Added value: +{
+  "description": "Optional. The brand kit to send with this video, by name or id, or \"none\". Leave out to use the kit chosen in Switch Agent settings (or the default kit).",
+  "type": "string"
+}

Previous 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."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. WAN 3.0 reference (wan30-reference) takes up to 5 audio files totaling 15 seconds, a song or a voice the subject performs to, addressed as Audio 1, Audio 2 in the prompt."

Previous 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."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. WAN 3.0 reference (wan30-reference) takes up to 5 audio files totaling 15 seconds, a song or a voice the subject performs to, addressed as Audio 1, Audio 2 in the prompt."

Previous value: -"HeyGen Video ids: heygen-video-t2v, heygen-video-i2v, heygen-video-r2v (option ids heygen-text / heygen-image / heygen-reference; 5-15 s, 480p/768p/2K, sound on every clip). 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 option): 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, the image option takes image_url and an optional end_image_url, the reference option takes up to 10 reference_image_urls and 5 reference_video_urls. Switch Cinema (option ids switch-cinema-480p / switch-cinema-720p, model switch-cinema-motion): remakes the clip in reference_video_urls with the person in 1 to 8 reference_image_urls, keeps the clip's motion, no duration setting, priced per second of the clip you attach (8 tokens at 480p, 17 at 720p)."New value: +"HeyGen Video ids: heygen-video-t2v, heygen-video-i2v, heygen-video-r2v (option ids heygen-text / heygen-image / heygen-reference; 5-15 s, 480p/768p/2K, sound on every clip). 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 option): 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, the image option takes image_url and an optional end_image_url, the reference option takes up to 10 reference_image_urls and 5 reference_video_urls. Higgsfield Genjutsu (option ids switch-cinema-480p / switch-cinema-720p, model switch-cinema-motion): remakes the clip in reference_video_urls with the person in 1 to 8 reference_image_urls, keeps the clip's motion, no duration setting, priced per second of the clip you attach (8 tokens at 480p, 17 at 720p)."

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. 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. Pictures of real people go here too, as they are: Switch checks every picture and sends a face through the protected face path automatically, in its own place (same order, same @Image numbers); on Seedance, only an account without identity verification is refused. Switch Cinema (switch-cinema-480p / switch-cinema-720p): 1 to 8 pictures of the person to put into the clip, 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. 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. Pictures of real people go here too, as they are: Switch checks every picture and sends a face through the protected face path automatically, in its own place (same order, same @Image numbers); on Seedance, only an account without identity verification is refused. Higgsfield Genjutsu (switch-cinema-480p / switch-cinema-720p): 1 to 8 pictures of the person to put into the clip, required."

Previous 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). Gemini Omni 1.1 Flash (gemini-omni-reference, gemini-omni-image): up to 3 clips of up to 3 seconds each, used as character or object references (their sound is ignored), named @Video1, @Video2 in the prompt in list order; a longer clip is refused before any charge. Switch Cinema (switch-cinema-480p / switch-cinema-720p): exactly one clip, the one whose motion is kept; the result is as long as this clip and its seconds are the whole price."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). Gemini Omni 1.1 Flash (gemini-omni-reference, gemini-omni-image): up to 3 clips of up to 3 seconds each, used as character or object references (their sound is ignored), named @Video1, @Video2 in the prompt in list order; a longer clip is refused before any charge. Higgsfield Genjutsu (switch-cinema-480p / switch-cinema-720p): exactly one clip, the one whose motion is kept; the result is as long as this clip and its seconds are the whole price."

