switch

Generate Video

generate_video

Generate Switch video across the real provider lineup (Kling, BytePlus Seedance, Switch Video/WAN 2.7, Switch Video Edit, Topaz upscale) and modes (text-to-video, image-to-video, frame-to-frame, motion, omni, reference-to-video, video-edit, upscale). Load load_video_workflow once per conversation when needed. Keep the user-selected model; use list_video_models only when the selection or its inputs are unknown. SwitchApp Video Enhanced runs automatically before submission; call enhance_video_prompt first to inspect it and reuse its signed enhancement_receipt. Use quote_video for the exact current token price and pass quote_fingerprint plus quoted_credits to enforce it. Use Switch MCP directly; never open the website, browser, or desktop unless the user explicitly asked. For realistic reference-driven video, evaluate BytePlus Seedance 2.5 first unless the user chose another provider or model. Before submission, map every actual image, video, and audio chip to its role and preserve its thumbnail, type, order, and role exactly; never silently drop, merge, reorder, convert, or repurpose references. Pass one shot, or shots:[...] for a storyboard (max 4 by default, hard max 10) where EACH shot is DIFFERENT — never repeat one prompt to get copies. Renders async (~30-90s); a background job delivers each clip to your library. Returns a task_id per shot — poll get_video_status or list_my_videos.

Input Schema

TableJSON Schema

Name	Required	Description
`mode`	No	Video mode. Must be supported by the chosen model (see list_video_models).
`audio`	No	Generate audio. ON by default on Seedance 2.5 (text, image and reference), on Omni, and on every WAN 3.0 lane (text, image, reference); set false for a silent clip. Models without audio ignore this. See list_video_models for which models generate audio and the max seconds with vs without audio.
`model`	No	Model id from list_video_models (e.g. kling-v3, seedance-2.0-t2v, wan-3.0-t2v, h3-max-t2v, topaz). Or prefer option_id from list_video_models. MiniMax H3 Max ids: h3-max-t2v, h3-max-i2v, h3-max-r2v (option ids h3max-text / h3max-image / h3max-reference). MiniMax H3 Max Turbo (preview, about twice as fast at half the price, no reference lane): h3-max-turbo-t2v, h3-max-turbo-i2v (option ids h3max-turbo-text / h3max-turbo-image). WAN 3.0 ids: wan-3.0-t2v, wan-3.0-i2v, wan-3.0-r2v (option ids wan30-text / wan30-image / wan30-reference): 720p or 1080p, any whole second 2 to 30, generated audio on by default, image lane takes image_url and an optional end_image_url, reference lane takes up to 10 reference_image_urls and 5 reference_video_urls.
`shots`	No	A storyboard of 1-10 DISTINCT shots. Each item takes the same fields as a single shot (subject, model, mode, image_url, etc.).
`subject`	No	The shot: subject + motion + scene (video needs motion language, e.g. "slow push-in"). WAN 3.0: refer to references by their place ("Image 1", "Video 1"), not by @tags; there is no negative-prompt field, so write exclusions inline as "Avoid: ...". MiniMax H3 Max: put spoken words in double quotes and the character says them lip-synced; name references by place (Image 1, Video 1, Audio 1).
`duration`	No	Clip length in seconds, or "auto" to let the model choose. Seedance 2.5 does 4-30s (auto bills the 30s cap up front and refunds the unused seconds); Seedance 2.0 does 4-15s; Switch Video (WAN 2.7) does 5/10/15; WAN 3.0 takes any whole second from 2 to 30; Kling/Switch Video Edit cap at 10; MiniMax H3 Max takes whole seconds 5 to 15 (no auto) — see each model's durations in list_video_models.
`image_url`	No	Required for image-to-video / frame-to-frame / motion. Accepts EITHER a Switch asset id (from show_media / list_my_assets / upload_media) OR a public https url. An asset id is resolved server-side, so just pass the id you have — no need to fetch a url first.
`option_id`	No	Optional catalog id from list_video_models (e.g. "kling-image"); use instead of model+mode.
`task_type`	No	Seedance 2.5 reference mode only: declare what you are doing with the reference clip so the size and length rules are checked immediately instead of failing a minute in. auto = a new take from the references (default), edit = change something inside the clip, extend = continue the clip. Editing and extension inherit the source clip's size, and editing also inherits its length.
`video_url`	No	Required for video-edit and upscale (the source clip). Accepts one of YOUR Switch videos — a job id from list_my_videos / get_video_status, or its download_url / view_url — or any publicly downloadable https URL. Switch resolves its own videos for you; no need to scrape a page for the file.
`resolution`	No	Output resolution. Defaults to 1080p where the model supports it. 720p is cheaper and faster. 480p is the cheapest. Seedance 2.5 offers 480p, 720p and 1080p on every mode (no 2K/4K). 4K is only on Kling v3 text/image and Kling Omni; Seedance text-to-video is 720p only. MiniMax H3 Max offers 480p and 768p only (its reference lane is 768p only). Each model lists its available resolutions in list_video_models.
`aspect_ratio`	No	e.g. 9:16, 16:9, 1:1. Must be allowed for the model (see list_video_models).
`end_image_url`	No	End frame for frame-to-frame mode.
`quoted_credits`	No	Exact quoted_credits returned by quote_video; used with quote_fingerprint.
`quote_fingerprint`	No	From quote_video. Pass with quoted_credits to reject a changed quote before charging.
`face_reference_ids`	No	Face reference asset ids from upload_reference_asset (frame_type "face") — the ONLY way to use a face/likeness reference in video. Each id is verified server-side (your own untouched original + identity verification) before the shot fires or is charged; URLs and generic uploads here are rejected.
`enhancement_receipt`	No	Receipt from enhance_video_prompt. Pass its enhanced_prompt as subject with the same model, settings and references. Prevents duplicate enhancement. Changed/expired receipts fail before generation.
`reference_audio_urls`	No	Seedance reference/omni only: up to 3 reference audio files to drive synthesized audio. Requires at least one reference image or video. MiniMax H3 Max reference (h3max-reference) also takes up to 3 audio files as conditioning (voice/sound guidance); it generates native audio on every clip regardless.
`reference_image_urls`	No	GENERIC reference images (products, scenery, outfits, style). Each entry accepts EITHER a Switch asset id (from show_media / list_my_assets / upload_media / get_my_active_references) OR a public https url — asset ids are resolved server-side. Seedance reference/omni accepts up to 9; Kling Omni up to 7. WAN 3.0 reference (option wan30-reference, model wan-3.0-r2v) accepts up to 10; name each one by its place in the prompt ("the woman in Image 1", "the jacket from Image 3"). For Seedance, at least one image or video reference is required. For a person's face/likeness use face_reference_ids instead.
`reference_video_urls`	No	Seedance reference/omni and WAN 3.0 reference. WAN 3.0 (wan30-reference): up to 5 clips, 15 seconds combined, each at least 16 fps, addressed in the prompt as "Video 1", "Video 2"; the audio inside the clips is not kept. Seedance: reference video clips for motion/style guidance — up to 10 on Seedance 2.5 (clips 2-30s, 30s combined), up to 3 on Seedance 2.0 (see list_video_models for each model's caps). A Seedance video ref can satisfy the required visual anchor. Per the BytePlus guide a video reference is a subject reference: it can carry appearance, identity, motion AND voice timbre. State in the prompt what each asset provides. MiniMax H3 Max reference (h3max-reference): up to 3 clips, each second of reference clip is billed on top of the output seconds (see its notes).
`character_orientation`	No	Motion mode only: follow the character image (default) or the reference video.
`person_rights_confirmed`	No	Required with video_people_declaration "person": confirms you own or are authorized to use the person's likeness in the reference video.
`video_people_declaration`	No	Required with reference_video_urls: "none" confirms no real person appears; "person" runs the protected pipeline (verified account, your own stored upload, Seedance 2.5/Mini lane, provider asset registration) — also pass person_rights_confirmed: true.

