{"models":[{"model_id":"5-lite-image-to-image","display_name":"Seedream 5 Lite","model_type":"image","provider":"ByteDance","cost_per_generation":12.0,"estimated_time_seconds":53,"capabilities":{"prompt_max_chars":2995,"duration_options":[],"quality_options":["basic","high"],"aspect_ratio_options":["1:1","4:3","3:4","16:9","9:16","3:2","2:3","21:9"],"max_input_images":10,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false},"requires_input_media":true,"input_media_types":["image"],"generation_types":["image-to-image"],"usage_notes":"Image-to-image only. Require source_media_urls (up to 10 image URLs). Set generation_type='image-to-image'. quality: 'basic' (default, 2K) or 'high' (4K output)."},{"model_id":"5-lite-text-to-image","display_name":"Seedream 5 Lite","model_type":"image","provider":"ByteDance","cost_per_generation":12.0,"estimated_time_seconds":52,"capabilities":{"prompt_max_chars":2995,"duration_options":[],"quality_options":["basic","high"],"aspect_ratio_options":["1:1","4:3","3:4","16:9","9:16","3:2","2:3","21:9"],"max_input_images":10,"input_media_types":[],"supports_negative_prompt":false,"supports_sound":false},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-image","image-to-image"],"usage_notes":"Text-to-image: omit source_media_urls. Image-to-image: pass source_media_urls (up to 10). Prompt max 2995 chars. quality: 'basic' (default, 2K) or 'high' (4K output). aspect_ratio e.g. 1:1, 9:16, 16:9."},{"model_id":"flux-2-1K","display_name":"Flux 2 1K","model_type":"image","provider":"Black Forest Labs","cost_per_generation":10.0,"estimated_time_seconds":25,"capabilities":{"prompt_max_chars":5000,"duration_options":[],"aspect_ratio_options":["1:1","4:3","3:4","16:9","9:16","3:2","2:3","auto"],"max_input_images":0,"input_media_types":[],"supports_negative_prompt":false,"supports_sound":false},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-image"],"usage_notes":"Use when you need identity preservation across a series. Base id defaults to 1K resolution — pick flux-2-1K or flux-2-2K variants for explicit resolution. Text-to-image only; do not pass source_media_urls."},{"model_id":"flux-2-2K","display_name":"Flux 2 2K","model_type":"image","provider":"Black Forest Labs","cost_per_generation":13.0,"estimated_time_seconds":151,"capabilities":{"prompt_max_chars":5000,"duration_options":[],"aspect_ratio_options":["1:1","4:3","3:4","16:9","9:16","3:2","2:3","auto"],"max_input_images":0,"input_media_types":[],"supports_negative_prompt":false,"supports_sound":false},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-image"],"usage_notes":"Same usage notes as 'flux-2-1K'."},{"model_id":"flux-2-edit-1K","display_name":"Flux 2 Edit 1K","model_type":"image","provider":"Black Forest Labs","cost_per_generation":10.0,"estimated_time_seconds":30,"capabilities":{"prompt_max_chars":5000,"duration_options":[],"aspect_ratio_options":["1:1","4:3","3:4","16:9","9:16","3:2","2:3","auto"],"max_input_images":8,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false},"requires_input_media":true,"input_media_types":["image"],"generation_types":["image-to-image"],"usage_notes":"Base id defaults to 1K resolution — use flux-2-edit-1K or flux-2-edit-2K variants for explicit output resolution (2K for higher detail). Image-to-image only: requires source_media_urls with 1–8 image URLs. Set generation_type='image-to-image'."},{"model_id":"flux-2-edit-2K","display_name":"Flux 2 Edit 2K","model_type":"image","provider":"Black Forest Labs","cost_per_generation":13.0,"estimated_time_seconds":30,"capabilities":{"prompt_max_chars":5000,"duration_options":[],"aspect_ratio_options":["1:1","4:3","3:4","16:9","9:16","3:2","2:3","auto"],"max_input_images":8,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false},"requires_input_media":true,"input_media_types":["image"],"generation_types":["image-to-image"],"usage_notes":"Same usage notes as 'flux-2-edit-1K'."},{"model_id":"gpt-1.5-image-high","display_name":"GPT 1.5 Image High Quality","model_type":"image","provider":"OpenAI","cost_per_generation":32.0,"estimated_time_seconds":30,"capabilities":{"prompt_max_chars":3000,"duration_options":[],"aspect_ratio_options":["1:1","2:3","3:2"],"max_input_images":16,"input_media_types":[],"supports_negative_prompt":false,"supports_sound":false},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-image","image-to-image"],"usage_notes":"Expensive per image. Text-to-image: omit source_media_urls. Image-to-image: pass source_media_urls (up to 16 images). Prompt max 3000 chars. quality: medium or high. Aspect ratios: ONLY 1:1, 2:3, 3:2 — this family does NOT accept 16:9 or 9:16."},{"model_id":"gpt-1.5-image-medium","display_name":"GPT 1.5 Image Medium Quality","model_type":"image","provider":"OpenAI","cost_per_generation":10.0,"estimated_time_seconds":30,"capabilities":{"prompt_max_chars":3000,"duration_options":[],"aspect_ratio_options":["1:1","2:3","3:2"],"max_input_images":16,"input_media_types":[],"supports_negative_prompt":false,"supports_sound":false},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-image","image-to-image"],"usage_notes":"Same usage notes as 'gpt-1.5-image-high'."},{"model_id":"gpt-image-2","display_name":"GPT Image 2","model_type":"image","provider":"OpenAI","cost_per_generation":11.0,"estimated_time_seconds":100,"capabilities":{"prompt_max_chars":20000,"duration_options":[],"aspect_ratio_options":["auto","1:1","9:16","16:9","4:3","3:4"],"resolution_options":["1K","2K","4K"],"max_input_images":16,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false},"requires_input_media":false,"input_media_types":["image"],"generation_types":["text-to-image","image-to-image"],"usage_notes":"OpenAI-class image model (GPT Image 2). Public model_id is gpt-image-2. Parameters: aspect_ratio (auto, 1:1, 9:16, 16:9, 4:3, 3:4 — default auto), resolution (1K, 2K, 4K — default 1K). Constraint: 2K and 4K REQUIRE an explicit aspect_ratio that is NOT auto and NOT 1:1 (only 9:16, 16:9, 4:3, or 3:4). 1K accepts every value including auto/1:1. Text-to-image: omit source_media_urls. Image-to-image: pass 1–16 image URLs. The API auto-routes: any source_media_urls switches to the image-to-image path. Prompt max 20000 chars.","cost_note":"Resolution pricing (credits): 1K = 11, 2K = 15, 4K = 21. Pass `resolution` to select a tier; the base price shown is the cheapest."},{"model_id":"grok-image-to-image","display_name":"Grok Image-to-Image","model_type":"image","provider":"xAI","cost_per_generation":14.0,"estimated_time_seconds":19,"capabilities":{"prompt_max_chars":5000,"duration_options":[],"aspect_ratio_options":["2:3","3:2","1:1","9:16","16:9"],"max_input_images":1,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false},"requires_input_media":true,"input_media_types":["image"],"generation_types":["image-to-image"],"usage_notes":"Image edit: pass source_media_urls (1 image). aspect_ratio: 1:1, 2:3, 3:2, 9:16, 16:9."},{"model_id":"grok-text-to-image","display_name":"Grok Text-to-Image","model_type":"image","provider":"xAI","cost_per_generation":14.0,"estimated_time_seconds":30,"capabilities":{"prompt_max_chars":5000,"duration_options":[],"aspect_ratio_options":["2:3","3:2","1:1","9:16","16:9"],"max_input_images":0,"input_media_types":[],"supports_negative_prompt":false,"supports_sound":false},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-image"],"usage_notes":"Text-to-image only. Omit source_media_urls."},{"model_id":"imagen-4","display_name":"Imagen 4","model_type":"image","provider":"Google","cost_per_generation":13.0,"estimated_time_seconds":30,"capabilities":{"prompt_max_chars":5000,"duration_options":[],"aspect_ratio_options":["1:1","16:9","9:16","4:3","3:4"],"max_input_images":0,"input_media_types":[],"supports_negative_prompt":true,"supports_sound":false},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-image"],"usage_notes":"Text-to-image only. Do not pass source_media_urls. negative_prompt supported. quality: standard, fast, ultra."},{"model_id":"imagen-4-fast","display_name":"Imagen 4 Fast","model_type":"image","provider":"Google","cost_per_generation":7.0,"estimated_time_seconds":30,"capabilities":{"prompt_max_chars":5000,"duration_options":[],"aspect_ratio_options":["1:1","16:9","9:16","4:3","3:4"],"max_input_images":0,"input_media_types":[],"supports_negative_prompt":true,"supports_sound":false},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-image"],"usage_notes":"Text-to-image only. Omit source_media_urls. negative_prompt supported."},{"model_id":"imagen-4-ultra","display_name":"Imagen 4 Ultra","model_type":"image","provider":"Google","cost_per_generation":19.0,"estimated_time_seconds":30,"capabilities":{"prompt_max_chars":5000,"duration_options":[],"aspect_ratio_options":["1:1","16:9","9:16","4:3","3:4"],"max_input_images":0,"input_media_types":[],"supports_negative_prompt":true,"supports_sound":false},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-image"],"usage_notes":"Text-to-image only. Omit source_media_urls. negative_prompt supported."},{"model_id":"logo-maker","display_name":"logo-maker","model_type":"image","provider":"Recraft","cost_per_generation":90.0,"estimated_time_seconds":30,"capabilities":{"prompt_max_chars":10000,"duration_options":[],"aspect_ratio_options":["1:1","4:3","3:4","3:2","2:3","16:9","9:16","4:5","5:4","1:2","2:1"],"max_input_images":0,"input_media_types":[],"supports_negative_prompt":false,"supports_sound":false},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-image"],"usage_notes":"Recraft SVG vector logo generator — use only for brand logos / SVG vector output, not general imagery. Text-to-image only; omit source_media_urls. aspect_ratio configurable. Prompt max 10000 chars."},{"model_id":"nano-banana","display_name":"Nano Banana","model_type":"image","provider":"Google","cost_per_generation":7.0,"estimated_time_seconds":41,"capabilities":{"prompt_max_chars":5000,"duration_options":[],"aspect_ratio_options":["1:1","16:9","9:16","4:3","3:4","3:2","2:3","21:9","5:4","4:5","auto"],"max_input_images":0,"input_media_types":[],"supports_negative_prompt":false,"supports_sound":false},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-image"],"usage_notes":"Prefer nano-banana-2 for better quality at the same price. Text-to-image only. For image editing use nano-banana-edit."},{"model_id":"nano-banana-2","display_name":"Nano Banana 2","model_type":"image","provider":"Google","cost_per_generation":11.0,"estimated_time_seconds":46,"capabilities":{"prompt_max_chars":20000,"duration_options":[],"aspect_ratio_options":["1:1","16:9","9:16","4:3","3:4","3:2","2:3","21:9","5:4","4:5","auto"],"resolution_options":["1K","2K","4K"],"max_input_images":8,"input_media_types":[],"supports_negative_prompt":false,"supports_sound":false},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-image","image-to-image"],"usage_notes":"Best value. Best for editing; amazing character consistency (NB family leads; NB2 wins on price + almost same as Pro + Google Search grounding). Use when user does not specify a model. Pass `resolution` (1K default, 2K, 4K) — each tier is a separate pricing SKU (check /v1/models). Use aspect_ratio (1:1, 16:9, 9:16, 3:4, 4:3, 3:2, 2:3, 5:4, 4:5, 21:9). Text-to-image: omit source_media_urls. Image-to-image: up to 8 images. Google Search grounding is always enabled."},{"model_id":"nano-banana-2-2K","display_name":"Nano Banana 2 2K","model_type":"image","provider":"Google","cost_per_generation":15.0,"estimated_time_seconds":46,"capabilities":{"prompt_max_chars":20000,"duration_options":[],"aspect_ratio_options":["1:1","16:9","9:16","4:3","3:4","3:2","2:3","21:9","5:4","4:5","auto"],"resolution_options":["1K","2K","4K"],"max_input_images":8,"input_media_types":[],"supports_negative_prompt":false,"supports_sound":false},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-image","image-to-image"],"usage_notes":"Same usage notes as 'nano-banana-2'."},{"model_id":"nano-banana-2-4K","display_name":"Nano Banana 2 4K","model_type":"image","provider":"Google","cost_per_generation":25.0,"estimated_time_seconds":46,"capabilities":{"prompt_max_chars":20000,"duration_options":[],"aspect_ratio_options":["1:1","16:9","9:16","4:3","3:4","3:2","2:3","21:9","5:4","4:5","auto"],"resolution_options":["1K","2K","4K"],"max_input_images":8,"input_media_types":[],"supports_negative_prompt":false,"supports_sound":false},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-image","image-to-image"],"usage_notes":"Same usage notes as 'nano-banana-2'."},{"model_id":"nano-banana-2-lite","display_name":"Nano Banana 2 Lite","model_type":"image","provider":"Google","cost_per_generation":8.0,"estimated_time_seconds":16,"capabilities":{"prompt_max_chars":20000,"duration_options":[],"aspect_ratio_options":["1:1","16:9","9:16","4:3","3:4","3:2","2:3","21:9","5:4","4:5","auto"],"max_input_images":10,"input_media_types":[],"supports_negative_prompt":false,"supports_sound":false},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-image","image-to-image"],"usage_notes":"Lite sibling of nano-banana-2 — single tier (no resolution options), the fastest and most affordable Nano Banana image model for generation and editing. No `resolution` parameter. Use aspect_ratio (1:1, 16:9, 9:16, 3:4, 4:3, 3:2, 2:3, 5:4, 4:5, 21:9; default auto). Text-to-image: omit source_media_urls. Image-to-image: up to 10 images."