must contain a clearly visible human face; Recommended duration: 2 ~ 300 seconds\",\"format\":\"uri\",\"required\":true},\"audio_url\":{\"type\":\"string\",\"description\":\"Target audio URL — the person in the video will lip-sync to this audio Requirements: Publicly accessible audio URL; Formats: WAV, MP3, M4A, and other common formats; Recommended to use human speech content\",\"format\":\"uri\",\"required\":true},\"ref_image_url\":{\"type\":\"string\",\"description\":\"Reference face image URL When the video contains multiple faces, use this image to specify the target face whose lip movements should be replaced Requirements: The image should show a clear frontal view of the target person's face; Only required when the video contains multiple faces\",\"format\":\"uri\"},\"video_extension\":{\"type\":\"boolean\",\"description\":\"Whether to automatically extend the video to match the audio length when the audio is longer than the video; true: output duration = audio duration (video extended automatically); false: output duration = min(video duration, audio duration)\",\"default\":false},\"query_face_threshold\":{\"type\":\"integer\",\"description\":\"Face matching confidence threshold; Range: 120 ~ 200; Lower values match more easily (may cause false matches); Higher values are stricter (may fail to match); If \\\"no matching face found\\\" is reported, try lowering the value (e.g. 140); If the wrong face is matched, try raising the value (e.g. 190)\",\"default\":170,\"minimum\":120,\"maximum\":200}},\"example\":{\"video_url\":\"https://example.com/speaker.mp4\",\"audio_url\":\"https://example.com/target-speech.wav\"}},\"wan2.5-image-to-image\":{\"model\":\"wan2.5-image-to-image\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"wan2.5-image-to-image Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/wan2.5/wan2.5-image-to-image\",\"required\":[\"prompt\",\"image_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the image to generate or how to edit the input image, limited to 2000 tokens\",\"maxLength\":2000,\"required\":true},\"n\":{\"type\":\"integer\",\"description\":\"Number of images to generate, supports any integer value between [1,4] Note: A single request will be pre-charged based on the value of n, and the actual charge will be based on the number of generated images\"},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL list for image-to-image and image editing functions Note: Maximum number of input images per request: 2 images; Image size: no more than 10MB; Supported image formats: .jpeg, .jpg, .png (transparent channels not supported), .bmp, .webp; Image resolution: image width and height range is [384, 5000] pixels; Image URLs must be directly accessible by the server, or the image URL should directly download when accessed (typically these URLs end with image file extensions, such as .png, .jpg)\",\"maxItems\":2,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true}},\"example\":{\"prompt\":\"Replace the background with a starry sky\",\"image_urls\":[\"https://example.com/image1.png\"]}},\"wan2.5-image-to-video\":{\"model\":\"wan2.5-image-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"wan2.5-image-to-video Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/wan2.5/wan2.5-image-to-video\",\"required\":[\"prompt\",\"image_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing what kind of video to generate, limited to 2000 tokens\",\"maxLength\":2000,\"required\":true},\"duration\":{\"type\":\"integer\",\"description\":\"Specifies the duration of the generated video (seconds) Note: Only supports values 5 and 10, representing 5 seconds and 10 seconds respectively; A single request will pre-charge based on the value of duration, with actual charges based on the generated video duration in seconds\"},\"quality\":{\"type\":\"string\",\"description\":\"Video quality, defaults to 720p Description: 480p: Lower quality, lower price; 720p: Standard quality, standard price, this is the default; 1080p: High quality, higher price\",\"default\":\"720p\"},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL list for first-frame image-to-video feature Note: Single request supports input image quantity: 1 image; Image size: no more than 10MB; Supported image formats: .jpeg, .jpg, .png (transparent channels not supported), .bmp, .webp; Image resolution: image width and height range is [360, 2000] pixels; Image URLs must be directly viewable by the server, or the image URL should trigger direct download when accessed (typically these URLs end with image file extensions, such as .png, .jpg)\",\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"prompt_extend\":{\"type\":\"boolean\",\"description\":\"Whether to enable intelligent prompt rewriting. When enabled, a large language model will optimize the prompt. This is particularly effective for prompts that lack detail or are too simple. Default value is true\",\"default\":true}},\"example\":{\"prompt\":\"A cat playing piano\",\"image_urls\":[\"https://example.com/image1.png\"]}},\"wan2.5-text-to-image\":{\"model\":\"wan2.5-text-to-image\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"wan2.5-text-to-image Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/wan2.5/wan2.5-text-to-image\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the image to generate, limited to 2000 tokens\",\"maxLength\":2000,\"required\":true},\"size\":{\"type\":\"string\",\"description\":\"Size of the generated image, currently only supports pixel format: Width x Height, such as: 768x768, 1280x1280, 1440x1440 and other values within the range; Total pixel range: [768x768, 1440x1440]; Aspect ratio range: [1/4, 4]\"},\"n\":{\"type\":\"integer\",\"description\":\"Number of images to generate, supports any integer value between [1,4] Note: A single request will be pre-charged based on the value of n, and the actual charge will be based on the number of generated images\"},\"prompt_extend\":{\"type\":\"boolean\",\"description\":\"Whether to enable intelligent prompt rewriting. When enabled, a large language model will optimize the prompt. This is particularly effective for prompts that lack detail or are too simple. Default value is true\",\"default\":true}},\"example\":{\"prompt\":\"A serene lake reflecting the beautiful sunset scenery\"}},\"wan2.5-text-to-video\":{\"model\":\"wan2.5-text-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"wan2.5-text-to-video Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/wan2.5/wan2.5-text-to-video\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing what kind of video to generate, limited to 2000 tokens\",\"maxLength\":2000,\"required\":true},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio, defaults to 16:9 Description: 480p: Supports 16:9 (landscape), 9:16 (portrait), 1:1 (square); 720p: Supports 16:9 (landscape), 9:16 (portrait), 1:1 (square), 4:3, 3:4; 1080p: Supports 16:9 (landscape), 9:16 (portrait), 1:1 (square), 4:3, 3:4\",\"default\":\"16:9\"},\"quality\":{\"type\":\"string\",\"description\":\"Video quality, defaults to 720p Description: 480p: Lower quality, lower price; 720p: Standard quality, standard price, this is the default; 1080p: High quality, higher price Note: Different quality levels support different aspect ratios, see aspect_ratio parameter for details\",\"default\":\"720p\"},\"duration\":{\"type\":\"integer\",\"description\":\"Specifies the duration of the generated video (seconds) Note: Only supports values 5 and 10, representing 5 seconds and 10 seconds respectively; A single request will pre-charge based on the value of duration, with actual charges based on the generated video duration in seconds\"},\"prompt_extend\":{\"type\":\"boolean\",\"description\":\"Whether to enable intelligent prompt rewriting. When enabled, a large language model will optimize the prompt. This is particularly effective for prompts that lack detail or are too simple. Default value is true\",\"default\":true}},\"example\":{\"prompt\":\"A cat playing piano\"}},\"wan2.6-image-to-video\":{\"model\":\"wan2.6-image-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"wan2.6-image-to-video API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/wan2.6/wan2.6-image-to-video\",\"required\":[\"prompt\",\"image_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the video you want to generate, limited to 1500 characters\",\"maxLength\":1500,\"required\":true},\"duration\":{\"type\":\"integer\",\"description\":\"Specifies the duration of the generated video (in seconds) Note: Supports any integer value between 2~15 seconds; Each request will be pre-charged based on the duration value, actual charge is based on the generated video