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedSep 16, 2026

addedInput schema / properties / enhancement_receipt

Added value: +{
+  "description": "Receipt from enhance_video_prompt. Pass its enhanced_prompt as subject with the same model, settings and references. Prevents duplicate enhancement. Changed/expired receipts fail before generation.",
+  "type": "string"
+}

addedInput schema / properties / quote_fingerprint

Added value: +{
+  "description": "From quote_video. Pass with quoted_credits to reject a changed quote before charging.",
+  "type": "string"
+}

addedInput schema / properties / quoted_credits

Added value: +{
+  "description": "Exact quoted_credits returned by quote_video; used with quote_fingerprint.",
+  "type": "number"
+}

addedInput schema / properties / shots / items / properties / enhancement_receipt

Added value: +{
+  "description": "Receipt from enhance_video_prompt. Pass its enhanced_prompt as subject with the same model, settings and references. Prevents duplicate enhancement. Changed/expired receipts fail before generation.",
+  "type": "string"
+}

addedInput schema / properties / shots / items / properties / quote_fingerprint

Added value: +{
+  "description": "From quote_video. Pass with quoted_credits to reject a changed quote before charging.",
+  "type": "string"
+}

addedInput schema / properties / shots / items / properties / quoted_credits

Added value: +{
+  "description": "Exact quoted_credits returned by quote_video; used with quote_fingerprint.",
+  "type": "number"
+}

Changed2 schema fields changedSep 3, 2026

changedInput schema / properties / model / description

Previous value: -"Model id from list_video_models (e.g. kling-v3, seedance-2.0-t2v, wan-3.0-t2v, h3-max-t2v, topaz). Or prefer option_id from list_video_models. MiniMax H3 Max ids: h3-max-t2v, h3-max-i2v, h3-max-r2v (option ids h3max-text / h3max-image / h3max-reference). WAN 3.0 ids: wan-3.0-t2v, wan-3.0-i2v, wan-3.0-r2v (option ids wan30-text / wan30-image / wan30-reference): 720p or 1080p, any whole second 2 to 30, generated audio on by default, image lane takes image_url and an optional end_image_url, reference lane takes up to 10 reference_image_urls and 5 reference_video_urls."New value: +"Model id from list_video_models (e.g. kling-v3, seedance-2.0-t2v, wan-3.0-t2v, h3-max-t2v, topaz). Or prefer option_id from list_video_models. MiniMax H3 Max ids: h3-max-t2v, h3-max-i2v, h3-max-r2v (option ids h3max-text / h3max-image / h3max-reference). MiniMax H3 Max Turbo (preview, about twice as fast at half the price, no reference lane): h3-max-turbo-t2v, h3-max-turbo-i2v (option ids h3max-turbo-text / h3max-turbo-image). WAN 3.0 ids: wan-3.0-t2v, wan-3.0-i2v, wan-3.0-r2v (option ids wan30-text / wan30-image / wan30-reference): 720p or 1080p, any whole second 2 to 30, generated audio on by default, image lane takes image_url and an optional end_image_url, reference lane takes up to 10 reference_image_urls and 5 reference_video_urls."

changedInput schema / properties / shots / items / properties / model / description

Previous value: -"Model id from list_video_models (e.g. kling-v3, seedance-2.0-t2v, wan-3.0-t2v, h3-max-t2v, topaz). Or prefer option_id from list_video_models. MiniMax H3 Max ids: h3-max-t2v, h3-max-i2v, h3-max-r2v (option ids h3max-text / h3max-image / h3max-reference). WAN 3.0 ids: wan-3.0-t2v, wan-3.0-i2v, wan-3.0-r2v (option ids wan30-text / wan30-image / wan30-reference): 720p or 1080p, any whole second 2 to 30, generated audio on by default, image lane takes image_url and an optional end_image_url, reference lane takes up to 10 reference_image_urls and 5 reference_video_urls."New value: +"Model id from list_video_models (e.g. kling-v3, seedance-2.0-t2v, wan-3.0-t2v, h3-max-t2v, topaz). Or prefer option_id from list_video_models. MiniMax H3 Max ids: h3-max-t2v, h3-max-i2v, h3-max-r2v (option ids h3max-text / h3max-image / h3max-reference). MiniMax H3 Max Turbo (preview, about twice as fast at half the price, no reference lane): h3-max-turbo-t2v, h3-max-turbo-i2v (option ids h3max-turbo-text / h3max-turbo-image). WAN 3.0 ids: wan-3.0-t2v, wan-3.0-i2v, wan-3.0-r2v (option ids wan30-text / wan30-image / wan30-reference): 720p or 1080p, any whole second 2 to 30, generated audio on by default, image lane takes image_url and an optional end_image_url, reference lane takes up to 10 reference_image_urls and 5 reference_video_urls."