},{"model_id":"nano-banana-edit","display_name":"Nano Banana Edit","model_type":"image","provider":"Google","cost_per_generation":7.0,"estimated_time_seconds":52,"capabilities":{"prompt_max_chars":5000,"duration_options":[],"aspect_ratio_options":["1:1","16:9","9:16","4:3","3:4","3:2","2:3","21:9","5:4","4:5","auto"],"max_input_images":10,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false},"requires_input_media":true,"input_media_types":["image"],"generation_types":["image-to-image"],"usage_notes":"Prefer nano-banana-2 for better quality at the same price. Requires source_media_urls with image URL(s). Up to 10 images. Set generation_type='image-to-image'."},{"model_id":"nano-banana-pro","display_name":"Nano Banana Pro","model_type":"image","provider":"Google","cost_per_generation":24.0,"estimated_time_seconds":67,"capabilities":{"prompt_max_chars":20000,"duration_options":[],"aspect_ratio_options":["1:1","16:9","9:16","4:3","3:4","3:2","2:3","21:9","5:4","4:5","auto"],"resolution_options":["1K","2K","4K"],"max_input_images":8,"input_media_types":[],"supports_negative_prompt":false,"supports_sound":false},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-image","image-to-image"],"usage_notes":"Reserve for complex multi-element compositions, intricate typography, print-quality brand assets. For most use cases nano-banana-2 is equivalent and cheaper. Pass `resolution` (1K default, 2K, 4K) — each tier is a separate pricing SKU (check /v1/models). Use aspect_ratio (1:1, 16:9, 9:16, 3:4, 4:3, 3:2, 2:3, 5:4, 4:5, 21:9). Text-to-image: omit source_media_urls. Image-to-image: up to 8 images."},{"model_id":"nano-banana-pro-2K","display_name":"Nano Banana Pro 2K","model_type":"image","provider":"Google","cost_per_generation":24.0,"estimated_time_seconds":67,"capabilities":{"prompt_max_chars":20000,"duration_options":[],"aspect_ratio_options":["1:1","16:9","9:16","4:3","3:4","3:2","2:3","21:9","5:4","4:5","auto"],"resolution_options":["1K","2K","4K"],"max_input_images":8,"input_media_types":[],"supports_negative_prompt":false,"supports_sound":false},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-image","image-to-image"],"usage_notes":"Same usage notes as 'nano-banana-pro'."},{"model_id":"nano-banana-pro-4K","display_name":"Nano Banana Pro 4K","model_type":"image","provider":"Google","cost_per_generation":30.0,"estimated_time_seconds":67,"capabilities":{"prompt_max_chars":20000,"duration_options":[],"aspect_ratio_options":["1:1","16:9","9:16","4:3","3:4","3:2","2:3","21:9","5:4","4:5","auto"],"resolution_options":["1K","2K","4K"],"max_input_images":8,"input_media_types":[],"supports_negative_prompt":false,"supports_sound":false},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-image","image-to-image"],"usage_notes":"Same usage notes as 'nano-banana-pro'."},{"model_id":"p-image-edit","display_name":"P Image Edit","model_type":"image","provider":"Pruna AI","cost_per_generation":6.0,"estimated_time_seconds":4,"capabilities":{"aspect_ratios":["auto","1:1","16:9","9:16","4:3","3:4","3:2","2:3"],"supports_seed":true,"generation_types":["image-to-image"],"max_input_images":8,"prompt_max_chars":5000,"duration_options":[],"aspect_ratio_options":["auto","1:1","16:9","9:16","4:3","3:4","3:2","2:3"],"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false},"requires_input_media":true,"input_media_types":["image"],"generation_types":["image-to-image"],"usage_notes":"Pruna AI P Image Edit. Image-to-image only: pass source_media_urls (1–8 image URLs). aspect_ratio: use 'auto' to match the first input image, or 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3. Set generation_type='image-to-image'. By default disable_safety_checker is true (moderation off); pass disable_safety_checker: false to enable the safety checker."},{"model_id":"qwen-image-to-image","display_name":"Qwen Image Edit","model_type":"image","provider":"Alibaba","cost_per_generation":10.0,"estimated_time_seconds":30,"capabilities":{"prompt_max_chars":5000,"duration_options":[],"aspect_ratio_options":["1:1","2:3","3:2","3:4","4:3","9:16","16:9","21:9"],"max_input_images":1,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false},"requires_input_media":true,"input_media_types":["image"],"generation_types":["image-to-image"],"usage_notes":"Image edit: pass source_media_urls (URLs as image_url array). aspect_ratio: 1:1, 2:3, 3:2, 3:4, 4:3, 9:16, 16:9, 21:9."},{"model_id":"qwen-text-to-image","display_name":"Qwen Text-to-Image","model_type":"image","provider":"Alibaba","cost_per_generation":10.0,"estimated_time_seconds":30,"capabilities":{"prompt_max_chars":5000,"duration_options":[],"aspect_ratio_options":["1:1","4:3","3:4","16:9","9:16"],"max_input_images":0,"input_media_types":[],"supports_negative_prompt":false,"supports_sound":false},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-image"],"usage_notes":"Text-to-image. Omit source_media_urls. aspect_ratio as image_size: 1:1, 4:3, 3:4, 16:9, 9:16."},{"model_id":"remove-background","display_name":"Remove Background","model_type":"image","provider":"Kubeez","cost_per_generation":5.0,"estimated_time_seconds":5,"capabilities":{"duration_options":[],"max_input_images":1,"max_input_audios":0,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false},"requires_input_media":true,"input_media_types":["image"],"generation_types":["background-removal"],"usage_notes":"Remove Background — cuts the subject out of an image. The output is a PNG with a real transparent background (alpha), not a white or checkerboard fill.\n\nTakes NO prompt: this is an operation on an existing image, so it is NOT a\ngenerate_media model. Call the dedicated endpoint instead.\n\nREST endpoint: POST /v1/generate/remove-background\nMCP: remove_background(image_url=...)\n\nFlow:\n  1. Upload the image via POST /v1/upload/media.\n  2. POST /v1/generate/remove-background with image_url.\n  3. Response returns generation_id (async, usually a few seconds).\n  4. Poll GET /v1/generate/media/{generation_id} until completed.\n\nInput: one .jpg / .jpeg / .png / .webp image, max 5MB (provider cap). Other\nformats are rejected. Billing: flat per image — see get_models / estimate.\n\nAlso available in-app at kubeez.com (image tools → Background Remover)."},{"model_id":"z-image","display_name":"z-image","model_type":"image","provider":"Alibaba","cost_per_generation":4.0,"estimated_time_seconds":8,"capabilities":{"prompt_max_chars":5000,"duration_options":[],"aspect_ratio_options":["1:1","4:3","3:4","16:9","9:16"],"max_input_images":0,"input_media_types":[],"supports_negative_prompt":false,"supports_sound":false},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-image"],"usage_notes":"Use when speed matters more than detail — quick previews, rapid iteration, bulk runs. Text-to-image only; omit source_media_urls. Prompt max 5000 chars. Aspect ratios: 1:1, 4:3, 3:4, 16:9, 9:16. Standard resolution (704px base)."},{"model_id":"z-image-hd","display_name":"z-image-hd","model_type":"image","provider":"Alibaba","cost_per_generation":6.0,"estimated_time_seconds":8,"capabilities":{"prompt_max_chars":5000,"duration_options":[],"aspect_ratio_options":["1:1","4:3","3:4","16:9","9:16"],"max_input_images":0,"input_media_types":[],"supports_negative_prompt":false,"supports_sound":false},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-image"],"usage_notes":"HD variant of Z-Image — higher resolution (1408px base) at same speed. Text-to-image only; omit source_media_urls. Prompt max 5000 chars. Aspect ratios: 1:1, 4:3, 3:4, 16:9, 9:16."},{"model_id":"seedream-5-pro","display_name":"Seedream 5.0 Pro","model_type":"image","provider":"ByteDance","cost_per_generation":14.0,"estimated_time_seconds":115,"capabilities":{"prompt_max_chars":2995,"duration_options":[],"aspect_ratio_options":["1:1","4:3","3:4","16:9","9:16"],"resolution_options":["1.5K"],"max_input_images":0,"input_media_types":[],"supports_negative_prompt":false,"supports_sound":false},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-image"],"usage_notes":"Seedream 5.0 Pro text-to-image, low tier (1.5K, default 1536x1536; 1K also allowed). Omit source_media_urls. Prompt max 2995 chars. For image editing / multi-reference use seedream-5-pro-edit; for 2K output use seedream-5-pro-2K."},{"model_id":"seedream-5-pro-2K","display_name":"Seedream 5.0 Pro 2K","model_type":"image","provider":"ByteDance","cost_per_generation":22.0,"estimated_time_seconds":137,"capabilities":{"prompt_max_chars":2995,"duration_options":[],"aspect_ratio_options":["1:1","4:3","3:4","16:9","9:16"],"resolution_options":["2K"],"max_input_images":0,"input_media_types":[],"supports_negative_prompt":false,"supports_sound":false},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-image"],"usage_notes":"Seedream 5.0 Pro text-to-image, high tier (2K, 2048x2048). Omit source_media_urls. Prompt max 2995 chars. For image editing / multi-reference use seedream-5-pro-edit-2K."},{"model_id":"seedream-5-pro-edit","display_name":"Seedream 5.0 Pro Edit","model_type":"image","provider":"ByteDance","cost_per_generation":14.0,"estimated_time_seconds":78,"capabilities":{"prompt_max_chars":2995,"duration_options":[],"aspect_ratio_options":["1:1","4:3","3:4","16:9","9:16"],"resolution_options":["1.5K"],"max_input_images":10,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false},"requires_input_media":true,"input_media_types":["image"],"generation_types":["image-to-image"],"usage_notes":"Seedream 5.0 Pro edit / multi-reference, low tier (1.5K, default 1536x1536; 1K also allowed). Require source_media_urls (up to 10 image URLs). Set generation_type='image-to-image'. Prompt max 2995 chars. Billing: base credits + 1 credit per extra reference beyond the first (first reference free). For 2K output use seedream-5-pro-edit-2K."},{"model_id":"seedream-5-pro-edit-2K","display_name":"Seedream 5.0 Pro Edit 2K","model_type":"image","provider":"ByteDance","cost_per_generation":22.0,"estimated_time_seconds":78,"capabilities":{"prompt_max_chars":2995,"duration_options":[],"aspect_ratio_options":["1:1","4:3","3:4","16:9","9:16"],"resolution_options":["2K"],"max_input_images":10,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false},"requires_input_media":true,"input_media_types":["image"],"generation_types":["image-to-image"],"usage_notes":"Seedream 5.0 Pro edit / multi-reference, high tier (2K, 2048x2048). Require source_media_urls (up to 10 image URLs). Set generation_type='image-to-image'. Prompt max 2995 chars. Billing: base credits + 1 credit per extra reference beyond the first (first reference free)."},{"model_id":"seedream-v4","display_name":"Seedream V4","model_type":"image","provider":"ByteDance","cost_per_generation":7.0,"estimated_time_seconds":30,"capabilities":{"prompt_max_chars":2500,"duration_options":[],"aspect_ratio_options":["1:1","4:3","3:4","16:9","9:16","3:2","2:3","21:9"],"max_input_images":10,"input_media_types":[],"supports_negative_prompt":false,"supports_sound":false},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-image","image-to-image"],"usage_notes":"ByteDance Seedream V4 — prefer seedream-v4-5 or 5-lite-text-to-image for better quality at the same price. Text-to-image: omit source_media_urls. Image-to-image: pass source_media_urls (up to 10). Prompt max 2500 chars."},{"model_id":"seedream-v4-5","display_name":"Seedream 4.5","model_type":"image","provider":"ByteDance","cost_per_generation":9.0,"estimated_time_seconds":23,"capabilities":{"prompt_max_chars":3000,"duration_options":[],"quality_options":["basic","high"],"aspect_ratio_options":["1:1","4:3","3:4","16:9","9:16","3:2","2:3","21:9"],"max_input_images":10,"input_media_types":[],"supports_negative_prompt":false,"supports_sound":false},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-image","image-to-image"],"usage_notes":"Seedream 4.5. Text-to-image: omit source_media_urls. Image-to-image: pass source_media_urls (up to 10). Prompt max 3000 chars. quality: 'basic' (default, 2K) or 'high' (4K output). aspect_ratio e.g. 1:1, 9:16, 16:9."},{"model_id":"seedream-v4-5-edit","display_name":"Seedream V4.5 Edit","model_type":"image","provider":"ByteDance","cost_per_generation":9.0,"estimated_time_seconds":52,"capabilities":{"prompt_max_chars":3000,"duration_options":[],"quality_options":["basic","high"],"aspect_ratio_options":["1:1","4:3","3:4","16:9","9:16","3:2","2:3","21:9"],"max_input_images":10,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false},"requires_input_media":true,"input_media_types":["image"],"generation_types":["image-to-image"],"usage_notes":"Seedream 4.5 Edit. Image-to-image only. Require source_media_urls (up to 10 image URLs). Set generation_type='image-to-image'. quality: 'basic' (default, 2K) or 'high' (4K output)."},{"model_id":"seedream-v4-edit","display_name":"Seedream V4 Edit","model_type":"image","provider":"ByteDance","cost_per_generation":7.0,"estimated_time_seconds":30,"capabilities":{"prompt_max_chars":2500,"duration_options":[],"quality_options":["1K","2K","4K"],"aspect_ratio_options":["1:1","4:3","3:4","16:9","9:16","3:2","2:3","21:9"],"max_input_images":10,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false},"requires_input_media":true,"input_media_types":["image"],"generation_types":["image-to-image"],"usage_notes":"Seedream V4 Edit. Image-to-image only. Require source_media_urls (up to 10 image URLs). Set generation_type='image-to-image'. Prompt max 2500 chars. Supports resolution via quality param: '1K' (default), '2K', or '4K' for higher resolution output."