duration\",\"minimum\":2,\"maximum\":15},\"quality\":{\"type\":\"string\",\"description\":\"Video quality, defaults to 720p Options: 720p: Standard definition, standard price, this is the default; 1080p: High definition, higher price\"},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL list for first-frame image-to-video generation Note: Single request supports 1 image; Image size: no more than 10MB; Supported formats: .jpeg, .jpg, .png (transparent channel not supported), .bmp, .webp; Image resolution: width and height range is [360, 2000] pixels; Image URL must be directly accessible by the server, or the URL should directly download the image (typically URLs ending with image extensions like .png, .jpg)\",\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"prompt_extend\":{\"type\":\"boolean\",\"description\":\"Whether to enable intelligent prompt rewriting. When enabled, a large model will optimize the prompt, which significantly improves results for simple or insufficiently descriptive prompts. Default is true\"},\"model_params\":{\"type\":\"object\",\"description\":\"Model parameter configuration\",\"properties\":{\"shot_type\":{\"type\":\"string\",\"description\":\"Specifies the shot type for the generated video, i.e., whether the video consists of a single continuous shot or multiple switching shots Effective Condition: Only effective when prompt_extend is true Parameter Priority: shot_type > prompt; For example, if shot_type is set to single, even if the prompt contains generate multi-shot video, the model will still output a single-shot video Options: single: Default, outputs single-shot video; multi: Outputs multi-shot video Note: Use this parameter when you want to strictly control the narrative structure of the video (e.g., single shot for product…\",\"enum\":[\"single\",\"multi\"]}}},\"audio_url\":{\"type\":\"string\",\"description\":\"Audio file URL. The model will use this audio to generate the video. Format Requirements: Supported format: mp3; Duration: 3~30 seconds; File size: Up to 15MB Overflow Handling: If the audio length exceeds the duration value (5 or 10 seconds), the first 5 or 10 seconds will be automatically extracted, and the rest will be discarded; If the audio length is shorter than the video duration, the portion exceeding the audio length will be silent. For example, if the audio is 3 seconds and the video duration is 5 seconds, the output video will have sound for the first 3 seconds and be silent for th…\",\"format\":\"uri\"}},\"example\":{\"prompt\":\"A cat playing piano\",\"image_urls\":[\"https://example.com/image1.png\"]}},\"wan2.6-image-to-video-flash\":{\"model\":\"wan2.6-image-to-video-flash\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"wan2.6-image-to-video-flash API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/wan2.6/wan2.6-image-to-video-flash\",\"required\":[\"prompt\",\"image_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the desired video, limited to 1500 characters\",\"maxLength\":1500,\"required\":true},\"duration\":{\"type\":\"integer\",\"description\":\"Specify the duration of the generated video (seconds) Note: Supports any integer value between 2~15 seconds; Each request will be pre-charged based on the duration value, actual charges are based on the generated video duration\",\"minimum\":2,\"maximum\":15},\"quality\":{\"type\":\"string\",\"description\":\"Video quality, defaults to 720p Options: 720p: Standard quality, standard pricing, this is the default; 1080p: High quality, higher pricing\"},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL list for first-frame image-to-video generation Note: Number of images per request: 1 image; Image size: not exceeding 10MB; Supported image formats: .jpeg, .jpg, .png (no transparency), .bmp, .webp; Image resolution: width and height range [360, 2000] pixels; Image URL must be directly viewable or downloadable (typically URLs ending with image extensions like .png, .jpg)\",\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"prompt_extend\":{\"type\":\"boolean\",\"description\":\"Whether to enable intelligent prompt rewriting. When enabled, uses a large model to optimize the prompt, particularly effective for simple or insufficiently descriptive prompts. Default is true\"},\"model_params\":{\"type\":\"object\",\"description\":\"Model parameter configuration\",\"properties\":{\"shot_type\":{\"type\":\"string\",\"description\":\"Specify the shot type of the generated video, i.e., whether the video consists of a single continuous shot or multiple switching shots Effective when: Only takes effect when prompt_extend is true Parameter priority: shot_type > prompt; For example, if shot_type is set to single, even if prompt contains generate multi-shot video, the model will still output a single-shot video Options: single: Default, outputs single-shot video; multi: Outputs multi-shot video Note: When you want strict control over video narrative structure (e.g., single-shot for product demos, multi-shot for story shorts), u…\",\"enum\":[\"single\",\"multi\"]}}},\"audio_url\":{\"type\":\"string\",\"description\":\"Audio file URL, the model will use this audio to generate the video Format requirements: Supported format: mp3; Duration range: 3~30 seconds; File size: not exceeding 15MB Overflow handling: If audio length exceeds duration value (5 or 10 seconds), automatically truncates to first 5 or 10 seconds, remaining part is discarded; If audio length is less than video duration, the portion beyond audio length will be silent. For example, if audio is 3 seconds and video duration is 5 seconds, the output video will have sound for the first 3 seconds and be silent for the last 2 seconds\",\"format\":\"uri\"},\"generate_audio\":{\"type\":\"boolean\",\"description\":\"Whether to generate audio, defaults to true Options: true: Generate video with audio, higher pricing; false: Generate video without audio, lower pricing\",\"default\":true}},\"example\":{\"prompt\":\"A cat playing piano\",\"image_urls\":[\"https://example.com/image1.png\"]}},\"wan2.6-reference-video\":{\"model\":\"wan2.6-reference-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"wan2.6-reference-video API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/wan2.6/wan2.6-reference-video\",\"required\":[\"prompt\",\"video_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the video you want to generate, limited to 1500 characters\",\"maxLength\":1500,\"required\":true},\"video_urls\":{\"type\":\"array\",\"description\":\"Array of reference video file URLs. Used to extract character appearance and voice from reference videos to generate new videos. URL Requirements: Supports HTTP or HTTPS protocol; Local files can obtain temporary URLs via [File Upload](/en/api-manual/file-series/upload-base64) Array Limits: Maximum 3 videos Video Requirements: Format: mp4, mov; Duration: 2~30 seconds; File size: Single video no more than 100MB Input Video Billing Rules: Each reference video is truncated and summed, total input billing duration capped at 5 seconds; 1 video: min(video duration, 5s); 2 videos: min(video1 duratio…\",\"maxItems\":3,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio, defaults to 16:9 Options: 720p: Supports 16:9 (landscape), 9:16 (portrait), 1:1 (square), 4:3, 3:4; 1080p: Supports 16:9 (landscape), 9:16 (portrait), 1:1 (square), 4:3, 3:4\"},\"quality\":{\"type\":\"string\",\"description\":\"Video quality, defaults to 720p Options: 720p: Standard definition, standard price, this is the default; 1080p: High definition, higher price Note: Different quality levels support different aspect ratios, see aspect_ratio parameter\"},\"duration\":{\"type\":\"integer\",\"description\":\"Specifies the duration of the generated video (in seconds) Note: Supports any integer value between 2~10 seconds Output Video Billing Rules: Output video billing duration: The number of seconds of video successfully generated by the model\",\"minimum\":2,\"maximum\":10},\"model_params\":{\"type\":\"object\",\"description\":\"Model parameter configuration\",\"properties\":{\"shot_type\":{\"type\":\"string\",\"description\":\"Specifies the shot type for the generated video, i.e., whether the video consists of a single continuous shot or multiple switching shots Parameter Priority: shot_type > prompt; For example, if shot_type is set to single, even if the prompt contains generate multi-shot video, the model will still output a single-shot video Options: single: Default, outputs single-shot video; multi: Outputs multi-shot video Note: Use this parameter when you want to strictly control the narrative structure of the video (e.g., single shot for product showcases, multi-shot for short stories)\",\"enum\":[\"single\",\"multi\"]}}}},\"example\":{\"prompt\":\"A