Changed12 schema fields changedSep 2, 2026

changedInput schema / properties / audio / description

Previous value: -"Generate audio. ON by default on Seedance 2.5 (text, image and reference) and on Omni; set false for a silent clip. Models without audio ignore this. See list_video_models for which models generate audio and the max seconds with vs without audio."New value: +"Generate audio. ON by default on Seedance 2.5 (text, image and reference), on Omni, and on every WAN 3.0 lane (text, image, reference); set false for a silent clip. Models without audio ignore this. See list_video_models for which models generate audio and the max seconds with vs without audio."

changedInput schema / properties / duration / description

Previous value: -"Clip length in seconds, or \"auto\" to let the model choose. Seedance 2.5 does 4-30s (auto bills the 30s cap up front and refunds the unused seconds); Seedance 2.0 does 4-15s; Switch Video (WAN) does 5/10/15; Kling/Switch Video Edit cap at 10; MiniMax H3 Max takes whole seconds 5 to 15 (no auto) — see each model's durations in list_video_models."New value: +"Clip length in seconds, or \"auto\" to let the model choose. Seedance 2.5 does 4-30s (auto bills the 30s cap up front and refunds the unused seconds); Seedance 2.0 does 4-15s; Switch Video (WAN 2.7) does 5/10/15; WAN 3.0 takes any whole second from 2 to 30; Kling/Switch Video Edit cap at 10; MiniMax H3 Max takes whole seconds 5 to 15 (no auto) — see each model's durations in list_video_models."

changedInput schema / properties / model / description

Previous value: -"Model id from list_video_models (e.g. kling-v3, seedance-2.0-t2v, wan-3.0-t2v, h3-max-t2v, topaz). Or prefer option_id from list_video_models. MiniMax H3 Max ids: h3-max-t2v, h3-max-i2v, h3-max-r2v (option ids h3max-text / h3max-image / h3max-reference)."New value: +"Model id from list_video_models (e.g. kling-v3, seedance-2.0-t2v, wan-3.0-t2v, h3-max-t2v, topaz). Or prefer option_id from list_video_models. MiniMax H3 Max ids: h3-max-t2v, h3-max-i2v, h3-max-r2v (option ids h3max-text / h3max-image / h3max-reference). WAN 3.0 ids: wan-3.0-t2v, wan-3.0-i2v, wan-3.0-r2v (option ids wan30-text / wan30-image / wan30-reference): 720p or 1080p, any whole second 2 to 30, generated audio on by default, image lane takes image_url and an optional end_image_url, reference lane takes up to 10 reference_image_urls and 5 reference_video_urls."

changedInput schema / properties / reference_image_urls / description

Previous value: -"GENERIC reference images (products, scenery, outfits, style). Each entry accepts EITHER a Switch asset id (from show_media / list_my_assets / upload_media / get_my_active_references) OR a public https url — asset ids are resolved server-side. Seedance reference/omni accepts up to 9; Kling Omni up to 7. For Seedance, at least one image or video reference is required. For a person's face/likeness use face_reference_ids instead."New value: +"GENERIC reference images (products, scenery, outfits, style). Each entry accepts EITHER a Switch asset id (from show_media / list_my_assets / upload_media / get_my_active_references) OR a public https url — asset ids are resolved server-side. Seedance reference/omni accepts up to 9; Kling Omni up to 7. WAN 3.0 reference (option wan30-reference, model wan-3.0-r2v) accepts up to 10; name each one by its place in the prompt (\"the woman in Image 1\", \"the jacket from Image 3\"). For Seedance, at least one image or video reference is required. For a person's face/likeness use face_reference_ids instead."

changedInput schema / properties / reference_video_urls / description

Previous value: -"Seedance reference/omni only: reference video clips for motion/style guidance — up to 10 on Seedance 2.5 (clips 2-30s, 30s combined), up to 3 on Seedance 2.0 (see list_video_models for each model's caps). A Seedance video ref can satisfy the required visual anchor. Per the BytePlus guide a video reference is a subject reference: it can carry appearance, identity, motion AND voice timbre. State in the prompt what each asset provides. MiniMax H3 Max reference (h3max-reference): up to 3 clips, each second of reference clip is billed on top of the output seconds (see its notes)."New value: +"Seedance reference/omni and WAN 3.0 reference. WAN 3.0 (wan30-reference): up to 5 clips, 15 seconds combined, each at least 16 fps, addressed in the prompt as \"Video 1\", \"Video 2\"; the audio inside the clips is not kept. Seedance: reference video clips for motion/style guidance — up to 10 on Seedance 2.5 (clips 2-30s, 30s combined), up to 3 on Seedance 2.0 (see list_video_models for each model's caps). A Seedance video ref can satisfy the required visual anchor. Per the BytePlus guide a video reference is a subject reference: it can carry appearance, identity, motion AND voice timbre. State in the prompt what each asset provides. MiniMax H3 Max reference (h3max-reference): up to 3 clips, each second of reference clip is billed on top of the output seconds (see its notes)."

changedInput schema / properties / shots / items / properties / audio / description

Previous value: -"Generate audio. ON by default on Seedance 2.5 (text, image and reference) and on Omni; set false for a silent clip. Models without audio ignore this. See list_video_models for which models generate audio and the max seconds with vs without audio."New value: +"Generate audio. ON by default on Seedance 2.5 (text, image and reference), on Omni, and on every WAN 3.0 lane (text, image, reference); set false for a silent clip. Models without audio ignore this. See list_video_models for which models generate audio and the max seconds with vs without audio."

changedInput schema / properties / shots / items / properties / duration / description

Previous value: -"Clip length in seconds, or \"auto\" to let the model choose. Seedance 2.5 does 4-30s (auto bills the 30s cap up front and refunds the unused seconds); Seedance 2.0 does 4-15s; Switch Video (WAN) does 5/10/15; Kling/Switch Video Edit cap at 10; MiniMax H3 Max takes whole seconds 5 to 15 (no auto) — see each model's durations in list_video_models."New value: +"Clip length in seconds, or \"auto\" to let the model choose. Seedance 2.5 does 4-30s (auto bills the 30s cap up front and refunds the unused seconds); Seedance 2.0 does 4-15s; Switch Video (WAN 2.7) does 5/10/15; WAN 3.0 takes any whole second from 2 to 30; Kling/Switch Video Edit cap at 10; MiniMax H3 Max takes whole seconds 5 to 15 (no auto) — see each model's durations in list_video_models."

changedInput schema / properties / shots / items / properties / model / description

Previous value: -"Model id from list_video_models (e.g. kling-v3, seedance-2.0-t2v, wan-3.0-t2v, h3-max-t2v, topaz). Or prefer option_id from list_video_models. MiniMax H3 Max ids: h3-max-t2v, h3-max-i2v, h3-max-r2v (option ids h3max-text / h3max-image / h3max-reference)."New value: +"Model id from list_video_models (e.g. kling-v3, seedance-2.0-t2v, wan-3.0-t2v, h3-max-t2v, topaz). Or prefer option_id from list_video_models. MiniMax H3 Max ids: h3-max-t2v, h3-max-i2v, h3-max-r2v (option ids h3max-text / h3max-image / h3max-reference). WAN 3.0 ids: wan-3.0-t2v, wan-3.0-i2v, wan-3.0-r2v (option ids wan30-text / wan30-image / wan30-reference): 720p or 1080p, any whole second 2 to 30, generated audio on by default, image lane takes image_url and an optional end_image_url, reference lane takes up to 10 reference_image_urls and 5 reference_video_urls."

changedInput schema / properties / shots / items / properties / reference_image_urls / description