},{"model_id":"V4","display_name":"Suno V4","model_type":"music","provider":"Suno","cost_per_generation":34.0,"estimated_time_seconds":120,"capabilities":{},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-music"],"usage_notes":""},{"model_id":"V4_5","display_name":"Suno V4.5","model_type":"music","provider":"Suno","cost_per_generation":34.0,"estimated_time_seconds":120,"capabilities":{},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-music"],"usage_notes":""},{"model_id":"V4_5PLUS","display_name":"Suno V4.5+","model_type":"music","provider":"Suno","cost_per_generation":34.0,"estimated_time_seconds":120,"capabilities":{},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-music"],"usage_notes":""},{"model_id":"V5","display_name":"Suno V5","model_type":"music","provider":"Suno","cost_per_generation":34.0,"estimated_time_seconds":120,"capabilities":{},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-music"],"usage_notes":""},{"model_id":"V5_5","display_name":"Suno V5.5","model_type":"music","provider":"Suno","cost_per_generation":34.0,"estimated_time_seconds":120,"capabilities":{},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-music"],"usage_notes":""},{"model_id":"auto-caption","display_name":"Auto Caption","model_type":"other","provider":"Kubeez","cost_per_generation":0.5,"estimated_time_seconds":30,"capabilities":{"duration_options":[],"caption_speech_options":["intl_auto","u3_en","u3_es","u3_fr","u3_de","u3_it","u3_pt"],"max_input_images":0,"max_input_videos":1,"input_media_types":["video"],"supports_negative_prompt":false,"supports_sound":false},"requires_input_media":true,"input_media_types":["video"],"generation_types":["video-to-captions"],"usage_notes":"Auto Captions — AI speech-to-text for videos. Returns word-level timestamped captions.\n\nEndpoint: POST /v1/generate/captions\n\nFlow:\n  1. Upload video via POST /v1/upload/media (duration auto-detected).\n  2. POST /v1/generate/captions with media_url.\n  3. Response contains captions with word-level timestamps.\n\nQuality modes:\n  • auto (default): auto-detects spoken language, lower cost.\n  • best: select a specific language (en/es/fr/de/it/pt) for higher accuracy.\n  • code_switching: detect multiple languages in one video.\n\nLimits: max 30 min. Billing: per-second of video duration.\n\nFor a full workflow with customizable caption styles, fonts, animations, and burned-in video rendering, use kubeez.com/media/auto-captions."},{"model_id":"mvsep-40","display_name":"BS Roformer (vocals, instrumental)","model_type":"separation","provider":"MVSEP","cost_per_generation":6.0,"estimated_time_seconds":30,"capabilities":{"duration_options":[],"max_input_images":0,"max_input_audios":1,"input_media_types":["audio"],"supports_negative_prompt":false,"supports_sound":false},"requires_input_media":true,"input_media_types":["audio"],"generation_types":["audio-separation"],"usage_notes":"Music Separation — split audio into vocals and instrumental tracks.\n\nEndpoint: POST /v1/generate/separation\n\nFlow:\n  1. Upload audio via POST /v1/upload/media (duration auto-detected).\n  2. POST /v1/generate/separation with media_url.\n  3. Response returns separation_id + task_id (async, 1-3 min).\n  4. Poll GET /v1/generate/media/{separation_id} until completed.\n  5. Results include vocals_url and instrumental_url.\n\nBilling: per-second of audio duration.\n\nFor a full workflow with preview and library, use kubeez.com/audio/separation."},{"model_id":"auto-caption-universal-3-pro","display_name":"Auto Caption (Universal-3 Pro)","model_type":"speech","provider":"AssemblyAI","cost_per_generation":0.7,"estimated_time_seconds":60,"capabilities":{},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-dialogue"],"usage_notes":""},{"model_id":"seed-audio-1.0","display_name":"seed-audio-1.0","model_type":"speech","provider":"ByteDance","cost_per_generation":0.75,"estimated_time_seconds":60,"capabilities":{"prompt_max_chars":2048,"max_input_images":1,"input_media_types":["image","audio"],"supports_negative_prompt":false,"supports_sound":false},"requires_input_media":false,"input_media_types":["image","audio"],"generation_types":["text-to-dialogue"],"usage_notes":"Prompt-driven generative Text-to-Speech powered by Seed 1.0 Audio (ByteDance).\n\nEndpoint: POST /v1/generate/dialogue with provider='seed'.\n\nUnlike ElevenLabs/Gemini (a chosen voice reading text verbatim), Seed takes a free-form `text` PROMPT and generates audio from it. No `voice` selection, no [tag] stripping, no ElevenLabs tuning params.\n\nParameters:\n  • text (required): the prompt, max 2048 characters.\n  • Reference (optional, image and audio CANNOT be mixed):\n      - one IMAGE: image_url (HTTPS) or image_data (base64), guides voice/mood; or\n      - up to 3 AUDIO: audio_references = [{speaker | audio_url | audio_data}, ...] (each clip <=30s)\n        for voice cloning, tagged IN `text` by upload order as <<TGT_SPK1>>/<<TGT_SPK2>>/<<TGT_SPK3>>\n        (e.g. 'Marcus (..., the actor is <<TGT_SPK1>>) says: \"...\"'). @Voice1/@Audio1/@Speaker1\n        are also accepted (auto-normalized to <<TGT_SPKn>> server-side).\n  • audio_config (optional): {format (mp3/wav/ogg_opus/pcm), sample_rate, speech_rate (-50..100), loudness_rate (-50..100), pitch_rate (-12..12)}.\n\nLimits: text ≤2048 chars; each reference ≤10 MB; ≤3 audio references; ≤1 image; output audio is capped at 120 seconds.\n\nBilling: per OUTPUT SECOND (capped at 120 s), minimum 1 credit. Read the per-second rate live from GET /v1/models.\n\nReturns generation_id immediately (the upstream call runs server-side); poll GET /v1/generate/media/{generation_id} until completed. Outputs appear in media_outputs with media_type=audio."},{"model_id":"text-to-dialogue-gemini","display_name":"Gemini 3.1 Flash TTS","model_type":"speech","provider":"Google","cost_per_generation":26.0,"estimated_time_seconds":60,"capabilities":{},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-dialogue"],"usage_notes":""},{"model_id":"text-to-dialogue-v3","display_name":"Text To Dialogue V3","model_type":"speech","provider":"ElevenLabs","cost_per_generation":26.0,"estimated_time_seconds":60,"capabilities":{"prompt_max_chars":5000,"max_input_images":0,"input_media_types":[],"supports_negative_prompt":false,"supports_sound":false},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-dialogue"],"usage_notes":"Text-to-Speech (single voice) powered by ElevenLabs v3 on Replicate.\n\nEndpoint: POST /v1/generate/dialogue\n\nSend a `text` prompt and one `voice` from the allow-list below.\n\nParameters:\n  • text (required): what to say. 5-5000 chars after [bracket] audio tags are stripped.\n  • voice (required): one of the 26 voice ids in `voice_allowlist`.\n  • stability: 0..1 (default 0.5). Higher = more stable, lower = more expressive.\n  • similarity_boost: 0..1 (default 0.75).\n  • style: 0..1 (default 0). Style exaggeration.\n  • speed: 0.7..1.2 (default 1.0).\n  • previous_text / next_text: optional context strings (audio tags stripped).\n  • language_code: one of 29 ISO codes in `language_code_allowlist` (default 'en'). The upstream wrapper rejects v2-documented hu/no/vi/he/fa — re-probe before adding new codes.\n\nAudio tags such as [HEY], [laughs], [whispers] are stripped server-side before the prompt is sent to Replicate — they will NOT be spoken or interpreted.\n\nLimits: prompt 5-5000 characters after tag stripping. Invalid voices and language_codes rejected before billing.\n\nBilling: 26 credits per 1000 characters (minimum 1 credit).\n\nTrack results via GET /v1/generate/media/{generation_id} (poll until completed).","cost_note":"Text-to-speech billing is PER 1,000 CHARACTERS (≤0.3 rounds down, >0.3 rounds up; min 1 credit). Rate: 26 credits per 1,000 chars. Example: 500 chars = ~13 cr; 1,500 chars = ~39 cr; 5,000 chars = ~130 cr. Voice must be one of 26 elevenlabs/v3 voices. Unsupported voices return 400.","voice_allowlist":["Rachel","Drew","Clyde","Paul","Aria","Domi","Dave","Roger","Fin","Sarah","James","Jane","Juniper","Arabella","Hope","Bradford","Reginald","Gaming","Austin","Kuon","Blondie","Priyanka","Alexandra","Monika","Mark","Grimblewood"],"language_code_allowlist":["ar","bg","cs","da","de","el","en","es","fi","fil","fr","hi","hr","id","it","ja","ko","ms","nl","pl","pt","ro","ru","sk","sv","ta","tr","uk","zh"]},{"model_id":"gemini-omni-video-4k-10s","display_name":"Gemini Omni Video (4K)","model_type":"video","provider":"Google","cost_per_generation":320.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":5000,"duration_options":["4s","6s","8s","10s"],"aspect_ratio_options":["16:9","9:16"],"resolution_options":["720p","1080p","4K"],"max_input_images":7,"max_input_videos":1,"max_input_audios":0,"input_media_types":["image","video"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included","reference_video_max_s":10.0},"requires_input_media":false,"input_media_types":["image","video"],"generation_types":["text-to-video","image-to-video","video-to-video"],"usage_notes":"Google's multi-modal video model — video output with built-in audio (29 named voices). 15 concrete variants encode resolution + output duration in the model_id:\n  gemini-omni-video-{720p|1080p|4k}-{4|6|8|10}s   (duration mode, text/image refs)\n  gemini-omni-video-{720p|1080p|4k}-video-ref     (video-ref mode, output = trim length)\n\n720p and 1080p are priced identically. The `duration` and `resolution` parameters are IGNORED — encode both in the variant id. Aspect ratio is strictly 16:9 or 9:16; any other value is rejected with HTTP 400 before credits are touched.\n\nOptional kwargs:\n  • voice_id  — one of 29 built-in voices. Unknown ids are rejected before any     credits are charged.\n  • character_ids — saved character IDs; each consumes 1 of the 7 reference slots.\n\nSource media (`source_media_urls`): 7 reference slots total. A video ref consumes 2 slots and FORCES a `-video-ref` variant (mixing a duration variant + video ref returns `variant_mismatch`). The driving clip window defaults to the first 10 s; pass `video_trim_start_s` / `video_trim_end_s` to pick a different window (range ≤ 10s, ends ≤ 30s). Audio file URLs are NOT accepted — use `voice_id` for spoken output."},{"model_id":"gemini-omni-video-4k-4s","display_name":"Gemini Omni Video (4K)","model_type":"video","provider":"Google","cost_per_generation":230.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":5000,"duration_options":["4s","6s","8s","10s"],"aspect_ratio_options":["16:9","9:16"],"resolution_options":["720p","1080p","4K"],"max_input_images":7,"max_input_videos":1,"max_input_audios":0,"input_media_types":["image","video"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included","reference_video_max_s":10.0},"requires_input_media":false,"input_media_types":["image","video"],"generation_types":["text-to-video","image-to-video","video-to-video"],"usage_notes":"Same usage notes as 'gemini-omni-video-4k-10s'."},{"model_id":"gemini-omni-video-4k-6s","display_name":"Gemini Omni Video (4K)","model_type":"video","provider":"Google","cost_per_generation":260.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":5000,"duration_options":["4s","6s","8s","10s"],"aspect_ratio_options":["16:9","9:16"],"resolution_options":["720p","1080p","4K"],"max_input_images":7,"max_input_videos":1,"max_input_audios":0,"input_media_types":["image","video"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included","reference_video_max_s":10.0},"requires_input_media":false,"input_media_types":["image","video"],"generation_types":["text-to-video","image-to-video","video-to-video"],"usage_notes":"Same usage notes as 'gemini-omni-video-4k-10s'."},{"model_id":"gemini-omni-video-4k-8s","display_name":"Gemini Omni Video (4K)","model_type":"video","provider":"Google","cost_per_generation":290.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":5000,"duration_options":["4s","6s","8s","10s"],"aspect_ratio_options":["16:9","9:16"],"resolution_options":["720p","1080p","4K"],"max_input_images":7,"max_input_videos":1,"max_input_audios":0,"input_media_types":["image","video"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included","reference_video_max_s":10.0},"requires_input_media":false,"input_media_types":["image","video"],"generation_types":["text-to-video","image-to-video","video-to-video"],"usage_notes":"Same usage notes as 'gemini-omni-video-4k-10s'."},{"model_id":"gemini-omni-video-4k-video-ref","display_name":"Gemini Omni Video (video ref, 4K)","model_type":"video","provider":"Google","cost_per_generation":380.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":5000,"duration_options":["4s","6s","8s","10s"],"aspect_ratio_options":["16:9","9:16"],"resolution_options":["720p","1080p","4K"],"max_input_images":7,"max_input_videos":1,"max_input_audios":0,"input_media_types":["image","video"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included","reference_video_max_s":10.0},"requires_input_media":false,"input_media_types":["image","video"],"generation_types":["text-to-video","image-to-video","video-to-video"],"usage_notes":"Same usage notes as 'gemini-omni-video-4k-10s'."