Previous value: -"HeyGen Video ids: heygen-video-t2v, heygen-video-i2v, heygen-video-r2v (option ids heygen-text / heygen-image / heygen-reference; 5-15 s, 480p/768p/2K, sound on every clip). 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 option): 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, the image option takes image_url and an optional end_image_url, the reference option takes up to 10 reference_image_urls and 5 reference_video_urls. Switch Cinema (option ids switch-cinema-480p / switch-cinema-720p, model switch-cinema-motion): remakes the clip in reference_video_urls with the person in 1 to 8 reference_image_urls, keeps the clip's motion, no duration setting, priced per second of the clip you attach (8 tokens at 480p, 17 at 720p)."New value: +"HeyGen Video ids: heygen-video-t2v, heygen-video-i2v, heygen-video-r2v (option ids heygen-text / heygen-image / heygen-reference; 5-15 s, 480p/768p/2K, sound on every clip). 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 option): 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, the image option takes image_url and an optional end_image_url, the reference option takes up to 10 reference_image_urls and 5 reference_video_urls. Higgsfield Genjutsu (option ids switch-cinema-480p / switch-cinema-720p, model switch-cinema-motion): remakes the clip in reference_video_urls with the person in 1 to 8 reference_image_urls, keeps the clip's motion, no duration setting, priced per second of the clip you attach (8 tokens at 480p, 17 at 720p)."

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. 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. Pictures of real people go here too, as they are: Switch checks every picture and sends a face through the protected face path automatically, in its own place (same order, same @Image numbers); on Seedance, only an account without identity verification is refused. Switch Cinema (switch-cinema-480p / switch-cinema-720p): 1 to 8 pictures of the person to put into the clip, 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. 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. Pictures of real people go here too, as they are: Switch checks every picture and sends a face through the protected face path automatically, in its own place (same order, same @Image numbers); on Seedance, only an account without identity verification is refused. Higgsfield Genjutsu (switch-cinema-480p / switch-cinema-720p): 1 to 8 pictures of the person to put into the clip, required."

Previous 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). Gemini Omni 1.1 Flash (gemini-omni-reference, gemini-omni-image): up to 3 clips of up to 3 seconds each, used as character or object references (their sound is ignored), named @Video1, @Video2 in the prompt in list order; a longer clip is refused before any charge. Switch Cinema (switch-cinema-480p / switch-cinema-720p): exactly one clip, the one whose motion is kept; the result is as long as this clip and its seconds are the whole price."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). Gemini Omni 1.1 Flash (gemini-omni-reference, gemini-omni-image): up to 3 clips of up to 3 seconds each, used as character or object references (their sound is ignored), named @Video1, @Video2 in the prompt in list order; a longer clip is refused before any charge. Higgsfield Genjutsu (switch-cinema-480p / switch-cinema-720p): exactly one clip, the one whose motion is kept; the result is as long as this clip and its seconds are the whole price."

Added value: +{
+  "description": "Switch Agent: true only when the person named this video's resolution themselves (\"make it in 1080p\"); a Seedance 2.5 video then starts at that resolution instead of its Draft. Leave it off otherwise: every Seedance 2.5 video starts as a Draft.",
+  "type": "boolean"
+}

Added value: +{
+  "description": "Switch Agent: true only when the person named this video's resolution themselves (\"make it in 1080p\"); a Seedance 2.5 video then starts at that resolution instead of its Draft. Leave it off otherwise: every Seedance 2.5 video starts as a Draft.",
+  "type": "boolean"
+}

Added value: +{
+  "description": "True when the person wrote this prompt themselves and is using it as their prompt (\"I'm doing the prompt\"): it goes exactly as written, never enhanced. Leave it off when you write the prompt, or when the person asks you to make it or fix it: then SwitchApp Video Enhanced runs.",
+  "type": "boolean"
+}

Added value: +{
+  "description": "True when the person wrote this prompt themselves and is using it as their prompt (\"I'm doing the prompt\"): it goes exactly as written, never enhanced. Leave it off when you write the prompt, or when the person asks you to make it or fix it: then SwitchApp Video Enhanced runs.",
+  "type": "boolean"
+}

Added value: +{
+  "description": "When the person asks for several of the same video (\"4 of them\"), number each call 1, 2, 3 ... so every take is made; the same take number twice in ten minutes is the same request and makes one video. Leave out for a single video.",
+  "minimum": 1,
+  "type": "integer"
+}