person dancing\",\"video_urls\":[\"https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/xxx.mp4\"]}},\"wan2.6-reference-video-flash\":{\"model\":\"wan2.6-reference-video-flash\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"wan2.6-reference-video-flash API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/wan2.6/wan2.6-reference-video-flash\",\"required\":[\"prompt\",\"video_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the desired video, limited to 1500 characters\",\"maxLength\":1500,\"required\":true},\"video_urls\":{\"type\":\"array\",\"description\":\"Array of reference video file URLs. Used to reference character appearance and voice from videos to generate new videos. URL requirements: Supports HTTP or HTTPS protocol; Local files can be uploaded via [Upload File](/en/api-manual/file-series/upload-base64) to get temporary URL Array limits: Maximum 3 videos Video requirements: Format: mp4, mov; Duration: 2～30s; File size: single video not exceeding 100MB Input video billing rules: Each reference video is truncated separately then summed, total input billing duration cap is 5 seconds; 1 video: min(video duration, 5s); 2 videos: min(video1 d…\",\"maxItems\":3,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio, defaults to 16:9 Options: 720p: Supports 16:9 (landscape), 9:16 (portrait), 1:1 (square), 4:3, 3:4; 1080p: Supports 16:9 (landscape), 9:16 (portrait), 1:1 (square), 4:3, 3:4\"},\"quality\":{\"type\":\"string\",\"description\":\"Video quality, defaults to 720p Options: 720p: Standard quality, standard pricing, this is the default; 1080p: High quality, higher pricing Note: Different qualities support different aspect ratios, see aspect_ratio parameter\"},\"duration\":{\"type\":\"integer\",\"description\":\"Specify the duration of the generated video (seconds) Note: Supports any integer value between 2~10 seconds Output video billing rules: Output video billing duration: actual seconds of successfully generated video\",\"minimum\":2,\"maximum\":10},\"model_params\":{\"type\":\"object\",\"description\":\"Model parameter configuration\",\"properties\":{\"shot_type\":{\"type\":\"string\",\"description\":\"Specify the shot type of the generated video, i.e., whether the video consists of a single continuous shot or multiple switching shots Parameter priority: shot_type > prompt; For example, if shot_type is set to single, even if prompt contains generate multi-shot video, the model will still output a single-shot video Options: single: Default, outputs single-shot video; multi: Outputs multi-shot video Note: When you want strict control over video narrative structure (e.g., single-shot for product demos, multi-shot for story shorts), use this parameter\",\"enum\":[\"single\",\"multi\"]}}},\"generate_audio\":{\"type\":\"boolean\",\"description\":\"Whether to generate audio, defaults to true Options: true: Generate video with audio, higher pricing; false: Generate video without audio, lower pricing\",\"default\":true}},\"example\":{\"prompt\":\"A person dancing\",\"video_urls\":[\"https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/xxx.mp4\"]}},\"wan2.6-text-to-video\":{\"model\":\"wan2.6-text-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"wan2.6-text-to-video API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/wan2.6/wan2.6-text-to-video\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the video you want to generate, limited to 1500 characters\",\"maxLength\":1500,\"required\":true},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio, defaults to 16:9 Options: 720p: Supports 16:9 (landscape), 9:16 (portrait), 1:1 (square), 4:3, 3:4; 1080p: Supports 16:9 (landscape), 9:16 (portrait), 1:1 (square), 4:3, 3:4\"},\"quality\":{\"type\":\"string\",\"description\":\"Video quality, defaults to 720p Options: 720p: Standard definition, standard price, this is the default; 1080p: High definition, higher price Note: Different quality levels support different aspect ratios, see aspect_ratio parameter\"},\"duration\":{\"type\":\"integer\",\"description\":\"Specifies the duration of the generated video (in seconds) Note: Supports any integer value between 2~15 seconds; Each request will be pre-charged based on the duration value, actual charge is based on the generated video duration\",\"minimum\":2,\"maximum\":15},\"prompt_extend\":{\"type\":\"boolean\",\"description\":\"Whether to enable intelligent prompt rewriting. When enabled, a large model will optimize the prompt, which significantly improves results for simple or insufficiently descriptive prompts. Default is true\"},\"model_params\":{\"type\":\"object\",\"description\":\"Model parameter configuration\",\"properties\":{\"shot_type\":{\"type\":\"string\",\"description\":\"Specifies the shot type for the generated video, i.e., whether the video consists of a single continuous shot or multiple switching shots Effective Condition: Only effective when prompt_extend is true Parameter Priority: shot_type > prompt; For example, if shot_type is set to single, even if the prompt contains generate multi-shot video, the model will still output a single-shot video Options: single: Default, outputs single-shot video; multi: Outputs multi-shot video Note: Use this parameter when you want to strictly control the narrative structure of the video (e.g., single shot for product…\",\"enum\":[\"single\",\"multi\"]}}},\"audio_url\":{\"type\":\"string\",\"description\":\"Audio file URL. The model will use this audio to generate the video. Format Requirements: Supported format: mp3; Duration: 3~30 seconds; File size: Up to 15MB Overflow Handling: If the audio length exceeds the duration value (5 or 10 seconds), the first 5 or 10 seconds will be automatically extracted, and the rest will be discarded; If the audio length is shorter than the video duration, the portion exceeding the audio length will be silent. For example, if the audio is 3 seconds and the video duration is 5 seconds, the output video will have sound for the first 3 seconds and be silent for th…\",\"format\":\"uri\"}},\"example\":{\"prompt\":\"A cat playing piano\"}},\"wan2.7-image-to-video\":{\"model\":\"wan2.7-image-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"wan2.7-image-to-video API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/wan2.7/wan2.7-image-to-video\",\"required\":[],\"params\":{\"generation_mode\":{\"type\":\"string\",\"description\":\"Generation mode that determines which material combinations are valid. Explicitly specifying it is recommended Values: first_frame: First-frame to video. Required: image_start. Optional: audio_urls. Not accepted: image_end, video_urls; first_last_frame: First-and-last-frame to video. Required: image_start + image_end. Optional: audio_urls. Not accepted: video_urls; video_continuation: Video continuation. Required: video_urls[0]. Optional: image_end (used as ending frame). Not accepted: image_start, audio_urls Backward-compatible behavior: when generation_mode is omitted, an appropriate mode w…\",\"enum\":[\"first_frame\",\"first_last_frame\",\"video_continuation\"]},\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt for video generation. Supports both Chinese and English; each character/letter counts as 1, with overflow auto-truncated. Maximum length: 5000 characters\",\"maxLength\":5000},\"negative_prompt\":{\"type\":\"string\",\"description\":\"Negative prompt describing what should not appear in the video. Supports both Chinese and English. Maximum length 500 characters; overflow is auto-truncated\",\"maxLength\":500},\"image_start\":{\"type\":\"string\",\"description\":\"First-frame image URL Mode constraints: first_frame mode: required; first_last_frame mode: required; video_continuation mode: not allowed Image limits: Formats: JPEG, JPG, PNG (transparency not supported), BMP, WEBP; Resolution: width and height in [240, 8000] pixels; Aspect ratio: 1:8 ~ 8:1; File size: up to 20MB\",\"format\":\"uri\"},\"image_end\":{\"type\":\"string\",\"description\":\"Ending-frame image URL Mode constraints: first_last_frame mode: required; video_continuation mode: optional (acts as the ending frame for the continuation); first_frame mode: not allowed (use first_last_frame if both first and last frames are needed) Image limits: Formats: JPEG, JPG, PNG (transparency not supported), BMP, WEBP; Resolution: width and height in [240, 8000] pixels; Aspect ratio: 1:8 ~ 8:1; File size: up to 20MB\",\"format\":\"uri\"},\"video_urls\":{\"type\":\"array\",\"description\":\"Video continuation URL array. Only 1 element is supported Mode constraints: video_continuation mode: required; first_frame / first_last_frame mode: not allowed; Cannot be combined