},{"model_id":"gemini-omni-video-720p-10s","display_name":"Gemini Omni Video","model_type":"video","provider":"Google","cost_per_generation":200.0,"estimated_time_seconds":58,"capabilities":{"prompt_max_chars":5000,"duration_options":["4s","6s","8s","10s"],"aspect_ratio_options":["16:9","9:16"],"resolution_options":["720p","1080p","4K"],"max_input_images":7,"max_input_videos":1,"max_input_audios":0,"input_media_types":["image","video"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included","reference_video_max_s":10.0},"requires_input_media":false,"input_media_types":["image","video"],"generation_types":["text-to-video","image-to-video","video-to-video"],"usage_notes":"Same usage notes as 'gemini-omni-video-4k-10s'."},{"model_id":"gemini-omni-video-1080p-10s","display_name":"Gemini Omni Video","model_type":"video","provider":"Google","cost_per_generation":200.0,"estimated_time_seconds":58,"capabilities":{"prompt_max_chars":5000,"duration_options":["4s","6s","8s","10s"],"aspect_ratio_options":["16:9","9:16"],"resolution_options":["720p","1080p","4K"],"max_input_images":7,"max_input_videos":1,"max_input_audios":0,"input_media_types":["image","video"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included","reference_video_max_s":10.0},"requires_input_media":false,"input_media_types":["image","video"],"generation_types":["text-to-video","image-to-video","video-to-video"],"usage_notes":"Same usage notes as 'gemini-omni-video-4k-10s'."},{"model_id":"gemini-omni-video-720p-4s","display_name":"Gemini Omni Video","model_type":"video","provider":"Google","cost_per_generation":110.0,"estimated_time_seconds":63,"capabilities":{"prompt_max_chars":5000,"duration_options":["4s","6s","8s","10s"],"aspect_ratio_options":["16:9","9:16"],"resolution_options":["720p","1080p","4K"],"max_input_images":7,"max_input_videos":1,"max_input_audios":0,"input_media_types":["image","video"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included","reference_video_max_s":10.0},"requires_input_media":false,"input_media_types":["image","video"],"generation_types":["text-to-video","image-to-video","video-to-video"],"usage_notes":"Same usage notes as 'gemini-omni-video-4k-10s'."},{"model_id":"gemini-omni-video-1080p-4s","display_name":"Gemini Omni Video","model_type":"video","provider":"Google","cost_per_generation":110.0,"estimated_time_seconds":63,"capabilities":{"prompt_max_chars":5000,"duration_options":["4s","6s","8s","10s"],"aspect_ratio_options":["16:9","9:16"],"resolution_options":["720p","1080p","4K"],"max_input_images":7,"max_input_videos":1,"max_input_audios":0,"input_media_types":["image","video"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included","reference_video_max_s":10.0},"requires_input_media":false,"input_media_types":["image","video"],"generation_types":["text-to-video","image-to-video","video-to-video"],"usage_notes":"Same usage notes as 'gemini-omni-video-4k-10s'."},{"model_id":"gemini-omni-video-720p-6s","display_name":"Gemini Omni Video","model_type":"video","provider":"Google","cost_per_generation":140.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":5000,"duration_options":["4s","6s","8s","10s"],"aspect_ratio_options":["16:9","9:16"],"resolution_options":["720p","1080p","4K"],"max_input_images":7,"max_input_videos":1,"max_input_audios":0,"input_media_types":["image","video"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included","reference_video_max_s":10.0},"requires_input_media":false,"input_media_types":["image","video"],"generation_types":["text-to-video","image-to-video","video-to-video"],"usage_notes":"Same usage notes as 'gemini-omni-video-4k-10s'."},{"model_id":"gemini-omni-video-1080p-6s","display_name":"Gemini Omni Video","model_type":"video","provider":"Google","cost_per_generation":140.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":5000,"duration_options":["4s","6s","8s","10s"],"aspect_ratio_options":["16:9","9:16"],"resolution_options":["720p","1080p","4K"],"max_input_images":7,"max_input_videos":1,"max_input_audios":0,"input_media_types":["image","video"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included","reference_video_max_s":10.0},"requires_input_media":false,"input_media_types":["image","video"],"generation_types":["text-to-video","image-to-video","video-to-video"],"usage_notes":"Same usage notes as 'gemini-omni-video-4k-10s'."},{"model_id":"gemini-omni-video-720p-8s","display_name":"Gemini Omni Video","model_type":"video","provider":"Google","cost_per_generation":170.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":5000,"duration_options":["4s","6s","8s","10s"],"aspect_ratio_options":["16:9","9:16"],"resolution_options":["720p","1080p","4K"],"max_input_images":7,"max_input_videos":1,"max_input_audios":0,"input_media_types":["image","video"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included","reference_video_max_s":10.0},"requires_input_media":false,"input_media_types":["image","video"],"generation_types":["text-to-video","image-to-video","video-to-video"],"usage_notes":"Same usage notes as 'gemini-omni-video-4k-10s'."},{"model_id":"gemini-omni-video-1080p-8s","display_name":"Gemini Omni Video","model_type":"video","provider":"Google","cost_per_generation":170.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":5000,"duration_options":["4s","6s","8s","10s"],"aspect_ratio_options":["16:9","9:16"],"resolution_options":["720p","1080p","4K"],"max_input_images":7,"max_input_videos":1,"max_input_audios":0,"input_media_types":["image","video"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included","reference_video_max_s":10.0},"requires_input_media":false,"input_media_types":["image","video"],"generation_types":["text-to-video","image-to-video","video-to-video"],"usage_notes":"Same usage notes as 'gemini-omni-video-4k-10s'."},{"model_id":"gemini-omni-video-720p-video-ref","display_name":"Gemini Omni Video (video ref)","model_type":"video","provider":"Google","cost_per_generation":260.0,"estimated_time_seconds":150,"capabilities":{"prompt_max_chars":5000,"duration_options":["4s","6s","8s","10s"],"aspect_ratio_options":["16:9","9:16"],"resolution_options":["720p","1080p","4K"],"max_input_images":7,"max_input_videos":1,"max_input_audios":0,"input_media_types":["image","video"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included","reference_video_max_s":10.0},"requires_input_media":false,"input_media_types":["image","video"],"generation_types":["text-to-video","image-to-video","video-to-video"],"usage_notes":"Same usage notes as 'gemini-omni-video-4k-10s'."},{"model_id":"gemini-omni-video-1080p-video-ref","display_name":"Gemini Omni Video (video ref)","model_type":"video","provider":"Google","cost_per_generation":260.0,"estimated_time_seconds":150,"capabilities":{"prompt_max_chars":5000,"duration_options":["4s","6s","8s","10s"],"aspect_ratio_options":["16:9","9:16"],"resolution_options":["720p","1080p","4K"],"max_input_images":7,"max_input_videos":1,"max_input_audios":0,"input_media_types":["image","video"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included","reference_video_max_s":10.0},"requires_input_media":false,"input_media_types":["image","video"],"generation_types":["text-to-video","image-to-video","video-to-video"],"usage_notes":"Same usage notes as 'gemini-omni-video-4k-10s'."},{"model_id":"grok-image-to-video","display_name":"Grok Image-to-Video","model_type":"video","provider":"xAI","cost_per_generation":65.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":5000,"duration_options":["6s","10s"],"quality_options":["480p","720p"],"aspect_ratio_options":["2:3","3:2","1:1","9:16","16:9"],"max_input_images":1,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included"},"requires_input_media":true,"input_media_types":["image"],"generation_types":["image-to-video"],"usage_notes":"Image-to-video only. Require source_media_urls with exactly one image URL. duration: 6 or 10 seconds. resolution: '480p' or '720p'. mode: 'fun' | 'normal' | 'spicy' — note that `spicy` auto-downgrades to `normal` for image-to-video (only text-to-video honors spicy). Output always includes audio; no sound parameter."},{"model_id":"grok-imagine-video-1-5-preview-480p","display_name":"Grok Imagine Video 1.5 (480p)","model_type":"video","provider":"xAI","cost_per_generation":20.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":4096,"duration_options":["2s","3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"aspect_ratio_options":["auto","1:1","16:9","9:16","4:3","3:4","3:2","2:3"],"max_input_images":1,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included"},"requires_input_media":true,"input_media_types":["image"],"generation_types":["image-to-video"],"usage_notes":"Grok Imagine Video 1.5 Preview (kie.ai) — IMAGE-TO-VIDEO ONLY, PER-SECOND pricing priced separately at 480p vs 720p; read the exact rate live from get_models / estimate (never assume). Pass the variant id `grok-imagine-video-1-5-preview-480p` or `grok-imagine-video-1-5-preview-720p` as `model` (resolution is encoded in the id), plus duration (integer 2-15s). Require source_media_urls with exactly one image URL (the starting frame). Aspect ratios: auto, 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3 (auto derives from the source image). Prompt optional, max 4096 chars. Output includes audio; no sound parameter. Content filtering (nsfw_checker) is off by default."},{"model_id":"grok-imagine-video-1-5-preview-720p","display_name":"Grok Imagine Video 1.5 (720p)","model_type":"video","provider":"xAI","cost_per_generation":30.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":4096,"duration_options":["2s","3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"aspect_ratio_options":["auto","1:1","16:9","9:16","4:3","3:4","3:2","2:3"],"max_input_images":1,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included"},"requires_input_media":true,"input_media_types":["image"],"generation_types":["image-to-video"],"usage_notes":"Same usage notes as 'grok-imagine-video-1-5-preview-480p'."},{"model_id":"grok-text-to-video-6s","display_name":"Grok Text-to-Video (6s)","model_type":"video","provider":"xAI","cost_per_generation":65.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":5000,"duration_options":["6s","10s"],"quality_options":["480p","720p"],"aspect_ratio_options":["2:3","3:2","1:1","9:16","16:9"],"max_input_images":0,"input_media_types":[],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included"},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-video"],"usage_notes":"Text-to-video only. duration: 6 or 10 seconds (pass as string). resolution: '480p' or '720p' (default 720p). mode: 'fun' | 'normal' (default) | 'spicy' — controls content style/edginess. Omit source_media_urls. Output always includes audio; no sound parameter."},{"model_id":"kling-2-5-image-to-video-pro","display_name":"Kling 2.5 Image-to-Video Pro","model_type":"video","provider":"Kuaishou","cost_per_generation":65.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":2500,"duration_options":[],"max_input_images":2,"input_media_types":["image"],"supports_negative_prompt":true,"supports_sound":false,"video_audio":"included"},"requires_input_media":true,"input_media_types":["image"],"generation_types":["image-to-video"],"usage_notes":"Use when you have both plates. Image-to-video with start and end frame. Require source_media_urls with exactly 2 image URLs. negative_prompt supported. Prompt max 2500 chars. Output includes audio; no sound parameter.","cost_note":"Kling 2.5 Pro bills per duration variant: 5s ≈ 65.0 cr; 10s ≈ ~2× the 5s rate. Image-to-video with start+end frame interpolation. Pass duration ('5' or '10')."},{"model_id":"kling-2-5-image-to-video-pro-10s","display_name":"Kling 2.5 Image-to-Video Pro 10s","model_type":"video","provider":"Kuaishou","cost_per_generation":125.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":2500,"duration_options":[],"max_input_images":2,"input_media_types":["image"],"supports_negative_prompt":true,"supports_sound":false,"video_audio":"included"},"requires_input_media":true,"input_media_types":["image"],"generation_types":["image-to-video"],"usage_notes":"Same usage notes as 'kling-2-5-image-to-video-pro'."},{"model_id":"kling-2-6-image-to-video-10s","display_name":"Kling 2.6 I2V (10s)","model_type":"video","provider":"Kuaishou","cost_per_generation":175.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":2500,"duration_options":["5s","10s"],"aspect_ratio_options":["1:1","16:9","9:16"],"max_input_images":1,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param"},"requires_input_media":true,"input_media_types":["image"],"generation_types":["image-to-video"],"usage_notes":"Superior camera motion, native audio-video sync in one pass. Choose for social media and cinematic camera shots. Image-to-video only. Require source_media_urls with exactly one image URL. duration 5s or 10s. Use sound: true for audio, false for silent. Prompt max 2500 chars."},{"model_id":"kling-2-6-image-to-video-10s-audio","display_name":"Kling 2.6 I2V (10s, Audio)","model_type":"video","provider":"Kuaishou","cost_per_generation":310.