Added value: +{
+  "description": "When the person asks for several of the same video (\"4 of them\"), number each call 1, 2, 3 ... so every take is made; the same take number twice in ten minutes is the same request and makes one video. Leave out for a single video.",
+  "minimum": 1,
+  "type": "integer"
+}

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. 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. Pictures of real people go here too, as they are: Switch checks every picture and sends a face through the protected face path automatically, in its own place (same order, same @Image numbers); only an account without identity verification is refused. Switch Cinema (switch-cinema-480p / switch-cinema-720p): 1 to 8 pictures of the person to put into the clip, 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. 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. Pictures of real people go here too, as they are: Switch checks every picture and sends a face through the protected face path automatically, in its own place (same order, same @Image numbers); on Seedance, only an account without identity verification is refused. Switch Cinema (switch-cinema-480p / switch-cinema-720p): 1 to 8 pictures of the person to put into the clip, required."

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. 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. Pictures of real people go here too, as they are: Switch checks every picture and sends a face through the protected face path automatically, in its own place (same order, same @Image numbers); only an account without identity verification is refused. Switch Cinema (switch-cinema-480p / switch-cinema-720p): 1 to 8 pictures of the person to put into the clip, 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. 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. Pictures of real people go here too, as they are: Switch checks every picture and sends a face through the protected face path automatically, in its own place (same order, same @Image numbers); on Seedance, only an account without identity verification is refused. Switch Cinema (switch-cinema-480p / switch-cinema-720p): 1 to 8 pictures of the person to put into the clip, required."

Previous value: -"Required with video_people_declaration \"person\": confirms you own or are authorized to use the person's likeness in the reference video."New value: +"Optional and not needed; kept so older apps that send it still work."

Previous 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 or Mini, provider asset registration) — also pass person_rights_confirmed: true."New value: +"Optional and not needed: every video maker takes clips with real people; Seedance asks for a verified account, every other model takes them as its own API allows."

Previous value: -"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."New value: +"Optional, kept for apps that already use it: asset ids from upload_reference_asset. Not needed for faces; put every picture in reference_image_urls and Switch handles faces itself. Each id here runs the same protected face path (your own untouched original + identity verification) before the shot fires or is charged."

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. 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. Switch Cinema (switch-cinema-480p / switch-cinema-720p): 1 to 8 pictures of the person to put into the clip, 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. 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. Pictures of real people go here too, as they are: Switch checks every picture and sends a face through the protected face path automatically, in its own place (same order, same @Image numbers); only an account without identity verification is refused. Switch Cinema (switch-cinema-480p / switch-cinema-720p): 1 to 8 pictures of the person to put into the clip, required."

Previous value: -"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."New value: +"Optional, kept for apps that already use it: asset ids from upload_reference_asset. Not needed for faces; put every picture in reference_image_urls and Switch handles faces itself. Each id here runs the same protected face path (your own untouched original + identity verification) before the shot fires or is charged."

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. 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. Switch Cinema (switch-cinema-480p / switch-cinema-720p): 1 to 8 pictures of the person to put into the clip, 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. 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. Pictures of real people go here too, as they are: Switch checks every picture and sends a face through the protected face path automatically, in its own place (same order, same @Image numbers); only an account without identity verification is refused. Switch Cinema (switch-cinema-480p / switch-cinema-720p): 1 to 8 pictures of the person to put into the clip, required."

Previous 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). Switch Cinema (switch-cinema-480p / switch-cinema-720p): exactly one clip, the one whose motion is kept; the result is as long as this clip and its seconds are the whole price."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). Gemini Omni 1.1 Flash (gemini-omni-reference, gemini-omni-image): up to 3 clips of up to 3 seconds each, used as character or object references (their sound is ignored), named @Video1, @Video2 in the prompt in list order; a longer clip is refused before any charge. Switch Cinema (switch-cinema-480p / switch-cinema-720p): exactly one clip, the one whose motion is kept; the result is as long as this clip and its seconds are the whole price."