Previous value: -"GENERIC reference images (products, scenery, outfits, style). Each entry accepts EITHER a Switch asset id (from show_media / list_my_assets / upload_media / get_my_active_references) OR a public https url — asset ids are resolved server-side. Seedance reference/omni accepts up to 9; Kling Omni up to 7. For Seedance, at least one image or video reference is required. For a person's face/likeness use face_reference_ids instead."New value: +"GENERIC reference images (products, scenery, outfits, style). Each entry accepts EITHER a Switch asset id (from show_media / list_my_assets / upload_media / get_my_active_references) OR a public https url — asset ids are resolved server-side. Seedance reference/omni accepts up to 9; Kling Omni up to 7. WAN 3.0 reference (option wan30-reference, model wan-3.0-r2v) accepts up to 10; name each one by its place in the prompt (\"the woman in Image 1\", \"the jacket from Image 3\"). For Seedance, at least one image or video reference is required. For a person's face/likeness use face_reference_ids instead."

changedInput schema / properties / shots / items / properties / reference_video_urls / description

Previous value: -"Seedance reference/omni only: reference video clips for motion/style guidance — up to 10 on Seedance 2.5 (clips 2-30s, 30s combined), up to 3 on Seedance 2.0 (see list_video_models for each model's caps). A Seedance video ref can satisfy the required visual anchor. Per the BytePlus guide a video reference is a subject reference: it can carry appearance, identity, motion AND voice timbre. State in the prompt what each asset provides. MiniMax H3 Max reference (h3max-reference): up to 3 clips, each second of reference clip is billed on top of the output seconds (see its notes)."New value: +"Seedance reference/omni and WAN 3.0 reference. WAN 3.0 (wan30-reference): up to 5 clips, 15 seconds combined, each at least 16 fps, addressed in the prompt as \"Video 1\", \"Video 2\"; the audio inside the clips is not kept. Seedance: reference video clips for motion/style guidance — up to 10 on Seedance 2.5 (clips 2-30s, 30s combined), up to 3 on Seedance 2.0 (see list_video_models for each model's caps). A Seedance video ref can satisfy the required visual anchor. Per the BytePlus guide a video reference is a subject reference: it can carry appearance, identity, motion AND voice timbre. State in the prompt what each asset provides. MiniMax H3 Max reference (h3max-reference): up to 3 clips, each second of reference clip is billed on top of the output seconds (see its notes)."

changedInput schema / properties / shots / items / properties / subject / description

Previous value: -"The shot: subject + motion + scene (video needs motion language, e.g. \"slow push-in\")."New value: +"The shot: subject + motion + scene (video needs motion language, e.g. \"slow push-in\"). WAN 3.0: refer to references by their place (\"Image 1\", \"Video 1\"), not by @tags; there is no negative-prompt field, so write exclusions inline as \"Avoid: ...\". MiniMax H3 Max: put spoken words in double quotes and the character says them lip-synced; name references by place (Image 1, Video 1, Audio 1)."

changedInput schema / properties / subject / description

Previous value: -"The shot: subject + motion + scene (video needs motion language, e.g. \"slow push-in\")."New value: +"The shot: subject + motion + scene (video needs motion language, e.g. \"slow push-in\"). WAN 3.0: refer to references by their place (\"Image 1\", \"Video 1\"), not by @tags; there is no negative-prompt field, so write exclusions inline as \"Avoid: ...\". MiniMax H3 Max: put spoken words in double quotes and the character says them lip-synced; name references by place (Image 1, Video 1, Audio 1)."

Changed12 schema fields changedSep 2, 2026

changedInput schema / properties / duration / description

Previous value: -"Clip length in seconds, or \"auto\" to let the model choose. Seedance 2.5 does 4-30s (auto bills the 30s cap up front and refunds the unused seconds); Seedance 2.0 does 4-15s; Switch Video (WAN) does 5/10/15; Kling/Switch Video Edit cap at 10 — see each model's durations in list_video_models."New value: +"Clip length in seconds, or \"auto\" to let the model choose. Seedance 2.5 does 4-30s (auto bills the 30s cap up front and refunds the unused seconds); Seedance 2.0 does 4-15s; Switch Video (WAN) does 5/10/15; Kling/Switch Video Edit cap at 10; MiniMax H3 Max takes whole seconds 5 to 15 (no auto) — see each model's durations in list_video_models."

changedInput schema / properties / model / description

Previous value: -"Model id from list_video_models (e.g. kling-v3, seedance-2.0-t2v, wan-2.7-t2v, topaz). Or prefer option_id from list_video_models."New value: +"Model id from list_video_models (e.g. kling-v3, seedance-2.0-t2v, wan-3.0-t2v, h3-max-t2v, topaz). Or prefer option_id from list_video_models. MiniMax H3 Max ids: h3-max-t2v, h3-max-i2v, h3-max-r2v (option ids h3max-text / h3max-image / h3max-reference)."

changedInput schema / properties / reference_audio_urls / description

Previous value: -"Seedance reference/omni only: up to 3 reference audio files to drive synthesized audio. Requires at least one reference image or video."New value: +"Seedance reference/omni only: up to 3 reference audio files to drive synthesized audio. Requires at least one reference image or video. MiniMax H3 Max reference (h3max-reference) also takes up to 3 audio files as conditioning (voice/sound guidance); it generates native audio on every clip regardless."

changedInput schema / properties / reference_video_urls / description

Previous value: -"Seedance reference/omni only: reference video clips for motion/style guidance — up to 10 on Seedance 2.5 (clips 2-30s, 30s combined), up to 3 on Seedance 2.0 (see list_video_models for each model's caps). A Seedance video ref can satisfy the required visual anchor. NOTE: the AUDIO track of these clips is IGNORED — never extracted or preserved."New value: +"Seedance reference/omni only: reference video clips for motion/style guidance — up to 10 on Seedance 2.5 (clips 2-30s, 30s combined), up to 3 on Seedance 2.0 (see list_video_models for each model's caps). A Seedance video ref can satisfy the required visual anchor. Per the BytePlus guide a video reference is a subject reference: it can carry appearance, identity, motion AND voice timbre. State in the prompt what each asset provides. MiniMax H3 Max reference (h3max-reference): up to 3 clips, each second of reference clip is billed on top of the output seconds (see its notes)."

changedInput schema / properties / resolution / description

Previous value: -"Output resolution. Defaults to 1080p where the model supports it. 720p is cheaper and faster. 480p is the cheapest. Seedance 2.5 offers 480p, 720p and 1080p on every mode (no 2K/4K). 4K is only on Kling v3 text/image and Kling Omni; Seedance text-to-video is 720p only. Each model lists its available resolutions in list_video_models."New value: +"Output resolution. Defaults to 1080p where the model supports it. 720p is cheaper and faster. 480p is the cheapest. Seedance 2.5 offers 480p, 720p and 1080p on every mode (no 2K/4K). 4K is only on Kling v3 text/image and Kling Omni; Seedance text-to-video is 720p only. MiniMax H3 Max offers 480p and 768p only (its reference lane is 768p only). Each model lists its available resolutions in list_video_models."