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":2500,"duration_options":["5s","10s"],"aspect_ratio_options":["1:1","16:9","9:16"],"max_input_images":1,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param"},"requires_input_media":true,"input_media_types":["image"],"generation_types":["image-to-video"],"usage_notes":"Same usage notes as 'kling-2-6-image-to-video-10s'."},{"model_id":"kling-2-6-image-to-video-5s","display_name":"Kling 2.6 I2V (5s)","model_type":"video","provider":"Kuaishou","cost_per_generation":90.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":2500,"duration_options":["5s","10s"],"aspect_ratio_options":["1:1","16:9","9:16"],"max_input_images":1,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param"},"requires_input_media":true,"input_media_types":["image"],"generation_types":["image-to-video"],"usage_notes":"Same usage notes as 'kling-2-6-image-to-video-10s'."},{"model_id":"kling-2-6-image-to-video-5s-audio","display_name":"Kling 2.6 I2V (5s, Audio)","model_type":"video","provider":"Kuaishou","cost_per_generation":175.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":2500,"duration_options":["5s","10s"],"aspect_ratio_options":["1:1","16:9","9:16"],"max_input_images":1,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param"},"requires_input_media":true,"input_media_types":["image"],"generation_types":["image-to-video"],"usage_notes":"Same usage notes as 'kling-2-6-image-to-video-10s'."},{"model_id":"kling-2-6-motion-control-1080p","display_name":"Kling 2.6 Motion Pro","model_type":"video","provider":"Kuaishou","cost_per_generation":690.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":2500,"duration_options":[],"aspect_ratio_options":["16:9","9:16","1:1"],"max_input_images":1,"max_input_videos":1,"input_media_types":["image","video"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included","reference_video_max_s":30.0},"requires_input_media":true,"input_media_types":["image","video"],"generation_types":["image-to-video"],"usage_notes":"Same as kling-2-6-motion-control-720p. Requires 1 image + 1 video URL in source_media_urls. Output typically includes audio; no sound parameter.","cost_note":"Credits are PER SECOND. kling-2-6-motion-control-1080p: 23.0/s. Example: 30s video = 690.0 credits. Cost = duration × rate."},{"model_id":"kling-2-6-motion-control-720p","display_name":"Kling 2.6 Motion","model_type":"video","provider":"Kuaishou","cost_per_generation":390.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":2500,"duration_options":[],"aspect_ratio_options":["16:9","9:16","1:1"],"max_input_images":1,"max_input_videos":1,"input_media_types":["image","video"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included","reference_video_max_s":30.0},"requires_input_media":true,"input_media_types":["image","video"],"generation_types":["image-to-video"],"usage_notes":"Motion Control: requires exactly 1 image URL + 1 video URL in source_media_urls (image first, then video). Video max 30s, typically MP4/WebM up to 100MB. Output typically includes audio (from generation); no sound parameter.","cost_note":"Credits are PER SECOND. kling-2-6-motion-control-720p: 13.0/s. Example: 30s video = 390.0 credits. Cost = duration × rate."},{"model_id":"kling-2-6-text-to-video-10s","display_name":"Kling 2.6 (10s, no audio)","model_type":"video","provider":"Kuaishou","cost_per_generation":175.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":2500,"duration_options":["5s","10s"],"aspect_ratio_options":["1:1","16:9","9:16"],"max_input_images":0,"input_media_types":[],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param"},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-video"],"usage_notes":"Superior camera motion, native audio-video sync in one pass. Choose for social media and cinematic camera shots. Text-to-video only. Omit source_media_urls. duration 5s or 10s. Use sound: true for audio, sound: false for silent. Prompt max 2500 chars."},{"model_id":"kling-2-6-text-to-video-10s-audio","display_name":"Kling 2.6 (10s, with audio)","model_type":"video","provider":"Kuaishou","cost_per_generation":310.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":2500,"duration_options":["5s","10s"],"aspect_ratio_options":["1:1","16:9","9:16"],"max_input_images":0,"input_media_types":[],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param"},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-video"],"usage_notes":"Same usage notes as 'kling-2-6-text-to-video-10s'."},{"model_id":"kling-2-6-text-to-video-5s","display_name":"Kling 2.6 (5s, no audio)","model_type":"video","provider":"Kuaishou","cost_per_generation":90.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":2500,"duration_options":["5s","10s"],"aspect_ratio_options":["1:1","16:9","9:16"],"max_input_images":0,"input_media_types":[],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param"},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-video"],"usage_notes":"Same usage notes as 'kling-2-6-text-to-video-10s'."},{"model_id":"kling-2-6-text-to-video-5s-audio","display_name":"Kling 2.6 (5s, with audio)","model_type":"video","provider":"Kuaishou","cost_per_generation":175.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":2500,"duration_options":["5s","10s"],"aspect_ratio_options":["1:1","16:9","9:16"],"max_input_images":0,"input_media_types":[],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param"},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-video"],"usage_notes":"Same usage notes as 'kling-2-6-text-to-video-10s'."},{"model_id":"kling-3-0-4k","display_name":"Kling 3.0 4K","model_type":"video","provider":"Kuaishou","cost_per_generation":355.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":2500,"duration_options":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"aspect_ratio_options":["16:9","9:16","1:1"],"max_input_images":2,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"always_on_flat_rate"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Kling 3.0 4K — highest-resolution tier with audio bundled at a flat per-second rate.\n\nModes:\n  • text-to-video → omit source_media_urls.\n  • image-to-video → pass 1 image URL (start frame) or 2 image URLs (start + end frame) in source_media_urls.\n\nDuration: any integer 3–15 seconds. The `sound` param is accepted for parity but the\nrate is identical with or without it (audio is bundled — no `-audio` variant exists).\n\nPRICING (per-second, flat):\n  • 70 credits/second regardless of the sound param.\n  Example: 10s = 700 credits.","cost_note":"Credits are PER SECOND, FLAT. kling-3-0-4k: 71.0/s (audio bundled — same price with or without sound). Duration: any integer 3-15 seconds. Formula: credits = duration × rate. Examples: 3s = 213.0 cr, 5s = 355.0 cr, 10s = 710.0 cr, 15s = 1065.0 cr."},{"model_id":"kling-3-0-motion-control-1080p","display_name":"Kling 3.0 Motion Pro","model_type":"video","provider":"Kuaishou","cost_per_generation":840.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":2500,"duration_options":[],"max_input_images":1,"max_input_videos":1,"input_media_types":["image","video"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included","reference_video_max_s":30.0},"requires_input_media":true,"input_media_types":["image","video"],"generation_types":["image-to-video"],"usage_notes":"Same as kling-3-0-motion-control-720p. Requires 1 image + 1 video URL in source_media_urls. Output typically includes audio; no sound parameter.","cost_note":"Credits are PER SECOND. kling-3-0-motion-control-1080p: 28.0/s. Example: 30s video = 840.0 credits. Cost = duration × rate."},{"model_id":"kling-3-0-motion-control-720p","display_name":"Kling 3.0 Motion","model_type":"video","provider":"Kuaishou","cost_per_generation":600.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":2500,"duration_options":[],"max_input_images":1,"max_input_videos":1,"input_media_types":["image","video"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included","reference_video_max_s":30.0},"requires_input_media":true,"input_media_types":["image","video"],"generation_types":["image-to-video"],"usage_notes":"Same as Kling 2.6 Motion Control. Requires 1 image + 1 video URL in source_media_urls (image first, then video). Video max 30s. Output typically includes audio; no sound parameter.","cost_note":"Credits are PER SECOND. kling-3-0-motion-control-720p: 20.0/s. Example: 30s video = 600.0 credits. Cost = duration × rate."},{"model_id":"kling-3-0-pro","display_name":"Kling 3.0 Pro","model_type":"video","provider":"Kuaishou","cost_per_generation":105.0,"estimated_time_seconds":207,"capabilities":{"prompt_max_chars":2500,"duration_options":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"aspect_ratio_options":["16:9","9:16","1:1"],"max_input_images":2,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Kling 3.0 pro — highest-quality tier.\n\nModes:\n  • text-to-video → omit source_media_urls.\n  • image-to-video → pass 1 image URL (start frame) or 2 image URLs (start + end frame) in source_media_urls.\n\nDuration: any integer 3–15 seconds. sound: true/false toggles generated audio.\n\nPRICING (per-second):\n  • Without sound: 21 credits/second.\n  • With sound: 31 credits/second (audio surcharge +10/s).\n  Example: 10s with audio = 310 credits; without audio = 210 credits.","cost_note":"Credits are PER SECOND. kling-3-0-pro: 21.0/s (no audio), 31.0/s (with audio). Duration: any integer 3-15 seconds. Formula: credits = duration × rate. Examples (no audio): 3s = 63.0 cr, 5s = 105.0 cr, 10s = 210.0 cr, 15s = 315.0 cr. With audio: 3s = 93.0 cr, 10s = 310.0 cr, 15s = 465.0 cr."},{"model_id":"kling-3-0-pro-audio","display_name":"Kling 3.0 Pro (with audio)","model_type":"video","provider":"Kuaishou","cost_per_generation":30.0,"estimated_time_seconds":207,"capabilities":{},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-video","image-to-video"],"usage_notes":""},{"model_id":"kling-3-0-std","display_name":"Kling 3.0","model_type":"video","provider":"Kuaishou","cost_per_generation":85.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":2500,"duration_options":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"aspect_ratio_options":["16:9","9:16","1:1"],"max_input_images":2,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Kling 3.0 standard — high-quality video at a cheaper rate than pro.\n\nModes:\n  • text-to-video → omit source_media_urls.\n  • image-to-video → pass 1 image URL (start frame) or 2 image URLs (start + end frame) in source_media_urls.\n\nDuration: any integer 3–15 seconds. sound: true/false toggles generated audio.\n\nPRICING (per-second):\n  • Without sound: 17 credits/second.\n  • With sound: 24 credits/second (audio surcharge +7/s).\n  Example: 10s with audio = 240 credits; without audio = 170 credits.","cost_note":"Credits are PER SECOND. kling-3-0-std: 17.0/s (no audio), 24.0/s (with audio). Duration: any integer 3-15 seconds. Formula: credits = duration × rate. Examples (no audio): 3s = 51.0 cr, 5s = 85.0 cr, 10s = 170.0 cr, 15s = 255.0 cr. With audio: 3s = 72.0 cr, 10s = 240.0 cr, 15s = 360.0 cr."},{"model_id":"kling-3-0-std-audio","display_name":"Kling 3.0 Std (with audio)","model_type":"video","provider":"Kuaishou","cost_per_generation":23.0,"estimated_time_seconds":120,"capabilities":{},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-video","image-to-video"],"usage_notes":""},{"model_id":"kling-3-0-turbo-1080p","display_name":"Kling 3.0 Turbo (1080p)","model_type":"video","provider":"Kuaishou","cost_per_generation":29.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":2500,"duration_options":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"aspect_ratio_options":["16:9","9:16","1:1"],"max_input_images":1,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Kling 3.0 Turbo — faster Kling 3.0 video. PER-SECOND pricing, priced separately at 720p vs 1080p; read the exact rate live from get_models / estimate (never assume). Free duration 3-15s. Pass the variant id `kling-3-0-turbo-720p` or `kling-3-0-turbo-1080p` as `model` (resolution is encoded in the id), plus duration (3-15) and generation_type.\n\nModes:\n  • text-to-video → omit source_media_urls; aspect_ratio 16:9 / 9:16 / 1:1.\n  • image-to-video → pass 1 image URL (the start frame) in source_media_urls.\n\nPrompt max 2500 chars. Audio is included in the output (no sound toggle). No negative prompt."},{"model_id":"kling-3-0-turbo-720p","display_name":"Kling 3.0 Turbo (720p)","model_type":"video","provider":"Kuaishou","cost_per_generation":23.0,"estimated_time_seconds":82,"capabilities":{"prompt_max_chars":2500,"duration_options":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"aspect_ratio_options":["16:9","9:16","1:1"],"max_input_images":1,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'kling-3-0-turbo-1080p'."},{"model_id":"p-video","display_name":"p-video","model_type":"video","provider":"Pruna AI","cost_per_generation":20.0,"estimated_time_seconds":8,"capabilities":{"prompt_max_chars":2000,"duration_options":["1s","2s","3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s","16s","17s","18s","19s","20s"],"quality_options":["720p","720p-draft","1080p","1080p-draft","draft"],"aspect_ratio_options":["16:9","9:16","4:3","3:4","3:2","2:3","1:1"],"max_input_images":2,"max_input_audios":1,"input_media_types":["image","audio"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"included"},"requires_input_media":false,"input_media_types":["image","audio"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Fast video generation with draft mode for rapid iteration.