with audio_urls Video limits: Formats: mp4, mov; Duration: 2 ~ 10 seconds (length of the input clip itself); Resolution: width and height in [240, 4096] pixels; Aspect ratio: 1:8 ~ 8:1; File size: up to 100MB Continuation duration rules: duration represents the total final output video length (input clip + model-generated continuation); Generated continuation length = duration − input video length; duration must be…\",\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"audio_urls\":{\"type\":\"array\",\"description\":\"Driving audio URL array. Currently supports only 1 element. The model will use this audio as the driving source for video generation (e.g. lip sync, motion alignment) Mode constraints: first_frame mode: optional; first_last_frame mode: optional; video_continuation mode: not allowed (cannot be combined with video_urls) Format requirements: Supported formats: wav, mp3; Duration range: 2 ~ 30 seconds; File size: up to 15MB Truncation handling: If audio length exceeds duration, the first N seconds are extracted and the rest discarded; If audio length is shorter than the video duration, the remain…\",\"minItems\":1,\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"quality\":{\"type\":\"string\",\"description\":\"Video quality, defaults to 720p Options: 720p: Standard definition, standard price, this is the default; 1080p: High definition, higher price\",\"enum\":[\"720p\",\"1080p\"],\"default\":\"720p\"},\"duration\":{\"type\":\"number\",\"description\":\"Video duration in seconds (integer). Range 2 ~ 15, default 5 Meaning: first_frame / first_last_frame modes: total length of the generated video; video_continuation mode: total length of the final output video (= original input clip + model-generated continuation) Additional constraints in video_continuation mode: duration must be ≥ input video length (otherwise an error is returned); Generated continuation length = duration − input video length; When duration equals the input video length, no continuation is generated and the input clip is returned as-is; See the continuation duration rules a…\",\"default\":5,\"minimum\":2,\"maximum\":15},\"seed\":{\"type\":\"integer\",\"description\":\"Random seed, defaults to random Notes: Range: 1 ~ 2147483647; Fixing the seed reduces variation when iterating on prompts and improves reproducibility\",\"minimum\":1,\"maximum\":2147483647},\"prompt_extend\":{\"type\":\"boolean\",\"description\":\"Whether to enable intelligent prompt rewriting. When enabled, a large model will optimize the prompt, which significantly improves results for simple or insufficiently descriptive prompts. Note: Default is false. Omitting the field or sending false will not trigger rewriting; explicitly send true to enable.\",\"default\":false}},\"example\":{\"generation_mode\":\"first_frame\",\"prompt\":\"A cat playing piano\",\"image_start\":\"https://example.com/first_frame.jpg\"}},\"wan2.7-reference-video\":{\"model\":\"wan2.7-reference-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"wan2.7-reference-video API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/wan2.7/wan2.7-reference-video\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt for video generation. Supports Chinese and English; each character / letter / punctuation counts as 1, with overflow auto-truncated. Maximum length 5000 characters Character indexing rules: Chinese: use \\\"图1, 图2 / 视频1, 视频2\\\" — corresponds 1-based to the order of image_urls / video_urls; English: use \\\"Image 1\\\", \\\"Video 1\\\" (capitalised, with a space between word and digit); Images and videos are counted independently, so \\\"Image 1\\\" and \\\"Video 1\\\" can coexist; If only one reference image or one reference video is provided, you can simply write \\\"the reference image\\\" or \\\"the reference video…\",\"maxLength\":5000,\"required\":true},\"negative_prompt\":{\"type\":\"string\",\"description\":\"Negative prompt describing what should not appear in the video. Supports both Chinese and English. Maximum length 500 characters; overflow is auto-truncated\",\"maxLength\":500},\"image_start\":{\"type\":\"string\",\"description\":\"Starting-frame image URL, used as the first frame of the generated video. Does not count toward the image_urls + video_urls ≤ 5 limit. Does not accept voice binding (the starting frame itself is not assigned a voice) Use cases: Subject already appears in the starting frame: combine with reference materials to reinforce identity consistency; Subject not in the starting frame: reference materials define new subjects appearing as the video progresses Image limits: Formats: JPEG, JPG, PNG (transparency not supported), BMP, WEBP; Resolution: width and height in [240, 8000] pixels; Aspect ratio: 1:…\",\"format\":\"uri\"},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL array. Can supply subjects (people / animals / objects) or scene backgrounds; when a subject is included, each image should contain a single character Quantity limits: image_urls + video_urls total ≤ 5; At least one of image_urls / video_urls must be provided (passing only image_start is not enough) Image limits: Formats: JPEG, JPG, PNG (transparency not supported), BMP, WEBP; Resolution: width and height in [240, 8000] pixels; Aspect ratio: 1:8 ~ 8:1; File size: up to 20MB\",\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"video_urls\":{\"type\":\"array\",\"description\":\"Reference video URL array. The video should ideally feature a subject (person / animal / object); empty or pure-background footage is discouraged. When a subject is included, each video should contain a single character. Audio in the video can be used as a voice reference Quantity limits: image_urls + video_urls total ≤ 5; At least one of image_urls / video_urls must be provided Video limits: Formats: mp4, mov; Duration: 1 ~ 30 seconds; Resolution: width and height in [240, 4096] pixels; Aspect ratio: 1:8 ~ 8:1; File size: up to 100MB Note: when video_urls is provided, duration is capped at 1…\",\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"audio_urls\":{\"type\":\"array\",\"description\":\"[Compatibility field — prefer model_params.voice_bindings] Reference voice URL array. Bound positionally to reference materials in this order: first match against video_urls, then against image_urls (in their array order, one-to-one). Up to 5 elements Priority: When both model_params.voice_bindings and audio_urls are supplied, only voice_bindings is used and this field is ignored; If a video in video_urls carries audio and no voice binding is set for it, the original audio is used; an explicit voice binding overrides the original audio Audio limits: Supported formats: wav, mp3; Duration range…\",\"maxItems\":5,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"model_params\":{\"type\":\"object\",\"description\":\"Advanced parameter container (recommended)\",\"properties\":{\"voice_bindings\":{\"type\":\"object\",\"description\":\"Precise voice binding for multiple characters (recommended). Has priority over audio_urls Binding rules: Keys are of the form image{N} or video{N} (1-based, no leading zeros, e.g. image1, video2); The N in the key matches \\\"图N / Image N\\\" or \\\"视频N / Video N\\\" in the prompt and corresponds to image_urls[N-1] / video_urls[N-1]; Each value is the voice audio URL for that character; Total bindings ≤ 5; image_start (starting frame) does not accept voice bindings; You may skip some characters (e.g. bind only image1 and image3, leaving image2 unbound) Audio limits: Supported formats: wav, mp3; Duration…\"}}},\"quality\":{\"type\":\"string\",\"description\":\"Video quality, defaults to 720p Options: 720p: Standard definition, standard price, this is the default; 1080p: High definition, higher price\",\"enum\":[\"720p\",\"1080p\"],\"default\":\"720p\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio, defaults to 16:9 Behavior: image_start not provided: video is generated using the specified aspect_ratio; image_start provided: this field is ignored; the video uses an aspect ratio close to the starting-frame image Output resolution per quality tier: | Quality | 16:9 | 9:16 | 1:1 | 4:3 | 3:4 | | --- | --- | --- | --- | --- | --- | | 720p | 1280×720 | 720×1280 | 960×960 | 1104×832 | 832×1104 | | 1080p | 1920×1080 | 1080×1920 | 1440×1440 | 1648×1248 | 1248×1648 |\",\"enum\":[\"16:9\",\"9:16\",\"1:1\",\"4:3\",\"3:4\"],\"default\":\"16:9\"},\"duration\":{\"type\":\"number\",\"description\":\"Video duration in seconds (integer) Range: Without video_urls: 2 ~ 15, default 5; With video_urls: 2 ~ 10 (capped at 10 seconds) Billing: based on the actual generated video duration\",\"default\":5,\"minimum\":2,\"maximum\":15},\"seed\":{\"type\":\"integer\",\"description\":\"Random seed, defaults to random Notes: Range: 1 ~ 2147483647; Fixing the seed reduces variation when iterating on prompts and improves reproducibility\",\"minimum\":1,\"maximum\":2147483647},\"prompt_extend\":{\"type\":\"boolean\",\"description\":\"Whether to enable intelligent prompt rewriting. When enabled, a large model will optimize the prompt, which significantly improves results for simple or insufficiently descriptive prompts. Note: Default is false. Omitting the field or sending false will not trigger rewriting; explicitly send true to enable.