changedInput schema / properties / resolution / enum

Previous value: -[
-  "480p",
-  "720p",
-  "1080p",
-  "4k"
-]New value: +[
+  "480p",
+  "720p",
+  "768p",
+  "1080p",
+  "4k"
+]

changedInput schema / properties / shots / items / properties / duration / description

Previous value: -"Clip length in seconds, or \"auto\" to let the model choose. Seedance 2.5 does 4-30s (auto bills the 30s cap up front and refunds the unused seconds); Seedance 2.0 does 4-15s; Switch Video (WAN) does 5/10/15; Kling/Switch Video Edit cap at 10 — see each model's durations in list_video_models."New value: +"Clip length in seconds, or \"auto\" to let the model choose. Seedance 2.5 does 4-30s (auto bills the 30s cap up front and refunds the unused seconds); Seedance 2.0 does 4-15s; Switch Video (WAN) does 5/10/15; Kling/Switch Video Edit cap at 10; MiniMax H3 Max takes whole seconds 5 to 15 (no auto) — see each model's durations in list_video_models."

changedInput schema / properties / shots / items / properties / model / description

Previous value: -"Model id from list_video_models (e.g. kling-v3, seedance-2.0-t2v, wan-2.7-t2v, topaz). Or prefer option_id from list_video_models."New value: +"Model id from list_video_models (e.g. kling-v3, seedance-2.0-t2v, wan-3.0-t2v, h3-max-t2v, topaz). Or prefer option_id from list_video_models. MiniMax H3 Max ids: h3-max-t2v, h3-max-i2v, h3-max-r2v (option ids h3max-text / h3max-image / h3max-reference)."

changedInput schema / properties / shots / items / properties / reference_audio_urls / description

Previous value: -"Seedance reference/omni only: up to 3 reference audio files to drive synthesized audio. Requires at least one reference image or video."New value: +"Seedance reference/omni only: up to 3 reference audio files to drive synthesized audio. Requires at least one reference image or video. MiniMax H3 Max reference (h3max-reference) also takes up to 3 audio files as conditioning (voice/sound guidance); it generates native audio on every clip regardless."

changedInput schema / properties / shots / items / properties / reference_video_urls / description

Previous value: -"Seedance reference/omni only: reference video clips for motion/style guidance — up to 10 on Seedance 2.5 (clips 2-30s, 30s combined), up to 3 on Seedance 2.0 (see list_video_models for each model's caps). A Seedance video ref can satisfy the required visual anchor. NOTE: the AUDIO track of these clips is IGNORED — never extracted or preserved."New value: +"Seedance reference/omni only: reference video clips for motion/style guidance — up to 10 on Seedance 2.5 (clips 2-30s, 30s combined), up to 3 on Seedance 2.0 (see list_video_models for each model's caps). A Seedance video ref can satisfy the required visual anchor. Per the BytePlus guide a video reference is a subject reference: it can carry appearance, identity, motion AND voice timbre. State in the prompt what each asset provides. MiniMax H3 Max reference (h3max-reference): up to 3 clips, each second of reference clip is billed on top of the output seconds (see its notes)."

changedInput schema / properties / shots / items / properties / resolution / description

Previous value: -"Output resolution. Defaults to 1080p where the model supports it. 720p is cheaper and faster. 480p is the cheapest. Seedance 2.5 offers 480p, 720p and 1080p on every mode (no 2K/4K). 4K is only on Kling v3 text/image and Kling Omni; Seedance text-to-video is 720p only. Each model lists its available resolutions in list_video_models."New value: +"Output resolution. Defaults to 1080p where the model supports it. 720p is cheaper and faster. 480p is the cheapest. Seedance 2.5 offers 480p, 720p and 1080p on every mode (no 2K/4K). 4K is only on Kling v3 text/image and Kling Omni; Seedance text-to-video is 720p only. MiniMax H3 Max offers 480p and 768p only (its reference lane is 768p only). Each model lists its available resolutions in list_video_models."

changedInput schema / properties / shots / items / properties / resolution / enum

Previous value: -[
-  "480p",
-  "720p",
-  "1080p",
-  "4k"
-]New value: +[
+  "480p",
+  "720p",
+  "768p",
+  "1080p",
+  "4k"
+]

Changed2 schema fields changedAug 18, 2026

changedInput schema / properties / resolution / description

Previous value: -"Output resolution. Defaults to 1080p where the model supports it. 720p is cheaper and faster. 480p is the cheapest. Seedance 2.5 offers 480p and 720p only, on every mode. 4K is only on Kling v3 text/image and Kling Omni; Seedance text-to-video is 720p only. Each model lists its available resolutions in list_video_models."New value: +"Output resolution. Defaults to 1080p where the model supports it. 720p is cheaper and faster. 480p is the cheapest. Seedance 2.5 offers 480p, 720p and 1080p on every mode (no 2K/4K). 4K is only on Kling v3 text/image and Kling Omni; Seedance text-to-video is 720p only. Each model lists its available resolutions in list_video_models."

changedInput schema / properties / shots / items / properties / resolution / description

Previous value: -"Output resolution. Defaults to 1080p where the model supports it. 720p is cheaper and faster. 480p is the cheapest. Seedance 2.5 offers 480p and 720p only, on every mode. 4K is only on Kling v3 text/image and Kling Omni; Seedance text-to-video is 720p only. Each model lists its available resolutions in list_video_models."New value: +"Output resolution. Defaults to 1080p where the model supports it. 720p is cheaper and faster. 480p is the cheapest. Seedance 2.5 offers 480p, 720p and 1080p on every mode (no 2K/4K). 4K is only on Kling v3 text/image and Kling Omni; Seedance text-to-video is 720p only. Each model lists its available resolutions in list_video_models."

Changed2 schema fields changedAug 13, 2026

addedInput schema / properties / person_rights_confirmed

Added value: +{
+  "description": "Required with video_people_declaration \"person\": confirms you own or are authorized to use the person's likeness in the reference video.",
+  "type": "boolean"
+}

changedInput schema / properties / video_people_declaration / description

Previous value: -"Required when reference_video_urls is used: \"none\" confirms no real person appears in the reference clips; \"person\" routes to the protected workflow (not yet supported through the connector)."New value: +"Required with reference_video_urls: \"none\" confirms no real person appears; \"person\" runs the protected pipeline (verified account, your own stored upload, Seedance 2.5/Mini lane, provider asset registration) — also pass person_rights_confirmed: true."