\n\nGeneration modes (auto-detected from source_media_urls):\n  • text-to-video: prompt only (no source_media_urls).\n  • image-to-video: pass 1 image (start frame), optional 2nd (end frame).\nAudio is an OPTIONAL INPUT — not a separate generation_type. In either mode above, attaching 1 audio URL (.mp3/.wav/.flac) in source_media_urls drives lip sync / music sync; the video length = audio length (the `duration` param is ignored) and billing uses the actual audio duration.\n\nQuality tiers (pass via quality param):\n  • 720p (default): 7 cr/s\n  • 720p-draft (bare `draft` is a synonym): 4 cr/s (faster, lower quality)\n  • 1080p: 12 cr/s\n  • 1080p-draft: 6 cr/s\n\nDuration: 1-20 seconds. FPS: 24 (default) or 48.\nAudio is generated natively. Aspect ratio ignored when image is provided.\n\nGood for: talking avatars, lip sync, product animation, social ads, music videos.","cost_note":"Credits are PER SECOND with four tiers. Pass `quality` to pick:\n  quality=null or '720p'  → 7 cr/s  (standard)\n  quality='720p-draft'    → 4 cr/s  (4× faster, cheapest)\n  quality='1080p'         → 12 cr/s  (standard HD)\n  quality='1080p-draft'   → 6 cr/s  (HD draft)\nFormula: credits = max(1, duration_seconds × rate). Duration 1-20. When an audio URL is attached, the ACTUAL audio duration is used for billing (resolved from media_upload_metadata at upload time — the `duration` param is ignored by the provider in that mode)."},{"model_id":"seedance-1-5-pro-1080p-12s","display_name":"Seedance 1.5 Pro","model_type":"video","provider":"ByteDance","cost_per_generation":156.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":2500,"duration_options":["4s","8s","12s"],"aspect_ratio_options":["1:1","21:9","4:3","3:4","16:9","9:16"],"max_input_images":2,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Video generation with start/end frame support.\n\nGeneration modes:\n  • Text-to-video: prompt only, no images needed.\n  • Image-to-video: pass 2 images (start + end frame) in source_media_urls.\n\nResolutions: 480p, 720p, 1080p. Duration: 4s, 8s, or 12s.\nAudio: use sound: true for generated audio (audio variants cost 2x).\nfixed_lens: true to keep camera static.\n\nPick a variant that matches your resolution, duration, and audio preference (e.g. seedance-1-5-pro-720p-8s for 720p 8s silent, seedance-1-5-pro-720p-8s-audio for audio)."},{"model_id":"seedance-1-5-pro-1080p-12s-audio","display_name":"Seedance 1.5 Pro","model_type":"video","provider":"ByteDance","cost_per_generation":312.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":2500,"duration_options":["4s","8s","12s"],"aspect_ratio_options":["1:1","21:9","4:3","3:4","16:9","9:16"],"max_input_images":2,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'seedance-1-5-pro-1080p-12s'."},{"model_id":"seedance-1-5-pro-1080p-4s","display_name":"Seedance 1.5 Pro","model_type":"video","provider":"ByteDance","cost_per_generation":39.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":2500,"duration_options":["4s","8s","12s"],"aspect_ratio_options":["1:1","21:9","4:3","3:4","16:9","9:16"],"max_input_images":2,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'seedance-1-5-pro-1080p-12s'."},{"model_id":"seedance-1-5-pro-1080p-4s-audio","display_name":"Seedance 1.5 Pro","model_type":"video","provider":"ByteDance","cost_per_generation":78.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":2500,"duration_options":["4s","8s","12s"],"aspect_ratio_options":["1:1","21:9","4:3","3:4","16:9","9:16"],"max_input_images":2,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'seedance-1-5-pro-1080p-12s'."},{"model_id":"seedance-1-5-pro-1080p-8s","display_name":"Seedance 1.5 Pro","model_type":"video","provider":"ByteDance","cost_per_generation":78.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":2500,"duration_options":["4s","8s","12s"],"aspect_ratio_options":["1:1","21:9","4:3","3:4","16:9","9:16"],"max_input_images":2,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'seedance-1-5-pro-1080p-12s'."},{"model_id":"seedance-1-5-pro-1080p-8s-audio","display_name":"Seedance 1.5 Pro","model_type":"video","provider":"ByteDance","cost_per_generation":156.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":2500,"duration_options":["4s","8s","12s"],"aspect_ratio_options":["1:1","21:9","4:3","3:4","16:9","9:16"],"max_input_images":2,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'seedance-1-5-pro-1080p-12s'."},{"model_id":"seedance-1-5-pro-480p-12s","display_name":"Seedance 1.5 Pro","model_type":"video","provider":"ByteDance","cost_per_generation":48.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":2500,"duration_options":["4s","8s","12s"],"aspect_ratio_options":["1:1","21:9","4:3","3:4","16:9","9:16"],"max_input_images":2,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'seedance-1-5-pro-1080p-12s'."},{"model_id":"seedance-1-5-pro-480p-12s-audio","display_name":"Seedance 1.5 Pro","model_type":"video","provider":"ByteDance","cost_per_generation":58.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":2500,"duration_options":["4s","8s","12s"],"aspect_ratio_options":["1:1","21:9","4:3","3:4","16:9","9:16"],"max_input_images":2,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'seedance-1-5-pro-1080p-12s'."},{"model_id":"seedance-1-5-pro-480p-4s","display_name":"Seedance 1.5 Pro","model_type":"video","provider":"ByteDance","cost_per_generation":12.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":2500,"duration_options":["4s","8s","12s"],"aspect_ratio_options":["1:1","21:9","4:3","3:4","16:9","9:16"],"max_input_images":2,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'seedance-1-5-pro-1080p-12s'."},{"model_id":"seedance-1-5-pro-480p-4s-audio","display_name":"Seedance 1.5 Pro","model_type":"video","provider":"ByteDance","cost_per_generation":24.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":2500,"duration_options":["4s","8s","12s"],"aspect_ratio_options":["1:1","21:9","4:3","3:4","16:9","9:16"],"max_input_images":2,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'seedance-1-5-pro-1080p-12s'."},{"model_id":"seedance-1-5-pro-480p-8s","display_name":"Seedance 1.5 Pro","model_type":"video","provider":"ByteDance","cost_per_generation":24.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":2500,"duration_options":["4s","8s","12s"],"aspect_ratio_options":["1:1","21:9","4:3","3:4","16:9","9:16"],"max_input_images":2,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'seedance-1-5-pro-1080p-12s'."},{"model_id":"seedance-1-5-pro-480p-8s-audio","display_name":"Seedance 1.5 Pro","model_type":"video","provider":"ByteDance","cost_per_generation":48.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":2500,"duration_options":["4s","8s","12s"],"aspect_ratio_options":["1:1","21:9","4:3","3:4","16:9","9:16"],"max_input_images":2,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'seedance-1-5-pro-1080p-12s'."},{"model_id":"seedance-1-5-pro-720p-12s","display_name":"Seedance 1.5 Pro","model_type":"video","provider":"ByteDance","cost_per_generation":76.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":2500,"duration_options":["4s","8s","12s"],"aspect_ratio_options":["1:1","21:9","4:3","3:4","16:9","9:16"],"max_input_images":2,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'seedance-1-5-pro-1080p-12s'."},{"model_id":"seedance-1-5-pro-720p-12s-audio","display_name":"Seedance 1.5 Pro","model_type":"video","provider":"ByteDance","cost_per_generation":152.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":2500,"duration_options":["4s","8s","12s"],"aspect_ratio_options":["1:1","21:9","4:3","3:4","16:9","9:16"],"max_input_images":2,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'seedance-1-5-pro-1080p-12s'."},{"model_id":"seedance-1-5-pro-720p-4s","display_name":"Seedance 1.5 Pro","model_type":"video","provider":"ByteDance","cost_per_generation":19.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":2500,"duration_options":["4s","8s","12s"],"aspect_ratio_options":["1:1","21:9","4:3","3:4","16:9","9:16"],"max_input_images":2,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'seedance-1-5-pro-1080p-12s'."},{"model_id":"seedance-1-5-pro-720p-4s-audio","display_name":"Seedance 1.5 Pro","model_type":"video","provider":"ByteDance","cost_per_generation":38.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":2500,"duration_options":["4s","8s","12s"],"aspect_ratio_options":["1:1","21:9","4:3","3:4","16:9","9:16"],"max_input_images":2,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'seedance-1-5-pro-1080p-12s'."},{"model_id":"seedance-1-5-pro-720p-8s","display_name":"Seedance 1.5 Pro","model_type":"video","provider":"ByteDance","cost_per_generation":38.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":2500,"duration_options":["4s","8s","12s"],"aspect_ratio_options":["1:1","21:9","4:3","3:4","16:9","9:16"],"max_input_images":2,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'seedance-1-5-pro-1080p-12s'."},{"model_id":"seedance-1-5-pro-720p-8s-audio","display_name":"Seedance 1.5 Pro","model_type":"video","provider":"ByteDance","cost_per_generation":76.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":2500,"duration_options":["4s","8s","12s"],"aspect_ratio_options":["1:1","21:9","4:3","3:4","16:9","9:16"],"max_input_images":2,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'seedance-1-5-pro-1080p-12s'."},{"model_id":"seedance-2-1080p","display_name":"Seedance 2 (1080p)","model_type":"video","provider":"ByteDance","cost_per_generation":870.0,"estimated_time_seconds":203,"capabilities":{"prompt_max_chars":2500,"duration_options":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"aspect_ratio_options":["adaptive","16:9","4:3","1:1","3:4","9:16","21:9"],"max_input_images":9,"max_input_videos":3,"max_input_audios":3,"input_media_types":["image","video","audio"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param","reference_video_max_s":15.0},"requires_input_media":false,"input_media_types":["image","video","audio"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"This is the higher-quality, slower, more expensive variant of Seedance 2. Pick `seedance-2` when the user wants the best Seedance 2 output, hasn't specified a preference, or asks for 'best quality'/'standard'. For cheaper or faster generation pick `seedance-2-fast`. Both tiers share the same input schema, same edge function, same hard limits — they differ ONLY in internal compute speed and per-second price. There is NO `speed` parameter; the model_id alone selects the tier.\n\nResolutions: 480p, 720p, 1080p, 4K. Duration: integer 4-15 seconds. Aspect: 1:1 / 4:3 / 3:4 / 16:9 / 9:16 / 21:9 / adaptive.\n\nModes:\n  (1) text-to-video — multimodal reference: up to 9 images + 3 videos + 3 audio, all optional.   Use source_media_urls for ALL reference media; the backend classifies each URL by file extension   into images / videos / audio automatically (.jpg .png .webp image; .mp4 .mov .webm video; .mp3 .wav   .m4a audio). Combined reference video duration ≤ 15s, combined reference audio duration ≤ 15s.\n  (2) image-to-video — pass 1 image URL (first frame) in source_media_urls; optional 2nd image   (last frame) for keyframe interpolation; optional up to 3 audio URLs. No reference videos allowed   in this mode.\n\nBILLING — two pricing paths:\n  • NO reference video → flat-rate output billing: credits = duration_seconds × base_credits_per_second.\n  • WITH reference video → credits = (output_duration + ref_video_total) × base_credits_per_second.   The `ref_video_total` is capped at 15s per request. The MCP layer assumes the pessimistic worst   case (15s) for reference videos, so ref-video requests are billed at `(duration + 15) × rate`   from the MCP agent's perspective. To get exact billing on a short reference clip, use the web UI.\n\nStandard-tier rate per second (this model):\n  seedance-2-480p                22 cr/s (no video ref)\n  seedance-2-720p                39 cr/s (no video ref)\n  seedance-2-1080p               87 cr/s (no video ref)\n  seedance-2-4k                  179 cr/s (no video ref)\n  seedance-2-480p-video-ref      17 cr/s (with reference video)\n  seedance-2-720p-video-ref      29 cr/s (with reference video)\n  seedance-2-1080p-video-ref     55 cr/s (with reference video)\n  seedance-2-4k-video-ref        112 cr/s (with reference video)\n\nFast-tier rate for comparison (use `seedance-2-fast` instead if picking that tier):\n  seedance-2-fast-480p           19 cr/s\n  seedance-2-fast-720p           31 cr/s\n  seedance-2-fast-480p-video-ref 15 cr/s\n  seedance-2-fast-720p-video-ref 22 cr/s\n\nAUDIO: ON by default and FREE (no surcharge, unlike Kling 3.0). The `sound` flag defaults to true; pass sound=false only if you want a silent clip. Silencing costs the same credits and just drops the audio track.\n\nHard limits (rejected with 400): >3 videos, >3 audios, >9 images, >15s combined ref video, >15s combined ref audio. Each single reference video/audio file must also be ≤15s.","cost_note":"Credits are PER SECOND: 87.0/s. Example: 10s video = 870.0 credits. Attaching a reference video switches to the video-ref pricing row (credits = (ref_video_seconds + output_seconds) × rate, capped at 15s ref)."