Previous 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). Switch Cinema (switch-cinema-480p / switch-cinema-720p): exactly one clip, the one whose motion is kept; the result is as long as this clip and its seconds are the whole price."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). Gemini Omni 1.1 Flash (gemini-omni-reference, gemini-omni-image): up to 3 clips of up to 3 seconds each, used as character or object references (their sound is ignored), named @Video1, @Video2 in the prompt in list order; a longer clip is refused before any charge. Switch Cinema (switch-cinema-480p / switch-cinema-720p): exactly one clip, the one whose motion is kept; the result is as long as this clip and its seconds are the whole price."

Previous value: -"Generate sound. ON by default on every video maker that can make sound (Seedance 2.5 and 2.0 on every lane, Kling Omni and Turbo, every WAN 3.0 lane, MiniMax H3 Max). Set false for a silent clip. Models without sound ignore this. See list_video_models for the max seconds with and without sound."New value: +"Generate sound. ON by default on every video maker that can make sound (Seedance 2.5 and 2.0 in every mode, Kling Omni and Turbo, every WAN 3.0 option, MiniMax H3 Max). Set false for a silent clip. Models without sound ignore this. See list_video_models for the max seconds with and without sound."

Previous value: -"HeyGen Video ids: heygen-video-t2v, heygen-video-i2v, heygen-video-r2v (option ids heygen-text / heygen-image / heygen-reference; 5-15 s, 480p/768p/2K, sound on every clip). 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. Switch Cinema (option ids switch-cinema-480p / switch-cinema-720p, model switch-cinema-motion): remakes the clip in reference_video_urls with the person in 1 to 8 reference_image_urls, keeps the clip's motion, no duration setting, priced per second of the clip you attach (8 tokens at 480p, 17 at 720p)."New value: +"HeyGen Video ids: heygen-video-t2v, heygen-video-i2v, heygen-video-r2v (option ids heygen-text / heygen-image / heygen-reference; 5-15 s, 480p/768p/2K, sound on every clip). 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 option): 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, the image option takes image_url and an optional end_image_url, the reference option takes up to 10 reference_image_urls and 5 reference_video_urls. Switch Cinema (option ids switch-cinema-480p / switch-cinema-720p, model switch-cinema-motion): remakes the clip in reference_video_urls with the person in 1 to 8 reference_image_urls, keeps the clip's motion, no duration setting, priced per second of the clip you attach (8 tokens at 480p, 17 at 720p)."

Previous value: -"HeyGen Video offers 480p, 768p and 2k (2k in 16:9 or 9:16 only, three times the 768p price). 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."New value: +"HeyGen Video offers 480p, 768p and 2k (2k in 16:9 or 9:16 only, three times the 768p price). 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 option is 768p only). Each model lists its available resolutions in list_video_models."

Previous value: -"Generate sound. ON by default on every video maker that can make sound (Seedance 2.5 and 2.0 on every lane, Kling Omni and Turbo, every WAN 3.0 lane, MiniMax H3 Max). Set false for a silent clip. Models without sound ignore this. See list_video_models for the max seconds with and without sound."New value: +"Generate sound. ON by default on every video maker that can make sound (Seedance 2.5 and 2.0 in every mode, Kling Omni and Turbo, every WAN 3.0 option, MiniMax H3 Max). Set false for a silent clip. Models without sound ignore this. See list_video_models for the max seconds with and without sound."