Changed1 schema field changedAug 13, 2026

addedInput schema / properties / video_people_declaration

Added value: +{
+  "description": "Required when reference_video_urls is used: \"none\" confirms no real person appears in the reference clips; \"person\" routes to the protected workflow (not yet supported through the connector).",
+  "enum": [
+    "none",
+    "person"
+  ],
+  "type": "string"
+}

Changed2 schema fields changedAug 13, 2026

changedInput schema / properties / reference_video_urls / description

Previous value: -"Seedance reference/omni only: up to 3 reference video clips for motion/style guidance. A Seedance video ref can satisfy the required visual anchor. NOTE: the AUDIO track of these clips is IGNORED — never extracted or preserved."New value: +"Seedance reference/omni only: reference video clips for motion/style guidance — up to 10 on Seedance 2.5 (clips 2-30s, 30s combined), up to 3 on Seedance 2.0 (see list_video_models for each model's caps). A Seedance video ref can satisfy the required visual anchor. NOTE: the AUDIO track of these clips is IGNORED — never extracted or preserved."

changedInput schema / properties / shots / items / properties / reference_video_urls / description

Previous value: -"Seedance reference/omni only: up to 3 reference video clips for motion/style guidance. A Seedance video ref can satisfy the required visual anchor. NOTE: the AUDIO track of these clips is IGNORED — never extracted or preserved."New value: +"Seedance reference/omni only: reference video clips for motion/style guidance — up to 10 on Seedance 2.5 (clips 2-30s, 30s combined), up to 3 on Seedance 2.0 (see list_video_models for each model's caps). A Seedance video ref can satisfy the required visual anchor. NOTE: the AUDIO track of these clips is IGNORED — never extracted or preserved."

Changed8 schema fields changedAug 12, 2026

changedInput schema / properties / audio / description

Previous value: -"Omni / Seedance refs: generate audio. Omni is ON by default; set false for a silent clip. Other models ignore this. See list_video_models for which models generate audio and the max seconds with vs without audio."New value: +"Generate audio. ON by default on Seedance 2.5 (text, image and reference) and on Omni; set false for a silent clip. Models without audio ignore this. See list_video_models for which models generate audio and the max seconds with vs without audio."

changedInput schema / properties / duration / description

Previous value: -"Clip length in seconds. Default 5. Seedance does 4-15s; Switch Video (WAN) does 5/10/15; Kling/Switch Video Edit cap at 10 — see each model's durations in list_video_models."New value: +"Clip length in seconds, or \"auto\" to let the model choose. Seedance 2.5 does 4-30s (auto bills the 30s cap up front and refunds the unused seconds); Seedance 2.0 does 4-15s; Switch Video (WAN) does 5/10/15; Kling/Switch Video Edit cap at 10 — see each model's durations in list_video_models."

changedInput schema / properties / resolution / description

Previous value: -"Output resolution. Defaults to 1080p where the model supports it. 720p is cheaper and faster. 480p is the cheapest, only on Seedance 2.0 Mini (budget tier). 4K is only on Kling v3 text/image and Kling Omni; Seedance text-to-video is 720p only. Each model lists its available resolutions in list_video_models."New value: +"Output resolution. Defaults to 1080p where the model supports it. 720p is cheaper and faster. 480p is the cheapest. Seedance 2.5 offers 480p and 720p only, on every mode. 4K is only on Kling v3 text/image and Kling Omni; Seedance text-to-video is 720p only. Each model lists its available resolutions in list_video_models."

changedInput schema / properties / shots / items / properties / audio / description

Previous value: -"Omni / Seedance refs: generate audio. Omni is ON by default; set false for a silent clip. Other models ignore this. See list_video_models for which models generate audio and the max seconds with vs without audio."New value: +"Generate audio. ON by default on Seedance 2.5 (text, image and reference) and on Omni; set false for a silent clip. Models without audio ignore this. See list_video_models for which models generate audio and the max seconds with vs without audio."

changedInput schema / properties / shots / items / properties / duration / description

Previous value: -"Clip length in seconds. Default 5. Seedance does 4-15s; Switch Video (WAN) does 5/10/15; Kling/Switch Video Edit cap at 10 — see each model's durations in list_video_models."New value: +"Clip length in seconds, or \"auto\" to let the model choose. Seedance 2.5 does 4-30s (auto bills the 30s cap up front and refunds the unused seconds); Seedance 2.0 does 4-15s; Switch Video (WAN) does 5/10/15; Kling/Switch Video Edit cap at 10 — see each model's durations in list_video_models."

changedInput schema / properties / shots / items / properties / resolution / description

Previous value: -"Output resolution. Defaults to 1080p where the model supports it. 720p is cheaper and faster. 480p is the cheapest, only on Seedance 2.0 Mini (budget tier). 4K is only on Kling v3 text/image and Kling Omni; Seedance text-to-video is 720p only. Each model lists its available resolutions in list_video_models."New value: +"Output resolution. Defaults to 1080p where the model supports it. 720p is cheaper and faster. 480p is the cheapest. Seedance 2.5 offers 480p and 720p only, on every mode. 4K is only on Kling v3 text/image and Kling Omni; Seedance text-to-video is 720p only. Each model lists its available resolutions in list_video_models."

addedInput schema / properties / shots / items / properties / task_type

Added value: +{
+  "description": "Seedance 2.5 reference mode only: declare what you are doing with the reference clip so the size and length rules are checked immediately instead of failing a minute in. auto = a new take from the references (default), edit = change something inside the clip, extend = continue the clip. Editing and extension inherit the source clip's size, and editing also inherits its length.",
+  "enum": [
+    "auto",
+    "edit",
+    "extend"
+  ],
+  "type": "string"
+}

addedInput schema / properties / task_type

Added value: +{
+  "description": "Seedance 2.5 reference mode only: declare what you are doing with the reference clip so the size and length rules are checked immediately instead of failing a minute in. auto = a new take from the references (default), edit = change something inside the clip, extend = continue the clip. Editing and extension inherit the source clip's size, and editing also inherits its length.",
+  "enum": [
+    "auto",
+    "edit",
+    "extend"
+  ],
+  "type": "string"
+}

Changed2 schema fields changedJul 26, 2026

changedInput schema / properties / shots / items / properties / video_url / description

Previous value: -"Required for video-edit and upscale (the source clip). Must be a publicly downloadable https URL."New value: +"Required for video-edit and upscale (the source clip). Accepts one of YOUR Switch videos — a job id from list_my_videos / get_video_status, or its download_url / view_url — or any publicly downloadable https URL. Switch resolves its own videos for you; no need to scrape a page for the file."

changedInput schema / properties / video_url / description

Previous value: -"Required for video-edit and upscale (the source clip). Must be a publicly downloadable https URL."New value: +"Required for video-edit and upscale (the source clip). Accepts one of YOUR Switch videos — a job id from list_my_videos / get_video_status, or its download_url / view_url — or any publicly downloadable https URL. Switch resolves its own videos for you; no need to scrape a page for the file."