},{"model_id":"seedance-2-1080p-video-ref","display_name":"Seedance 2 (1080p, video ref)","model_type":"video","provider":"ByteDance","cost_per_generation":825.0,"estimated_time_seconds":203,"capabilities":{"prompt_max_chars":2500,"duration_options":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"aspect_ratio_options":["adaptive","16:9","4:3","1:1","3:4","9:16","21:9"],"max_input_images":9,"max_input_videos":3,"max_input_audios":3,"input_media_types":["image","video","audio"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param","reference_video_max_s":15.0},"requires_input_media":false,"input_media_types":["image","video","audio"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'seedance-2-1080p'.","cost_note":"Credits are PER SECOND with a REFERENCE VIDEO formula: credits = (ref_video_seconds + output_seconds) × 55.0/s. Example: 5s ref + 10s output = (5 + 10) × 55.0 = 825.0 credits. BILLING: uses the EXACT reference video duration when the file was uploaded via /v1/upload/media or the Kubeez upload portal (we store client-probed metadata at upload time). Third-party URLs with no metadata fall back to a pessimistic 15s cap → worst case for this example = 1375.0 credits. Ref total always clamped at 15s."},{"model_id":"seedance-2-480p","display_name":"Seedance 2 (480p)","model_type":"video","provider":"ByteDance","cost_per_generation":220.0,"estimated_time_seconds":203,"capabilities":{"prompt_max_chars":2500,"duration_options":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"aspect_ratio_options":["adaptive","16:9","4:3","1:1","3:4","9:16","21:9"],"max_input_images":9,"max_input_videos":3,"max_input_audios":3,"input_media_types":["image","video","audio"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param","reference_video_max_s":15.0},"requires_input_media":false,"input_media_types":["image","video","audio"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'seedance-2-1080p'.","cost_note":"Credits are PER SECOND: 22.0/s. Example: 10s video = 220.0 credits. Attaching a reference video switches to the video-ref pricing row (credits = (ref_video_seconds + output_seconds) × rate, capped at 15s ref)."},{"model_id":"seedance-2-480p-video-ref","display_name":"Seedance 2 (480p, video ref)","model_type":"video","provider":"ByteDance","cost_per_generation":255.0,"estimated_time_seconds":203,"capabilities":{"prompt_max_chars":2500,"duration_options":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"aspect_ratio_options":["adaptive","16:9","4:3","1:1","3:4","9:16","21:9"],"max_input_images":9,"max_input_videos":3,"max_input_audios":3,"input_media_types":["image","video","audio"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param","reference_video_max_s":15.0},"requires_input_media":false,"input_media_types":["image","video","audio"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'seedance-2-1080p'.","cost_note":"Credits are PER SECOND with a REFERENCE VIDEO formula: credits = (ref_video_seconds + output_seconds) × 17.0/s. Example: 5s ref + 10s output = (5 + 10) × 17.0 = 255.0 credits. BILLING: uses the EXACT reference video duration when the file was uploaded via /v1/upload/media or the Kubeez upload portal (we store client-probed metadata at upload time). Third-party URLs with no metadata fall back to a pessimistic 15s cap → worst case for this example = 425.0 credits. Ref total always clamped at 15s."},{"model_id":"seedance-2-4k","display_name":"Seedance 2 (4K)","model_type":"video","provider":"ByteDance","cost_per_generation":2600.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":2500,"duration_options":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"aspect_ratio_options":["adaptive","16:9","4:3","1:1","3:4","9:16","21:9"],"max_input_images":9,"max_input_videos":3,"max_input_audios":3,"input_media_types":["image","video","audio"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param","reference_video_max_s":15.0},"requires_input_media":false,"input_media_types":["image","video","audio"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'seedance-2-1080p'.","cost_note":"Credits are PER SECOND: 260.0/s. Example: 10s video = 2600.0 credits. Attaching a reference video switches to the video-ref pricing row (credits = (ref_video_seconds + output_seconds) × rate, capped at 15s ref)."},{"model_id":"seedance-2-4k-video-ref","display_name":"Seedance 2 (4K, video ref)","model_type":"video","provider":"ByteDance","cost_per_generation":2475.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":2500,"duration_options":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"aspect_ratio_options":["adaptive","16:9","4:3","1:1","3:4","9:16","21:9"],"max_input_images":9,"max_input_videos":3,"max_input_audios":3,"input_media_types":["image","video","audio"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param","reference_video_max_s":15.0},"requires_input_media":false,"input_media_types":["image","video","audio"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'seedance-2-1080p'.","cost_note":"Credits are PER SECOND with a REFERENCE VIDEO formula: credits = (ref_video_seconds + output_seconds) × 165.0/s. Example: 5s ref + 10s output = (5 + 10) × 165.0 = 2475.0 credits. BILLING: uses the EXACT reference video duration when the file was uploaded via /v1/upload/media or the Kubeez upload portal (we store client-probed metadata at upload time). Third-party URLs with no metadata fall back to a pessimistic 15s cap → worst case for this example = 4125.0 credits. Ref total always clamped at 15s."},{"model_id":"seedance-2-720p","display_name":"Seedance 2 (720p)","model_type":"video","provider":"ByteDance","cost_per_generation":390.0,"estimated_time_seconds":203,"capabilities":{"prompt_max_chars":2500,"duration_options":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"aspect_ratio_options":["adaptive","16:9","4:3","1:1","3:4","9:16","21:9"],"max_input_images":9,"max_input_videos":3,"max_input_audios":3,"input_media_types":["image","video","audio"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param","reference_video_max_s":15.0},"requires_input_media":false,"input_media_types":["image","video","audio"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'seedance-2-1080p'.","cost_note":"Credits are PER SECOND: 39.0/s. Example: 10s video = 390.0 credits. Attaching a reference video switches to the video-ref pricing row (credits = (ref_video_seconds + output_seconds) × rate, capped at 15s ref)."},{"model_id":"seedance-2-720p-video-ref","display_name":"Seedance 2 (720p, video ref)","model_type":"video","provider":"ByteDance","cost_per_generation":435.0,"estimated_time_seconds":203,"capabilities":{"prompt_max_chars":2500,"duration_options":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"aspect_ratio_options":["adaptive","16:9","4:3","1:1","3:4","9:16","21:9"],"max_input_images":9,"max_input_videos":3,"max_input_audios":3,"input_media_types":["image","video","audio"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param","reference_video_max_s":15.0},"requires_input_media":false,"input_media_types":["image","video","audio"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'seedance-2-1080p'.","cost_note":"Credits are PER SECOND with a REFERENCE VIDEO formula: credits = (ref_video_seconds + output_seconds) × 29.0/s. Example: 5s ref + 10s output = (5 + 10) × 29.0 = 435.0 credits. BILLING: uses the EXACT reference video duration when the file was uploaded via /v1/upload/media or the Kubeez upload portal (we store client-probed metadata at upload time). Third-party URLs with no metadata fall back to a pessimistic 15s cap → worst case for this example = 725.0 credits. Ref total always clamped at 15s."},{"model_id":"seedance-2-fast-480p","display_name":"Seedance 2.0 Fast","model_type":"video","provider":"ByteDance","cost_per_generation":190.0,"estimated_time_seconds":133,"capabilities":{"prompt_max_chars":2500,"duration_options":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"aspect_ratio_options":["adaptive","16:9","4:3","1:1","3:4","9:16","21:9"],"max_input_images":9,"max_input_videos":3,"max_input_audios":3,"input_media_types":["image","video","audio"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param","reference_video_max_s":15.0},"requires_input_media":false,"input_media_types":["image","video","audio"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"This is the cheaper, faster variant of Seedance 2. Pick `seedance-2-fast` when the user wants lower cost, quick turnaround, drafts, bulk runs, or explicitly asks for 'fast' / 'cheap'. For higher-fidelity output prefer `seedance-2` (standard tier). Both tiers share the same input schema, same edge function, same hard limits — they differ ONLY in internal compute speed and per-second price. There is NO `speed` parameter; the model_id alone selects the tier.\n\nResolutions: 480p, 720p (1080p and 4K are standard-tier only — use `seedance-2`). Duration: integer 4-15 seconds. Aspect: 1:1 / 4:3 / 3:4 / 16:9 / 9:16 / 21:9 / adaptive.\n\nModes:\n  (1) text-to-video — multimodal reference: up to 9 images + 3 videos + 3 audio, all optional.   Use source_media_urls for ALL reference media; the backend classifies each URL by file extension   into images / videos / audio automatically (.jpg .png .webp image; .mp4 .mov .webm video; .mp3 .wav   .m4a audio). Combined reference video duration ≤ 15s, combined reference audio duration ≤ 15s.\n  (2) image-to-video — pass 1 image URL (first frame) in source_media_urls; optional 2nd image   (last frame) for keyframe interpolation; optional up to 3 audio URLs. No reference videos allowed   in this mode.\n\nBILLING — two pricing paths:\n  • NO reference video → flat-rate output billing: credits = duration_seconds × base_credits_per_second.\n  • WITH reference video → credits = (output_duration + ref_video_total) ×   base_credits_per_second. The `ref_video_total` is the sum of all reference video durations in seconds,   capped at 15s per request. The MCP layer can NOT probe video durations, so it tells the edge function   to assume the pessimistic worst case (15s) — meaning Seedance 2 generations WITH a reference video   are billed at `(duration + 15) × rate` from the MCP agent's perspective. To get exact billing on a   short reference clip, use the web UI.\n\nFast-tier rate per second (this model):\n  seedance-2-fast-480p           19 cr/s (no video ref)\n  seedance-2-fast-720p           31 cr/s (no video ref)\n  seedance-2-fast-480p-video-ref 15 cr/s (with reference video)\n  seedance-2-fast-720p-video-ref 22 cr/s (with reference video)\n\nStandard-tier rate for comparison (use `seedance-2` instead if picking that tier):\n  seedance-2-480p                22 cr/s\n  seedance-2-720p                39 cr/s\n  seedance-2-1080p               87 cr/s\n  seedance-2-4k                  179 cr/s\n  seedance-2-480p-video-ref      17 cr/s\n  seedance-2-720p-video-ref      29 cr/s\n  seedance-2-1080p-video-ref     55 cr/s\n  seedance-2-4k-video-ref        112 cr/s\n\nAUDIO: ON by default and FREE (no surcharge, unlike Kling 3.0). The `sound` flag defaults to true; pass sound=false only if you want a silent clip. Silencing costs the same credits and just drops the audio track.\n\nHard limits (rejected with 400): >3 videos, >3 audios, >9 images, >15s combined ref video, >15s combined ref audio. Each single reference video/audio file must also be ≤15s.","cost_note":"Credits are PER SECOND: 19.0/s. Example: 10s video = 190.0 credits. Attaching a reference video switches to the video-ref pricing row (credits = (ref_video_seconds + output_seconds) × rate, capped at 15s ref)."},{"model_id":"seedance-2-fast-480p-video-ref","display_name":"Seedance 2.0 Fast","model_type":"video","provider":"ByteDance","cost_per_generation":225.0,"estimated_time_seconds":133,"capabilities":{"prompt_max_chars":2500,"duration_options":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"aspect_ratio_options":["adaptive","16:9","4:3","1:1","3:4","9:16","21:9"],"max_input_images":9,"max_input_videos":3,"max_input_audios":3,"input_media_types":["image","video","audio"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param","reference_video_max_s":15.0},"requires_input_media":false,"input_media_types":["image","video","audio"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'seedance-2-fast-480p'.","cost_note":"Credits are PER SECOND with a REFERENCE VIDEO formula: credits = (ref_video_seconds + output_seconds) × 15.0/s. Example: 5s ref + 10s output = (5 + 10) × 15.0 = 225.0 credits. BILLING: uses the EXACT reference video duration when the file was uploaded via /v1/upload/media or the Kubeez upload portal (we store client-probed metadata at upload time). Third-party URLs with no metadata fall back to a pessimistic 15s cap → worst case for this example = 375.0 credits. Ref total always clamped at 15s."},{"model_id":"seedance-2-fast-720p","display_name":"Seedance 2.0 Fast","model_type":"video","provider":"ByteDance","cost_per_generation":310.0,"estimated_time_seconds":133,"capabilities":{"prompt_max_chars":2500,"duration_options":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"aspect_ratio_options":["adaptive","16:9","4:3","1:1","3:4","9:16","21:9"],"max_input_images":9,"max_input_videos":3,"max_input_audios":3,"input_media_types":["image","video","audio"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param","reference_video_max_s":15.0},"requires_input_media":false,"input_media_types":["image","video","audio"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'seedance-2-fast-480p'.","cost_note":"Credits are PER SECOND: 31.0/s. Example: 10s video = 310.0 credits. Attaching a reference video switches to the video-ref pricing row (credits = (ref_video_seconds + output_seconds) × rate, capped at 15s ref)."