\",\"default\":false}},\"example\":{\"prompt\":\"The character from the reference video dancing on a meadow\",\"video_urls\":[\"https://example.com/reference.mp4\"]}},\"wan2.7-text-to-video\":{\"model\":\"wan2.7-text-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"wan2.7-text-to-video API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/wan2.7/wan2.7-text-to-video\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt for video generation. Supports both Chinese and English; each character/letter counts as 1, with overflow auto-truncated. Maximum length: 5000 characters Multi-shot narrative: Control shot structure via natural language; Single shot: state \\\"generate a single-shot video\\\" in the prompt; Multi shot: use \\\"generate a multi-shot video\\\" or timestamped shot lists (e.g. \\\"Shot 1 [0-3s]\\\")\",\"maxLength\":5000,\"required\":true},\"negative_prompt\":{\"type\":\"string\",\"description\":\"Negative prompt describing what should not appear in the video. Supports both Chinese and English. Maximum length 500 characters; overflow is auto-truncated\",\"maxLength\":500},\"audio_urls\":{\"type\":\"array\",\"description\":\"Driving audio URL array (optional). Currently supports only 1 element Behavior: Provided: the model uses this audio as the driving source; Omitted: the model auto-generates background music or sound effects matching the visual content Format requirements: Supported formats: wav, mp3; Duration range: 2 ~ 30 seconds; File size: up to 15MB Truncation handling: If audio length exceeds duration, the first N seconds are extracted and the rest discarded; If audio length is shorter than the video duration, the remaining portion is silent. For example: if audio is 3s and video duration is 5s, the firs…\",\"minItems\":1,\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"quality\":{\"type\":\"string\",\"description\":\"Video quality, defaults to 720p Options: 720p: Standard definition, standard price, this is the default; 1080p: High definition, higher price\",\"enum\":[\"720p\",\"1080p\"],\"default\":\"720p\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio, defaults to 16:9 Output resolution per quality tier: | Quality | 16:9 | 9:16 | 1:1 | 4:3 | 3:4 | | --- | --- | --- | --- | --- | --- | | 720p | 1280×720 | 720×1280 | 960×960 | 1104×832 | 832×1104 | | 1080p | 1920×1080 | 1080×1920 | 1440×1440 | 1648×1248 | 1248×1648 |\",\"enum\":[\"16:9\",\"9:16\",\"1:1\",\"4:3\",\"3:4\"],\"default\":\"16:9\"},\"duration\":{\"type\":\"number\",\"description\":\"Video duration in seconds, range 2-15 Note: Any integer value between 2~15 seconds is supported; Final billing is based on the actual generated video duration\",\"default\":5,\"minimum\":2,\"maximum\":15},\"seed\":{\"type\":\"integer\",\"description\":\"Random seed, defaults to random Notes: Range: 1 ~ 2147483647; Fixing the seed reduces variation when iterating on prompts and improves reproducibility\",\"minimum\":1,\"maximum\":2147483647},\"prompt_extend\":{\"type\":\"boolean\",\"description\":\"Whether to enable intelligent prompt rewriting. When enabled, a large model will optimize the prompt, which significantly improves results for simple or insufficiently descriptive prompts. Note: Default is false. Omitting the field or sending false will not trigger rewriting; explicitly send true to enable.\",\"default\":false}},\"example\":{\"prompt\":\"A small kitten running under the moonlight\",\"aspect_ratio\":\"16:9\",\"duration\":5}},\"wan2.7-video-edit\":{\"model\":\"wan2.7-video-edit\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"wan2.7-video-edit API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/wan2.7/wan2.7-video-edit\",\"required\":[\"video_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing the desired editing effect. Supports Chinese and English; each character/letter counts as 1, with overflow auto-truncated. Maximum length 5000 characters\",\"maxLength\":5000},\"negative_prompt\":{\"type\":\"string\",\"description\":\"Negative prompt describing what should not appear in the video. Supports both Chinese and English. Maximum length 500 characters; overflow is auto-truncated\",\"maxLength\":500},\"video_urls\":{\"type\":\"array\",\"description\":\"Source video URL array. Exactly 1 video is required Video limits: Formats: mp4, mov; Duration: 2 ~ 10 seconds; Resolution: width and height in [240, 4096] pixels; Aspect ratio: 1:8 ~ 8:1; File size: up to 100MB\",\"minItems\":1,\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL array, up to 4 images. Used for the \\\"instruction + reference image\\\" pattern, e.g. replacing clothing or props with elements from a reference image Image limits: Formats: JPEG, JPG, PNG (transparency not supported), BMP, WEBP; Resolution: width and height in [240, 8000] pixels; Aspect ratio: 1:8 ~ 8:1; File size: up to 20MB\",\"maxItems\":4,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"keep_original_sound\":{\"type\":\"boolean\",\"description\":\"Audio handling for the edited video. Default: false; false: Smart mode. The model decides based on prompt content — if the prompt mentions audio elements, it may regenerate audio; otherwise it may preserve the original audio of the input video; true: Force-preserve the original audio of the input video; do not regenerate\",\"default\":false},\"quality\":{\"type\":\"string\",\"description\":\"Video quality, defaults to 720p Options: 720p: Standard definition, standard price, this is the default; 1080p: High definition, higher price\",\"enum\":[\"720p\",\"1080p\"],\"default\":\"720p\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio (optional) Behavior: Not provided: video is generated using an aspect ratio close to the input video; Provided: video is generated using the specified aspect_ratio Output resolution per quality tier: | Quality | 16:9 | 9:16 | 1:1 | 4:3 | 3:4 | | --- | --- | --- | --- | --- | --- | | 720p | 1280×720 | 720×1280 | 960×960 | 1104×832 | 832×1104 | | 1080p | 1920×1080 | 1080×1920 | 1440×1440 | 1648×1248 | 1248×1648 |\",\"enum\":[\"16:9\",\"9:16\",\"1:1\",\"4:3\",\"3:4\"]},\"duration\":{\"type\":\"number\",\"description\":\"Video duration in seconds Rules: Default 0: keep the input video duration; no truncation (only set this field when you want to truncate the input video); When set explicitly, range is 2 ~ 10: the system truncates the input video starting at 0s up to the specified duration\",\"default\":0,\"minimum\":0,\"maximum\":10},\"seed\":{\"type\":\"integer\",\"description\":\"Random seed, defaults to random Notes: Range: 1 ~ 2147483647; Fixing the seed reduces variation when iterating on prompts and improves reproducibility\",\"minimum\":1,\"maximum\":2147483647},\"prompt_extend\":{\"type\":\"boolean\",\"description\":\"Whether to enable intelligent prompt rewriting. When enabled, a large model will optimize the prompt, which significantly improves results for simple or insufficiently descriptive prompts. Note: Default is false. Omitting the field or sending false will not trigger rewriting; explicitly send true to enable.\",\"default\":false}},\"example\":{\"prompt\":\"Convert the entire scene to a clay-style look\",\"video_urls\":[\"https://example.com/source.mp4\"]}},\"wan3.0-image-to-video\":{\"model\":\"wan3.0-image-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Wan3.0 Image-to-Video\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/wan3.0/wan3.0-image-to-video\",\"required\":[\"image_start\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt for video generation. Chinese and English are supported, each Chinese character / letter counts as 1 character, maximum length 20000 characters; anything beyond that is truncated automatically (no error) Use it to describe the action, camera movement and visual changes expected between the first frame (or the first and last frames).