Changed4 schema fields changedJul 15, 2026

addedInput schema / properties / face_reference_ids

Added value: +{
+  "description": "Face reference asset ids from upload_reference_asset (frame_type \"face\") — the ONLY way to use a face/likeness reference in video. Each id is verified server-side (your own untouched original + identity verification) before the shot fires or is charged; URLs and generic uploads here are rejected.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

changedInput schema / properties / reference_image_urls / description

Previous value: -"Reference images. Each entry accepts EITHER a Switch asset id (from show_media / list_my_assets / upload_media / get_my_active_references) OR a public https url — asset ids are resolved server-side. Seedance reference/omni accepts up to 9; Kling Omni up to 7. For Seedance, at least one image or video reference is required."New value: +"GENERIC reference images (products, scenery, outfits, style). Each entry accepts EITHER a Switch asset id (from show_media / list_my_assets / upload_media / get_my_active_references) OR a public https url — asset ids are resolved server-side. Seedance reference/omni accepts up to 9; Kling Omni up to 7. For Seedance, at least one image or video reference is required. For a person's face/likeness use face_reference_ids instead."

addedInput schema / properties / shots / items / properties / face_reference_ids

Added value: +{
+  "description": "Face reference asset ids from upload_reference_asset (frame_type \"face\") — the ONLY way to use a face/likeness reference in video. Each id is verified server-side (your own untouched original + identity verification) before the shot fires or is charged; URLs and generic uploads here are rejected.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

changedInput schema / properties / shots / items / properties / reference_image_urls / description

Previous value: -"Reference images. Each entry accepts EITHER a Switch asset id (from show_media / list_my_assets / upload_media / get_my_active_references) OR a public https url — asset ids are resolved server-side. Seedance reference/omni accepts up to 9; Kling Omni up to 7. For Seedance, at least one image or video reference is required."New value: +"GENERIC reference images (products, scenery, outfits, style). Each entry accepts EITHER a Switch asset id (from show_media / list_my_assets / upload_media / get_my_active_references) OR a public https url — asset ids are resolved server-side. Seedance reference/omni accepts up to 9; Kling Omni up to 7. For Seedance, at least one image or video reference is required. For a person's face/likeness use face_reference_ids instead."

Changed4 schema fields changedJun 25, 2026

changedInput schema / properties / resolution / description

Previous value: -"Output resolution. Defaults to 1080p where the model supports it. 720p is cheaper and faster. 4K is only on Kling v3 text/image and Kling Omni; Seedance text-to-video is 720p only. Each model lists its available resolutions in list_video_models."New value: +"Output resolution. Defaults to 1080p where the model supports it. 720p is cheaper and faster. 480p is the cheapest, only on Seedance 2.0 Mini (budget tier). 4K is only on Kling v3 text/image and Kling Omni; Seedance text-to-video is 720p only. Each model lists its available resolutions in list_video_models."

changedInput schema / properties / resolution / enum

Previous value: -[
-  "720p",
-  "1080p",
-  "4k"
-]New value: +[
+  "480p",
+  "720p",
+  "1080p",
+  "4k"
+]

changedInput schema / properties / shots / items / properties / resolution / description

Previous value: -"Output resolution. Defaults to 1080p where the model supports it. 720p is cheaper and faster. 4K is only on Kling v3 text/image and Kling Omni; Seedance text-to-video is 720p only. Each model lists its available resolutions in list_video_models."New value: +"Output resolution. Defaults to 1080p where the model supports it. 720p is cheaper and faster. 480p is the cheapest, only on Seedance 2.0 Mini (budget tier). 4K is only on Kling v3 text/image and Kling Omni; Seedance text-to-video is 720p only. Each model lists its available resolutions in list_video_models."

changedInput schema / properties / shots / items / properties / resolution / enum

Previous value: -[
-  "720p",
-  "1080p",
-  "4k"
-]New value: +[
+  "480p",
+  "720p",
+  "1080p",
+  "4k"
+]

Changed4 schema fields changedJun 14, 2026

changedInput schema / properties / image_url / description

Previous value: -"Required for image-to-video / frame-to-frame / motion. A storage-backed (Switch) image URL — use the url returned by upload_media (for a photo the user attached in chat) or by list_my_assets."New value: +"Required for image-to-video / frame-to-frame / motion. Accepts EITHER a Switch asset id (from show_media / list_my_assets / upload_media) OR a public https url. An asset id is resolved server-side, so just pass the id you have — no need to fetch a url first."

changedInput schema / properties / reference_image_urls / description

Previous value: -"Reference images. Seedance reference/omni accepts up to 9; Kling Omni accepts up to 7. For Seedance, at least one image or video reference is required. Use urls returned by upload_media (for photos the user attached in chat) or list_my_assets."New value: +"Reference images. Each entry accepts EITHER a Switch asset id (from show_media / list_my_assets / upload_media / get_my_active_references) OR a public https url — asset ids are resolved server-side. Seedance reference/omni accepts up to 9; Kling Omni up to 7. For Seedance, at least one image or video reference is required."

changedInput schema / properties / shots / items / properties / image_url / description

Previous value: -"Required for image-to-video / frame-to-frame / motion. A storage-backed (Switch) image URL — use the url returned by upload_media (for a photo the user attached in chat) or by list_my_assets."New value: +"Required for image-to-video / frame-to-frame / motion. Accepts EITHER a Switch asset id (from show_media / list_my_assets / upload_media) OR a public https url. An asset id is resolved server-side, so just pass the id you have — no need to fetch a url first."

changedInput schema / properties / shots / items / properties / reference_image_urls / description

Previous value: -"Reference images. Seedance reference/omni accepts up to 9; Kling Omni accepts up to 7. For Seedance, at least one image or video reference is required. Use urls returned by upload_media (for photos the user attached in chat) or list_my_assets."New value: +"Reference images. Each entry accepts EITHER a Switch asset id (from show_media / list_my_assets / upload_media / get_my_active_references) OR a public https url — asset ids are resolved server-side. Seedance reference/omni accepts up to 9; Kling Omni up to 7. For Seedance, at least one image or video reference is required."