Previous value: -"HeyGen Video ids: heygen-video-t2v, heygen-video-i2v, heygen-video-r2v (option ids heygen-text / heygen-image / heygen-reference; 5-15 s, 480p/768p/2K, sound on every clip). 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. Switch Cinema (option ids switch-cinema-480p / switch-cinema-720p, model switch-cinema-motion): remakes the clip in reference_video_urls with the person in 1 to 8 reference_image_urls, keeps the clip's motion, no duration setting, priced per second of the clip you attach (8 tokens at 480p, 17 at 720p)."New value: +"HeyGen Video ids: heygen-video-t2v, heygen-video-i2v, heygen-video-r2v (option ids heygen-text / heygen-image / heygen-reference; 5-15 s, 480p/768p/2K, sound on every clip). 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 option): 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, the image option takes image_url and an optional end_image_url, the reference option takes up to 10 reference_image_urls and 5 reference_video_urls. Switch Cinema (option ids switch-cinema-480p / switch-cinema-720p, model switch-cinema-motion): remakes the clip in reference_video_urls with the person in 1 to 8 reference_image_urls, keeps the clip's motion, no duration setting, priced per second of the clip you attach (8 tokens at 480p, 17 at 720p)."

Previous value: -"HeyGen Video offers 480p, 768p and 2k (2k in 16:9 or 9:16 only, three times the 768p price). 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."New value: +"HeyGen Video offers 480p, 768p and 2k (2k in 16:9 or 9:16 only, three times the 768p price). 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 option is 768p only). Each model lists its available resolutions in list_video_models."

Previous 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."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 or Mini, provider asset registration) — also pass person_rights_confirmed: true."

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). 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. Switch Cinema (option ids switch-cinema-480p / switch-cinema-720p, model switch-cinema-motion): remakes the clip in reference_video_urls with the person in 1 to 8 reference_image_urls, keeps the clip's motion, no duration setting, priced per second of the clip you attach (8 tokens at 480p, 17 at 720p)."New value: +"HeyGen Video ids: heygen-video-t2v, heygen-video-i2v, heygen-video-r2v (option ids heygen-text / heygen-image / heygen-reference; 5-15 s, 480p/768p/2K, sound on every clip). 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. Switch Cinema (option ids switch-cinema-480p / switch-cinema-720p, model switch-cinema-motion): remakes the clip in reference_video_urls with the person in 1 to 8 reference_image_urls, keeps the clip's motion, no duration setting, priced per second of the clip you attach (8 tokens at 480p, 17 at 720p)."

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. MiniMax H3 Max offers 480p and 768p only (its reference lane is 768p only). Each model lists its available resolutions in list_video_models."New value: +"HeyGen Video offers 480p, 768p and 2k (2k in 16:9 or 9:16 only, three times the 768p price). 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."

Previous value: -[
-  "480p",
-  "720p",
-  "768p",
-  "1080p",
-  "4k"
-]New value: +[
+  "480p",
+  "720p",
+  "768p",
+  "1080p",
+  "2k",
+  "4k"
+]

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). 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. Switch Cinema (option ids switch-cinema-480p / switch-cinema-720p, model switch-cinema-motion): remakes the clip in reference_video_urls with the person in 1 to 8 reference_image_urls, keeps the clip's motion, no duration setting, priced per second of the clip you attach (8 tokens at 480p, 17 at 720p)."New value: +"HeyGen Video ids: heygen-video-t2v, heygen-video-i2v, heygen-video-r2v (option ids heygen-text / heygen-image / heygen-reference; 5-15 s, 480p/768p/2K, sound on every clip). 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. Switch Cinema (option ids switch-cinema-480p / switch-cinema-720p, model switch-cinema-motion): remakes the clip in reference_video_urls with the person in 1 to 8 reference_image_urls, keeps the clip's motion, no duration setting, priced per second of the clip you attach (8 tokens at 480p, 17 at 720p)."

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. MiniMax H3 Max offers 480p and 768p only (its reference lane is 768p only). Each model lists its available resolutions in list_video_models."New value: +"HeyGen Video offers 480p, 768p and 2k (2k in 16:9 or 9:16 only, three times the 768p price). 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."

Previous value: -[
-  "480p",
-  "720p",
-  "768p",
-  "1080p",
-  "4k"
-]New value: +[
+  "480p",
+  "720p",
+  "768p",
+  "1080p",
+  "2k",
+  "4k"
+]

Previous 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."New value: +"Generate sound. ON by default on every video maker that can make sound (Seedance 2.5 and 2.0 on every lane, Kling Omni and Turbo, every WAN 3.0 lane, MiniMax H3 Max). Set false for a silent clip. Models without sound ignore this. See list_video_models for the max seconds with and without sound."