\"},\"image_start\":{\"type\":\"string\",\"description\":\"First-frame image URL, used strictly as the first frame of the generated video. Required Image limits: Formats: JPEG, JPG, PNG (transparency not supported), BMP, WEBP; Resolution: width and height in [240, 8000] pixels; Aspect ratio: 1:8 ~ 8:1; File size: up to 20MB\",\"format\":\"uri\",\"required\":true},\"image_end\":{\"type\":\"string\",\"description\":\"Last-frame image URL, used strictly as the last frame of the generated video. Optional Constraint: must be used together with image_start, passing the last frame alone is not supported. Image limits: Formats: JPEG, JPG, PNG (transparency not supported), BMP, WEBP; Resolution: width and height in [240, 8000] pixels; Aspect ratio: 1:8 ~ 8:1; File size: up to 20MB\",\"format\":\"uri\"},\"duration\":{\"type\":\"integer\",\"description\":\"Duration of the generated video in seconds, defaults to 5 Accepted values: Any integer between 2 and 30; -1: smart duration, the model decides the output length from the prompt and the input material How smart duration is billed: the output length cannot be known at submission time, so credits are pre-authorized at the 30-second cap; once the task succeeds it is settled against the actual output duration and the excess hold is released automatically. If your balance cannot cover the capped hold, pass an explicit number of seconds instead.\",\"default\":5},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution, defaults to 720p Options: 480p: lower definition, lowest price (billing baseline); 720p: standard definition, this is the default, 2x the price of 480p; 1080p: high definition, 4x the price of 480p\",\"enum\":[\"480p\",\"720p\",\"1080p\"],\"default\":\"720p\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio, defaults to adaptive Options: adaptive: adaptive, the model recommends a suitable aspect ratio based on the input material's ratio and the intent of the prompt, this is the default; 16:9 (landscape), 9:16 (portrait), 1:1 (square), 4:3, 3:4\",\"enum\":[\"adaptive\",\"16:9\",\"9:16\",\"1:1\",\"4:3\",\"3:4\"],\"default\":\"adaptive\"},\"generate_audio\":{\"type\":\"boolean\",\"description\":\"Whether the output video contains an audio track, defaults to true Options: true: the output video contains sound (voices, sound effects, background music), this is the default; false: silent video output Sound on and sound off cost the same, there is no extra charge.\",\"default\":true},\"seed\":{\"type\":\"integer\",\"description\":\"Random seed, used to reproduce generation results, random by default Notes: Range: 0 ~ 2147483647; Fixing the seed reduces variation when iterating on prompts and improves reproducibility\",\"minimum\":0,\"maximum\":2147483647}},\"example\":{\"prompt\":\"The boy in the frame “comes alive” out of the wall and performs an English rap at breakneck speed, while street lights under a railway bridge at night create a cinematic mood.\",\"image_start\":\"https://example.com/first_frame.png\",\"duration\":5,\"quality\":\"720p\"}},\"wan3.0-prime-image-to-video\":{\"model\":\"wan3.0-prime-image-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Wan3.0 Prime Image-to-Video\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/wan3.0/wan3.0-prime-image-to-video\",\"required\":[\"image_start\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt for video generation. Chinese and English are supported, each Chinese character / letter counts as 1 character, maximum length 20000 characters; anything beyond that is truncated automatically (no error) Use it to describe the action, camera movement and visual changes expected between the first frame (or the first and last frames).\"},\"image_start\":{\"type\":\"string\",\"description\":\"First-frame image URL, used strictly as the first frame of the generated video. Required Image limits: Formats: JPEG, JPG, PNG (transparency not supported), BMP, WEBP; Resolution: width and height in [240, 8000] pixels; Aspect ratio: 1:8 ~ 8:1; File size: up to 20MB\",\"format\":\"uri\",\"required\":true},\"image_end\":{\"type\":\"string\",\"description\":\"Last-frame image URL, used strictly as the last frame of the generated video. Optional Constraint: must be used together with image_start, passing the last frame alone is not supported. Image limits: Formats: JPEG, JPG, PNG (transparency not supported), BMP, WEBP; Resolution: width and height in [240, 8000] pixels; Aspect ratio: 1:8 ~ 8:1; File size: up to 20MB\",\"format\":\"uri\"},\"duration\":{\"type\":\"integer\",\"description\":\"Duration of the generated video in seconds, defaults to 5 Accepted values: Any integer between 2 and 30; -1: smart duration, the model decides the output length from the prompt and the input material How smart duration is billed: the output length cannot be known at submission time, so credits are pre-authorized at the 30-second cap; once the task succeeds it is settled against the actual output duration and the excess hold is released automatically. If your balance cannot cover the capped hold, pass an explicit number of seconds instead.\",\"default\":5},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution, defaults to 720p Options: 480p: lower definition, lowest price (billing baseline); 720p: standard definition, this is the default, 2.06x the price of 480p; 1080p: high definition, 4.12x the price of 480p\",\"enum\":[\"480p\",\"720p\",\"1080p\"],\"default\":\"720p\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio, defaults to adaptive Options: adaptive: adaptive, the model recommends a suitable aspect ratio based on the input material's ratio and the intent of the prompt, this is the default; 16:9 (landscape), 9:16 (portrait), 1:1 (square), 4:3, 3:4\",\"enum\":[\"adaptive\",\"16:9\",\"9:16\",\"1:1\",\"4:3\",\"3:4\"],\"default\":\"adaptive\"},\"generate_audio\":{\"type\":\"boolean\",\"description\":\"Whether the output video contains an audio track, defaults to true Options: true: the output video contains sound (voices, sound effects, background music), this is the default; false: silent video output Sound on and sound off cost the same, there is no extra charge.\",\"default\":true},\"seed\":{\"type\":\"integer\",\"description\":\"Random seed, used to reproduce generation results, random by default Notes: Range: 0 ~ 2147483647; Fixing the seed reduces variation when iterating on prompts and improves reproducibility\",\"minimum\":0,\"maximum\":2147483647}},\"example\":{\"prompt\":\"The boy in the frame “comes alive” out of the wall and performs an English rap at breakneck speed, while street lights under a railway bridge at night create a cinematic mood.\",\"image_start\":\"https://example.com/first_frame.png\",\"duration\":5,\"quality\":\"720p\"}},\"wan3.0-prime-reference-video\":{\"model\":\"wan3.0-prime-reference-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Wan3.0 Prime Reference-to-Video\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/wan3.0/wan3.0-prime-reference-video\",\"required\":[],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt for video generation. Chinese and English are supported, each Chinese character / letter counts as 1 character, maximum length 20000 characters; anything beyond that is truncated automatically (no error) Material reference rules: Use \\\"Image 1\\\", \\\"Image 2\\\" to refer to the images at the matching positions in image_urls (1-based); Use \\\"Video 1\\\", \\\"Video 2\\\" to refer to the videos at the matching positions in video_urls; Use \\\"Audio 1\\\", \\\"Audio 2\\\" to refer to the audio at the matching positions in audio_urls; Images, videos and audio are counted independently, so \\\"Image 1\\\" and \\\"Video 1\\\" ca…\"},\"image_urls\":{\"type\":\"array\",\"description\":\"Array of reference image URLs, up to 10 images. They can supply subjects (people / animals / objects) or scene backgrounds; when a subject is included, each image should contain a single character The array order matches \\\"Image 1, Image 2, ...\\\" in the prompt. Image limits: Formats: JPEG, JPG, PNG (transparency not supported), BMP, WEBP; Resolution: width and height in [240, 8000] pixels; Aspect ratio: 1:8 ~ 8:1; File size: up to 20MB\",\"maxItems\":10,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"video_urls\":{\"type\":\"array\",\"description\":\"Array of reference video URLs, up to 5 clips. The array order matches \\\"Video 1, Video 2, ...\\\" in the prompt Duration limits: 1 ~ 15 seconds per clip; 15 seconds in total at most; Total reference video duration + output video duration must not exceed 30 seconds 🔴 Reference videos count toward billing: billed duration = input video duration + output video duration. Reference images, reference audio, files and web pages are not billed Video limits: Formats: mp4, mov; Resolution: width and height in [240, 4096] pixels; Aspect ratio: 1:8 ~ 8:1; Size per file: up to 100MB\",\"maxItems\":5,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"audio_urls\":{\"type\":\"array\",\"description\":\"Array of reference audio URLs, up to 5 clips. The array order matches \\\"Audio 1, Audio 2, ...