Changed10 schema fields changedJun 14, 2026

changedInput schema / properties / duration / description

Previous value: -"Clip length in seconds. Default 5. 15s only on Switch Video (WAN); other models cap at 10 — see list_video_models."New value: +"Clip length in seconds. Default 5. Seedance does 4-15s; Switch Video (WAN) does 5/10/15; Kling/Switch Video Edit cap at 10 — see each model's durations in list_video_models."

removedInput schema / properties / duration / enum
```
Removed value: -[
-  "5",
-  "10",
-  "15"
-]
```

changedInput schema / properties / image_url / description

Previous value: -"Required for image-to-video / frame-to-frame / motion. A storage-backed (Switch) image URL."New value: +"Required for image-to-video / frame-to-frame / motion. A storage-backed (Switch) image URL — use the url returned by upload_media (for a photo the user attached in chat) or by list_my_assets."

changedInput schema / properties / reference_image_urls / description

Previous value: -"Reference images. Seedance reference/omni accepts up to 9; Kling Omni accepts up to 7. For Seedance, at least one image or video reference is required."New value: +"Reference images. Seedance reference/omni accepts up to 9; Kling Omni accepts up to 7. For Seedance, at least one image or video reference is required. Use urls returned by upload_media (for photos the user attached in chat) or list_my_assets."

addedInput schema / properties / resolution

Added value: +{
+  "description": "Output resolution. Defaults to 1080p where the model supports it. 720p is cheaper and faster. 4K is only on Kling v3 text/image and Kling Omni; Seedance text-to-video is 720p only. Each model lists its available resolutions in list_video_models.",
+  "enum": [
+    "720p",
+    "1080p",
+    "4k"
+  ],
+  "type": "string"
+}

changedInput schema / properties / shots / items / properties / duration / description

Previous value: -"Clip length in seconds. Default 5. 15s only on Switch Video (WAN); other models cap at 10 — see list_video_models."New value: +"Clip length in seconds. Default 5. Seedance does 4-15s; Switch Video (WAN) does 5/10/15; Kling/Switch Video Edit cap at 10 — see each model's durations in list_video_models."

removedInput schema / properties / shots / items / properties / duration / enum
```
Removed value: -[
-  "5",
-  "10",
-  "15"
-]
```

changedInput schema / properties / shots / items / properties / image_url / description

Previous value: -"Required for image-to-video / frame-to-frame / motion. A storage-backed (Switch) image URL."New value: +"Required for image-to-video / frame-to-frame / motion. A storage-backed (Switch) image URL — use the url returned by upload_media (for a photo the user attached in chat) or by list_my_assets."

changedInput schema / properties / shots / items / properties / reference_image_urls / description

Previous value: -"Reference images. Seedance reference/omni accepts up to 9; Kling Omni accepts up to 7. For Seedance, at least one image or video reference is required."New value: +"Reference images. Seedance reference/omni accepts up to 9; Kling Omni accepts up to 7. For Seedance, at least one image or video reference is required. Use urls returned by upload_media (for photos the user attached in chat) or list_my_assets."

addedInput schema / properties / shots / items / properties / resolution

Added value: +{
+  "description": "Output resolution. Defaults to 1080p where the model supports it. 720p is cheaper and faster. 4K is only on Kling v3 text/image and Kling Omni; Seedance text-to-video is 720p only. Each model lists its available resolutions in list_video_models.",
+  "enum": [
+    "720p",
+    "1080p",
+    "4k"
+  ],
+  "type": "string"
+}

Changed4 schema fields changedJun 12, 2026

changedInput schema / properties / reference_image_urls / description

Previous value: -"Required for reference-to-video / Seedance omni (1-9 image URLs)."New value: +"Reference images. Seedance reference/omni accepts up to 9; Kling Omni accepts up to 7. For Seedance, at least one image or video reference is required."

changedInput schema / properties / reference_video_urls / description

Previous value: -"Seedance reference/omni only: up to 3 reference video clips for motion/style guidance. NOTE: the AUDIO track of these clips is IGNORED — never extracted or preserved (see list_video_models)."New value: +"Seedance reference/omni only: up to 3 reference video clips for motion/style guidance. A Seedance video ref can satisfy the required visual anchor. NOTE: the AUDIO track of these clips is IGNORED — never extracted or preserved."

changedInput schema / properties / shots / items / properties / reference_image_urls / description

Previous value: -"Required for reference-to-video / Seedance omni (1-9 image URLs)."New value: +"Reference images. Seedance reference/omni accepts up to 9; Kling Omni accepts up to 7. For Seedance, at least one image or video reference is required."

changedInput schema / properties / shots / items / properties / reference_video_urls / description

Previous value: -"Seedance reference/omni only: up to 3 reference video clips for motion/style guidance. NOTE: the AUDIO track of these clips is IGNORED — never extracted or preserved (see list_video_models)."New value: +"Seedance reference/omni only: up to 3 reference video clips for motion/style guidance. A Seedance video ref can satisfy the required visual anchor. NOTE: the AUDIO track of these clips is IGNORED — never extracted or preserved."

First observedJun 5, 2026

TDQS

A4.7/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations only carry readOnlyHint=false, so the description carries the full burden — and it delivers: async rendering timing ('Renders async (~30-90s); a background job delivers each clip to your library'), return shape ('Returns a task_id per shot — poll get_video_status or list_my_videos'), reference-preservation invariants ('never silently drop, merge, reorder, convert, or repurpose references'), the shot-distinctness rule, and the automatic enhancement pipeline. This is exactly the behavioral context an agent needs beyond the schema and exceeds what annotations provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long, but the tool is genuinely complex (23 params, 8 modes, 6 providers), and every sentence carries distinct operational value: scope, workflow loading, model selection, enhancement, quoting, channel restrictions, provider preference, reference integrity, shot limits, and async behavior. The front-loaded purpose sentence is followed by a logical flow of actionable directives with no repetition or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no output schema, the description compensates fully: it explains return values (task_id per shot), polling mechanism, pricing workflow, enhancement flow, storyboard limits (max 4 default, hard max 10), conditional per-modal requirements, and provider-specific guidance. Model-specific caps are deferred to list_video_models, which is the correct division of labor. Nothing an agent needs to call this correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema fully documents all 23 parameters — per the rubric, the baseline is 3 even with no param info in the description. The description does add cross-parameter workflow semantics (quote enforcement via quote_fingerprint, enhancement_receipt reuse, storyboard shot limits), which is valuable, but it does not add per-parameter meaning beyond what the schema already states.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb, resource, and exhaustive scope: 'Generate Switch video across the real provider lineup (Kling, BytePlus Seedance, Switch Video/WAN 2.7, Switch Video Edit, Topaz upscale) and modes (text-to-video, image-to-video, frame-to-frame, motion, omni, reference-to-video, video-edit, upscale).' This clearly distinguishes it from siblings like generate_image, generate_audio, and upscale_video, which are separate resources.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit when-to-use and routing guidance is abundant: 'Load load_video_workflow once per conversation when needed,' 'use list_video_models only when the selection or its inputs are unknown,' 'call enhance_video_prompt first,' 'Use quote_video for the exact current token price,' 'never open the website, browser, or desktop unless the user explicitly asked,' and 'evaluate BytePlus Seedance 2.5 first' for reference-driven video. Each directive names the sibling tool and the condition that selects it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All switch tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?