Previous 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."New value: +"Generate sound. ON by default on every video maker that can make sound (Seedance 2.5 and 2.0 on every lane, Kling Omni and Turbo, every WAN 3.0 lane, MiniMax H3 Max). Set false for a silent clip. Models without sound ignore this. See list_video_models for the max seconds with and without sound."

Previous 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)."New value: +"The shot: subject + motion + scene (video needs motion language, e.g. \"slow push-in\"). Name the creator's staged Studio references as @Image1, @Video1 (the Video tab strip, then the image strip; see get_my_active_references) and they attach automatically; nothing attaches unless named. 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)."

Previous 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)."New value: +"The shot: subject + motion + scene (video needs motion language, e.g. \"slow push-in\"). Name the creator's staged Studio references as @Image1, @Video1 (the Video tab strip, then the image strip; see get_my_active_references) and they attach automatically; nothing attaches unless named. 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)."

Previous value: -"Optional catalog id from list_video_models (e.g. \"kling-image\"); use instead of model+mode."New value: +"Catalog id from list_video_models. Native Seedance Draft: seedance-25-draft-text, seedance-25-draft-image, seedance-25-draft-reference (480p with audio). Make Full HD: seedance-25-draft-final with the completed draft job_id in video_url, no new creative settings. Quote then generate within 7 days."

Previous value: -"Optional catalog id from list_video_models (e.g. \"kling-image\"); use instead of model+mode."New value: +"Catalog id from list_video_models. Native Seedance Draft: seedance-25-draft-text, seedance-25-draft-image, seedance-25-draft-reference (480p with audio). Make Full HD: seedance-25-draft-final with the completed draft job_id in video_url, no new creative settings. Quote then generate within 7 days."

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). 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."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. Switch Cinema (option ids switch-cinema-480p / switch-cinema-720p, model switch-cinema-motion): remakes the clip in reference_video_urls with the person in 1 to 8 reference_image_urls, keeps the clip's motion, no duration setting, priced per second of the clip you attach (8 tokens at 480p, 17 at 720p)."

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. 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."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. Switch Cinema (switch-cinema-480p / switch-cinema-720p): 1 to 8 pictures of the person to put into the clip, required."

Previous 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)."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). Switch Cinema (switch-cinema-480p / switch-cinema-720p): exactly one clip, the one whose motion is kept; the result is as long as this clip and its seconds are the whole price."

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). 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."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. Switch Cinema (option ids switch-cinema-480p / switch-cinema-720p, model switch-cinema-motion): remakes the clip in reference_video_urls with the person in 1 to 8 reference_image_urls, keeps the clip's motion, no duration setting, priced per second of the clip you attach (8 tokens at 480p, 17 at 720p)."

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. 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."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. Switch Cinema (switch-cinema-480p / switch-cinema-720p): 1 to 8 pictures of the person to put into the clip, required."

Previous 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)."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). Switch Cinema (switch-cinema-480p / switch-cinema-720p): exactly one clip, the one whose motion is kept; the result is as long as this clip and its seconds are the whole price."

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"
+}

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

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

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"
+}

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

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

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."

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."

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."

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."

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."

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."

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)."

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."

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."

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."

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."

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)."

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)."

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)."

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."

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)."

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."

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)."

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."

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

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."

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)."

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."

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)."

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."

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

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."

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."

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"
+}

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."

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"
+}

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."

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."

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."

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."

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."

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."

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."

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."

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"
+}

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"
+}

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."

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."

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"
+}

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."

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"
+}

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."

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."

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

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."

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

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."

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."

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."

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."

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."

Removed value: -[
-  "5",
-  "10",
-  "15"
-]

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."

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."

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"
+}

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."

Removed value: -[
-  "5",
-  "10",
-  "15"
-]

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."

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."

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"
+}

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."

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."

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."

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."