\\\" in the prompt Different semantics from Wan2.7: in Wan2.7, audio_urls carried a voice bound to a specific reference image / reference video; in Wan3.0 Prime reference audio is standalone material referred to directly from the prompt as \\\"Audio 1\\\", and the model_params.voice_bindings voice-binding protocol is not supported. Rewrite accordingly when migrating from Wan2.7. Duration limits: 1 ~ 15 seconds per clip, 15 seconds in total at most; Reference audio is not billed Audio limits: Formats: wav, mp3;…\",\"maxItems\":5,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"model_params\":{\"type\":\"object\",\"description\":\"Model extension parameters. file_url and link_url are mutually exclusive, pick one of the two\",\"properties\":{\"file_url\":{\"type\":\"string\",\"description\":\"Reference file URL, at most 1. The model interprets the file's content automatically and generates the video from it (for example turning a product deck into a promo video) Mutually exclusive with link_url, the two cannot be supplied together File limits: Formats: docx, doc, xlsx, xls, pptx, ppt, pdf, txt, key, pages, numbers, md; File size: up to 100MB; Pages: no more than 50\",\"format\":\"uri\"},\"link_url\":{\"type\":\"string\",\"description\":\"Reference web page link, at most 1. The model fetches and interprets the page content automatically, then generates the video Mutually exclusive with file_url, the two cannot be supplied together Limitation: only public pages that require no login can be parsed (news articles, blog posts, newsletter articles, etc.)\",\"format\":\"uri\"}}},\"duration\":{\"type\":\"integer\",\"description\":\"Duration of the generated video in seconds, defaults to 5 Accepted values: Any integer between 2 and 30; -1: smart duration, the model decides the output length from the prompt and the input material How smart duration is billed: the output length cannot be known at submission time, so credits are pre-authorized at the 30-second cap; once the task succeeds it is settled against the actual output duration and the excess hold is released automatically. If your balance cannot cover the capped hold, pass an explicit number of seconds instead. Extra constraint when reference videos are supplied: T…\",\"default\":5},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution, defaults to 720p Options: 480p: lower definition, lowest price (billing baseline); 720p: standard definition, this is the default, 2.06x the price of 480p; 1080p: high definition, 4.12x the price of 480p\",\"enum\":[\"480p\",\"720p\",\"1080p\"],\"default\":\"720p\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio, defaults to adaptive Options: adaptive: adaptive, the model recommends a suitable aspect ratio based on the input material's ratio and the intent of the prompt, this is the default; 16:9 (landscape), 9:16 (portrait), 1:1 (square), 4:3, 3:4\",\"enum\":[\"adaptive\",\"16:9\",\"9:16\",\"1:1\",\"4:3\",\"3:4\"],\"default\":\"adaptive\"},\"generate_audio\":{\"type\":\"boolean\",\"description\":\"Whether the output video contains an audio track, defaults to true Options: true: the output video contains sound (voices, sound effects, background music), this is the default; false: silent video output Sound on and sound off cost the same, there is no extra charge.\",\"default\":true},\"seed\":{\"type\":\"integer\",\"description\":\"Random seed, used to reproduce generation results, random by default Notes: Range: 0 ~ 2147483647; Fixing the seed reduces variation when iterating on prompts and improves reproducibility\",\"minimum\":0,\"maximum\":2147483647}},\"example\":{\"prompt\":\"The character in Video 1 holds Image 3 and plays a soft country folk tune on the chair in Image 4, saying: “What lovely sunshine today.”\",\"image_urls\":[\"https://example.com/role.jpg\",\"https://example.com/object.png\",\"https://example.com/guitar.png\",\"https://example.com/chair.png\"],\"video_urls\":[\"https://example.com/ref_role.mp4\"],\"duration\":10,\"quality\":\"720p\",\"aspect_ratio\":\"adaptive\"}},\"wan3.0-prime-text-to-video\":{\"model\":\"wan3.0-prime-text-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Wan3.0 Prime Text-to-Video\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/wan3.0/wan3.0-prime-text-to-video\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt for video generation. Chinese and English are supported, each Chinese character / letter counts as 1 character, maximum length 20000 characters; anything beyond that is truncated automatically (no error) Note: this model is pure text-to-video and accepts no media input.\",\"required\":true},\"duration\":{\"type\":\"integer\",\"description\":\"Duration of the generated video in seconds, defaults to 5 Accepted values: Any integer between 2 and 30; -1: smart duration, the model decides the output length from the prompt and the input material How smart duration is billed: the output length cannot be known at submission time, so credits are pre-authorized at the 30-second cap; once the task succeeds it is settled against the actual output duration and the excess hold is released automatically. If your balance cannot cover the capped hold, pass an explicit number of seconds instead.\",\"default\":5},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution, defaults to 720p Options: 480p: lower definition, lowest price (billing baseline); 720p: standard definition, this is the default, 2.06x the price of 480p; 1080p: high definition, 4.12x the price of 480p\",\"enum\":[\"480p\",\"720p\",\"1080p\"],\"default\":\"720p\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio, defaults to adaptive Options: adaptive: adaptive, the model recommends a suitable aspect ratio based on the input material's ratio and the intent of the prompt, this is the default; 16:9 (landscape), 9:16 (portrait), 1:1 (square), 4:3, 3:4\",\"enum\":[\"adaptive\",\"16:9\",\"9:16\",\"1:1\",\"4:3\",\"3:4\"],\"default\":\"adaptive\"},\"generate_audio\":{\"type\":\"boolean\",\"description\":\"Whether the output video contains an audio track, defaults to true Options: true: the output video contains sound (voices, sound effects, background music), this is the default; false: silent video output Sound on and sound off cost the same, there is no extra charge.\",\"default\":true},\"seed\":{\"type\":\"integer\",\"description\":\"Random seed, used to reproduce generation results, random by default Notes: Range: 0 ~ 2147483647; Fixing the seed reduces variation when iterating on prompts and improves reproducibility\",\"minimum\":0,\"maximum\":2147483647}},\"example\":{\"prompt\":\"A kitten runs across a rooftop in the moonlight, city neon flickers in the distance, cinematic quality, smooth camera work.\",\"duration\":5,\"quality\":\"720p\",\"aspect_ratio\":\"16:9\",\"generate_audio\":true}},\"wan3.0-reference-video\":{\"model\":\"wan3.0-reference-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Wan3.0 Reference-to-Video\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/wan3.0/wan3.0-reference-video\",\"required\":[],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt for video generation. Chinese and English are supported, each Chinese character / letter counts as 1 character, maximum length 20000 characters; anything beyond that is truncated automatically (no error) Material reference rules: Use \\\"Image 1\\\", \\\"Image 2\\\" to refer to the images at the matching positions in image_urls (1-based); Use \\\"Video 1\\\", \\\"Video 2\\\" to refer to the videos at the matching positions in video_urls; Use \\\"Audio 1\\\", \\\"Audio 2\\\" to refer to the audio at the matching positions in audio_urls; Images, videos and audio are counted independently, so \\\"Image 1\\\" and \\\"Video 1\\\" ca…\"},\"image_urls\":{\"type\":\"array\",\"description\":\"Array of reference image URLs, up to 10 images. They can supply subjects (people / animals / objects) or scene backgrounds; when a subject is included, each image should contain a single character The array order matches \\\"Image 1, Image 2, ...\\\" in the prompt. Image limits: Formats: JPEG, JPG, PNG (transparency not supported), BMP, WEBP; Resolution: width and height in [240, 8000] pixels; Aspect ratio: 1:8 ~ 8:1; File size: up to 20MB\",\"maxItems\":10,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"video_urls\":{\"type\":\"array\",\"description\":\"Array of reference video URLs, up to 5 clips. The array order matches \\\"Video 1, Video 2, ...\\\" in the prompt Duration limits: 1 ~ 15 seconds per clip; 15 seconds in total at most; Total reference video duration + output video duration must not exceed 30 seconds 🔴 Reference videos count toward billing: billed duration = input video duration + output video duration. Reference images, reference audio, files and web pages are not billed Video limits: Formats: mp4, mov; Resolution: width and height in [240, 4096] pixels; Aspect ratio: 1:8 ~ 8:1; Size per file: up to 100MB\",\"maxItems\":5,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"audio_urls\":{\"type\":\"array\",\"description\":\"Array of reference audio URLs, up to 5 clips. The array order matches \\\"Audio 1, Audio 2, ...\\\" in the prompt Different semantics from Wan2.7: in Wan2.7, audio_urls carried a voice bound to a specific reference image / reference video; in Wan3.0 reference audio is standalone material referred to directly from the prompt as \\\"Audio 1\\\", and the model_params.voice_bindings voice-binding protocol is not supported. Rewrite accordingly when migrating from Wan2.7. Duration limits: 1 ~ 15 seconds per clip, 15 seconds in total at most; Reference audio is not billed Audio limits: Formats: wav, mp3; File s…\",\"maxItems\":5,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"model_params\":{\"type\":\"object\",\"description\":\"Model extension parameters. file_url and link_url are mutually exclusive, pick one of the two\",\"properties\":{\"file_url\":{\"type\":\"string\",\"description\":\"Reference file URL, at most 1. The model interprets the file's content automatically and generates the video from it (for example turning a product deck into a promo video) Mutually exclusive with link_url, the two cannot be supplied together File limits: Formats: docx, doc, xlsx, xls, pptx, ppt, pdf, txt, key, pages, numbers, md; File size: up to 100MB; Pages: no more than 50\",\"format\":\"uri\"},\"link_url\":{\"type\":\"string\",\"description\":\"Reference web page link, at most 1. The model fetches and interprets the page content automatically, then generates the video Mutually exclusive with file_url, the two cannot be supplied together Limitation: only public pages that require no login can be parsed (news articles, blog posts, newsletter articles, etc.)\",\"format\":\"uri\"}}},\"duration\":{\"type\":\"integer\",\"description\":\"Duration of the generated video in seconds, defaults to 5 Accepted values: Any integer between 2 and 30; -1: smart duration, the model decides the output length from the prompt and the input material How smart duration is billed: the output length cannot be known at submission time, so credits are pre-authorized at the 30-second cap; once the task succeeds it is settled against the actual output duration and the excess hold is released automatically. If your balance cannot cover the capped hold, pass an explicit number of seconds instead. Extra constraint when reference videos are supplied: T…\",\"default\":5},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution, defaults to 720p Options: 480p: lower definition, lowest price (billing baseline); 720p: standard definition, this is the default, 2x the price of 480p; 1080p: high definition, 4x the price of 480p\",\"enum\":[\"480p\",\"720p\",\"1080p\"],\"default\":\"720p\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio, defaults to adaptive Options: adaptive: adaptive, the model recommends a suitable aspect ratio based on the input material's ratio and the intent of the prompt, this is the default; 16:9 (landscape), 9:16 (portrait), 1:1 (square), 4:3, 3:4\",\"enum\":[\"adaptive\",\"16:9\",\"9:16\",\"1:1\",\"4:3\",\"3:4\"],\"default\":\"adaptive\"},\"generate_audio\":{\"type\":\"boolean\",\"description\":\"Whether the output video contains an audio track, defaults to true Options: true: the output video contains sound (voices, sound effects, background music), this is the default; false: silent video output Sound on and sound off cost the same, there is no extra charge.\",\"default\":true},\"seed\":{\"type\":\"integer\",\"description\":\"Random seed, used to reproduce generation results, random by default Notes: Range: 0 ~ 2147483647; Fixing the seed reduces variation when iterating on prompts and improves reproducibility\",\"minimum\":0,\"maximum\":2147483647}},\"example\":{\"prompt\":\"The character in Video 1 holds Image 3 and plays a soft country folk tune on the chair in Image 4, saying: “What lovely sunshine today.”\",\"image_urls\":[\"https://example.com/role.jpg\",\"https://example.com/object.png\",\"https://example.com/guitar.png\",\"https://example.com/chair.png\"],\"video_urls\":[\"https://example.com/ref_role.mp4\"],\"duration\":10,\"quality\":\"720p\",\"aspect_ratio\":\"adaptive\"}},\"wan3.0-text-to-video\":{\"model\":\"wan3.0-text-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Wan3.0 Text-to-Video\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/wan3.0/wan3.0-text-to-video\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt for video generation. Chinese and English are supported, each Chinese character / letter counts as 1 character, maximum length 20000 characters; anything beyond that is truncated automatically (no error) Note: this model is pure text-to-video and accepts no media input.\",\"required\":true},\"duration\":{\"type\":\"integer\",\"description\":\"Duration of the generated video in seconds, defaults to 5 Accepted values: Any integer between 2 and 30; -1: smart duration, the model decides the output length from the prompt and the input material How smart duration is billed: the output length cannot be known at submission time, so credits are pre-authorized at the 30-second cap; once the task succeeds it is settled against the actual output duration and the excess hold is released automatically. If your balance cannot cover the capped hold, pass an explicit number of seconds instead.\",\"default\":5},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution, defaults to 720p Options: 480p: lower definition, lowest price (billing baseline); 720p: standard definition, this is the default, 2x the price of 480p; 1080p: high definition, 4x the price of 480p\",\"enum\":[\"480p\",\"720p\",\"1080p\"],\"default\":\"720p\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio, defaults to adaptive Options: adaptive: adaptive, the model recommends a suitable aspect ratio based on the input material's ratio and the intent of the prompt, this is the default; 16:9 (landscape), 9:16 (portrait), 1:1 (square), 4:3, 3:4\",\"enum\":[\"adaptive\",\"16:9\",\"9:16\",\"1:1\",\"4:3\",\"3:4\"],\"default\":\"adaptive\"},\"generate_audio\":{\"type\":\"boolean\",\"description\":\"Whether the output video contains an audio track, defaults to true Options: true: the output video contains sound (voices, sound effects, background music), this is the default; false: silent video output Sound on and sound off cost the same, there is no extra charge.\",\"default\":true},\"seed\":{\"type\":\"integer\",\"description\":\"Random seed, used to reproduce generation results, random by default Notes: Range: 0 ~ 2147483647; Fixing the seed reduces variation when iterating on prompts and improves reproducibility\",\"minimum\":0,\"maximum\":2147483647}},\"example\":{\"prompt\":\"A kitten runs across a rooftop in the moonlight, city neon flickers in the distance, cinematic quality, smooth camera work.\",\"duration\":5,\"quality\":\"720p\",\"aspect_ratio\":\"16:9\",\"generate_audio\":true}},\"z-image-turbo\":{\"model\":\"z-image-turbo\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"z-image-turbo Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/z-image-turbo/z-image-turbo-image-generate\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the image to be generated, limited to 2000 characters\",\"maxLength\":2000,\"required\":true},\"size\":{\"type\":\"string\",\"description\":\"Size of the generated image. Supports two formats: Aspect Ratio Format: Use preset ratios like 1:1, 16:9, 9:16, etc.; Supported ratios: 1:1, 2:3, 3:2, 3:4, 4:3, 9:16, 16:9, 1:2, 2:1 Custom Dimensions: Width x Height (e.g., 1024x768); Width and height range: 376-1536 pixels\",\"enum\":[\"1:1\",\"2:3\",\"3:2\",\"3:4\",\"4:3\",\"9:16\",\"16:9\",\"1:2\",\"2:1\"]},\"seed\":{\"type\":\"integer\",\"description\":\"Random seed for reproducible results Note: Range: 1 to 2147483647; Leave empty for random seed; Same seed with same prompt produces similar results\",\"minimum\":1,\"maximum\":2147483647},\"nsfw_check\":{\"type\":\"boolean\",\"description\":\"Enable additional NSFW content moderation Note: Default: false (disabled); Basic content moderation is always active even when disabled; Enable for stricter content filtering\",\"default\":false}},\"example\":{\"prompt\":\"a cute cat\",\"size\":\"1:1\"}}}}";
+//# sourceMappingURL=model-params.generated.js.map