},{"model_id":"seedance-2-fast-720p-video-ref","display_name":"Seedance 2.0 Fast","model_type":"video","provider":"ByteDance","cost_per_generation":330.0,"estimated_time_seconds":133,"capabilities":{"prompt_max_chars":2500,"duration_options":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"aspect_ratio_options":["adaptive","16:9","4:3","1:1","3:4","9:16","21:9"],"max_input_images":9,"max_input_videos":3,"max_input_audios":3,"input_media_types":["image","video","audio"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param","reference_video_max_s":15.0},"requires_input_media":false,"input_media_types":["image","video","audio"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'seedance-2-fast-480p'.","cost_note":"Credits are PER SECOND with a REFERENCE VIDEO formula: credits = (ref_video_seconds + output_seconds) × 22.0/s. Example: 5s ref + 10s output = (5 + 10) × 22.0 = 330.0 credits. BILLING: uses the EXACT reference video duration when the file was uploaded via /v1/upload/media or the Kubeez upload portal (we store client-probed metadata at upload time). Third-party URLs with no metadata fall back to a pessimistic 15s cap → worst case for this example = 550.0 credits. Ref total always clamped at 15s."},{"model_id":"seedance-2-mini-480p","display_name":"Seedance 2.0 Mini","model_type":"video","provider":"ByteDance","cost_per_generation":120.0,"estimated_time_seconds":103,"capabilities":{"prompt_max_chars":2500,"duration_options":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"aspect_ratio_options":["adaptive","16:9","4:3","1:1","3:4","9:16","21:9"],"max_input_images":9,"max_input_videos":3,"max_input_audios":3,"input_media_types":["image","video","audio"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param","reference_video_max_s":15.0},"requires_input_media":false,"input_media_types":["image","video","audio"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"This is the CHEAPEST variant of Seedance 2 — a separate model with the same multimodal capabilities as `seedance-2-fast` / `seedance-2`, at roughly half the cost. Pick `seedance-2-mini` for high-frequency / bulk / cost-sensitive jobs: e-commerce content, batch marketing assets, UGC, and special-effects clips where budget matters more than maximum fidelity. For higher quality prefer `seedance-2-fast` (mid) or `seedance-2` (best). All three share the same input schema, same edge function, same hard limits — they differ ONLY in compute speed and per-second price. The tier is selected by model_id (the edge function maps it to the provider speed param).\n\nResolutions: 480p, 720p ONLY (no 1080p, no 4K — use `seedance-2` for those). Duration: integer 4-15 seconds. Aspect: 1:1 / 4:3 / 3:4 / 16:9 / 9:16 / 21:9 / adaptive.\n\nModes:\n  (1) text-to-video — multimodal reference: up to 9 images + 3 videos + 3 audio, all optional.   Combined reference video duration ≤ 15s, combined reference audio duration ≤ 15s.\n  (2) image-to-video — exactly 2 images (first + last frame) for keyframe interpolation; optional   up to 3 audio URLs. No reference videos allowed in this mode.\n\nBILLING — two pricing paths:\n  • NO reference video → flat-rate output billing: credits = duration_seconds × base_credits_per_second.\n  • WITH reference video → credits = (output_duration + ref_video_total) × base_credits_per_second,   ref_video_total capped at 15s per request.\n\nMini-tier rate per second (this model):\n  seedance-2-mini-480p           12 cr/s (no video ref)\n  seedance-2-mini-720p           24 cr/s (no video ref)\n  seedance-2-mini-480p-video-ref  8 cr/s (with reference video)\n  seedance-2-mini-720p-video-ref 15 cr/s (with reference video)\n\nAUDIO: ON by default and FREE (no surcharge). The `sound` flag defaults to true; pass sound=false only if you want a silent clip.\n\nHard limits (rejected with 400): >3 videos, >3 audios, >9 images, >15s combined ref video, >15s combined ref audio. Each single reference video/audio file must also be ≤15s.","cost_note":"Credits are PER SECOND: 12.0/s. Example: 10s video = 120.0 credits. Attaching a reference video switches to the video-ref pricing row (credits = (ref_video_seconds + output_seconds) × rate, capped at 15s ref)."},{"model_id":"seedance-2-mini-480p-video-ref","display_name":"Seedance 2.0 Mini","model_type":"video","provider":"ByteDance","cost_per_generation":120.0,"estimated_time_seconds":103,"capabilities":{"prompt_max_chars":2500,"duration_options":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"aspect_ratio_options":["adaptive","16:9","4:3","1:1","3:4","9:16","21:9"],"max_input_images":9,"max_input_videos":3,"max_input_audios":3,"input_media_types":["image","video","audio"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param","reference_video_max_s":15.0},"requires_input_media":false,"input_media_types":["image","video","audio"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'seedance-2-mini-480p'.","cost_note":"Credits are PER SECOND with a REFERENCE VIDEO formula: credits = (ref_video_seconds + output_seconds) × 8.0/s. Example: 5s ref + 10s output = (5 + 10) × 8.0 = 120.0 credits. BILLING: uses the EXACT reference video duration when the file was uploaded via /v1/upload/media or the Kubeez upload portal (we store client-probed metadata at upload time). Third-party URLs with no metadata fall back to a pessimistic 15s cap → worst case for this example = 200.0 credits. Ref total always clamped at 15s."},{"model_id":"seedance-2-mini-720p","display_name":"Seedance 2.0 Mini","model_type":"video","provider":"ByteDance","cost_per_generation":240.0,"estimated_time_seconds":103,"capabilities":{"prompt_max_chars":2500,"duration_options":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"aspect_ratio_options":["adaptive","16:9","4:3","1:1","3:4","9:16","21:9"],"max_input_images":9,"max_input_videos":3,"max_input_audios":3,"input_media_types":["image","video","audio"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param","reference_video_max_s":15.0},"requires_input_media":false,"input_media_types":["image","video","audio"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'seedance-2-mini-480p'.","cost_note":"Credits are PER SECOND: 24.0/s. Example: 10s video = 240.0 credits. Attaching a reference video switches to the video-ref pricing row (credits = (ref_video_seconds + output_seconds) × rate, capped at 15s ref)."},{"model_id":"seedance-2-mini-720p-video-ref","display_name":"Seedance 2.0 Mini","model_type":"video","provider":"ByteDance","cost_per_generation":225.0,"estimated_time_seconds":103,"capabilities":{"prompt_max_chars":2500,"duration_options":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"aspect_ratio_options":["adaptive","16:9","4:3","1:1","3:4","9:16","21:9"],"max_input_images":9,"max_input_videos":3,"max_input_audios":3,"input_media_types":["image","video","audio"],"supports_negative_prompt":false,"supports_sound":true,"video_audio":"toggle_via_sound_param","reference_video_max_s":15.0},"requires_input_media":false,"input_media_types":["image","video","audio"],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'seedance-2-mini-480p'.","cost_note":"Credits are PER SECOND with a REFERENCE VIDEO formula: credits = (ref_video_seconds + output_seconds) × 15.0/s. Example: 5s ref + 10s output = (5 + 10) × 15.0 = 225.0 credits. BILLING: uses the EXACT reference video duration when the file was uploaded via /v1/upload/media or the Kubeez upload portal (we store client-probed metadata at upload time). Third-party URLs with no metadata fall back to a pessimistic 15s cap → worst case for this example = 375.0 credits. Ref total always clamped at 15s."},{"model_id":"v1-pro-fast-i2v-1080p-10s","display_name":"Seedance 1.0","model_type":"video","provider":"ByteDance","cost_per_generation":130.0,"estimated_time_seconds":36,"capabilities":{"prompt_max_chars":5000,"duration_options":["5s","10s"],"max_input_images":1,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"silent"},"requires_input_media":true,"input_media_types":["image"],"generation_types":["image-to-video"],"usage_notes":"Silent output only. Seedance 1.0 (model_id: v1-pro-fast-i2v). Image-to-video only. Require source_media_urls with exactly one image URL. duration 5s or 10s. No generated audio: silent video only (unlike most other video models)."},{"model_id":"v1-pro-fast-i2v-1080p-5s","display_name":"Seedance 1.0","model_type":"video","provider":"ByteDance","cost_per_generation":80.0,"estimated_time_seconds":36,"capabilities":{"prompt_max_chars":5000,"duration_options":["5s","10s"],"max_input_images":1,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"silent"},"requires_input_media":true,"input_media_types":["image"],"generation_types":["image-to-video"],"usage_notes":"Same usage notes as 'v1-pro-fast-i2v-1080p-10s'."},{"model_id":"v1-pro-fast-i2v-720p-10s","display_name":"Seedance 1.0","model_type":"video","provider":"ByteDance","cost_per_generation":80.0,"estimated_time_seconds":36,"capabilities":{"prompt_max_chars":5000,"duration_options":["5s","10s"],"max_input_images":1,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"silent"},"requires_input_media":true,"input_media_types":["image"],"generation_types":["image-to-video"],"usage_notes":"Same usage notes as 'v1-pro-fast-i2v-1080p-10s'."},{"model_id":"v1-pro-fast-i2v-720p-5s","display_name":"Seedance 1.0","model_type":"video","provider":"ByteDance","cost_per_generation":40.0,"estimated_time_seconds":36,"capabilities":{"prompt_max_chars":5000,"duration_options":["5s","10s"],"max_input_images":1,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"silent"},"requires_input_media":true,"input_media_types":["image"],"generation_types":["image-to-video"],"usage_notes":"Same usage notes as 'v1-pro-fast-i2v-1080p-10s'."},{"model_id":"veo3-1-fast-first-and-last-frames","display_name":"Veo 3.1 Fast First-and-Last-Frames","model_type":"video","provider":"Google","cost_per_generation":75.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":5000,"duration_options":["8s"],"aspect_ratio_options":["16:9","9:16"],"resolution_options":["720p","1080p","4k"],"max_input_images":2,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["first-and-last-frames"],"usage_notes":"First + last frame variant. Pass EXACTLY 2 images in source_media_urls — index 0 = start frame, index 1 = end frame. The model interpolates motion between them. Audio is always included. Duration is automatic."},{"model_id":"veo3-1-fast-first-and-last-frames-1080p","display_name":"Veo 3.1 Fast First and last frames (1080p)","model_type":"video","provider":"Google","cost_per_generation":90.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":5000,"duration_options":["8s"],"aspect_ratio_options":["16:9","9:16"],"resolution_options":["720p","1080p","4k"],"max_input_images":2,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["first-and-last-frames"],"usage_notes":"Same usage notes as 'veo3-1-fast-first-and-last-frames'."},{"model_id":"veo3-1-fast-first-and-last-frames-4k","display_name":"Veo 3.1 Fast First and last frames (4K)","model_type":"video","provider":"Google","cost_per_generation":220.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":5000,"duration_options":["8s"],"aspect_ratio_options":["16:9","9:16"],"resolution_options":["720p","1080p","4k"],"max_input_images":2,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["first-and-last-frames"],"usage_notes":"Same usage notes as 'veo3-1-fast-first-and-last-frames'."},{"model_id":"veo3-1-fast-reference-to-video","display_name":"Veo 3.1 Fast Reference-to-Video","model_type":"video","provider":"Google","cost_per_generation":75.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":5000,"duration_options":["8s"],"aspect_ratio_options":["16:9"],"resolution_options":["720p","1080p","4k"],"max_input_images":3,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["reference-to-video"],"usage_notes":"Reference-to-video variant. Pass 1-3 reference images in source_media_urls — the model uses them to guide the visual style of the generated video. Aspect ratio is LOCKED to 16:9 (any other value is ignored by the backend). Audio is always included. Duration is automatic (not configurable)."},{"model_id":"veo3-1-fast-reference-to-video-1080p","display_name":"Veo 3.1 Fast Reference to video (1080p)","model_type":"video","provider":"Google","cost_per_generation":90.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":5000,"duration_options":["8s"],"aspect_ratio_options":["16:9"],"resolution_options":["720p","1080p","4k"],"max_input_images":3,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["reference-to-video"],"usage_notes":"Same usage notes as 'veo3-1-fast-reference-to-video'."},{"model_id":"veo3-1-fast-reference-to-video-4k","display_name":"Veo 3.1 Fast Reference to video (4K)","model_type":"video","provider":"Google","cost_per_generation":220.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":5000,"duration_options":["8s"],"aspect_ratio_options":["16:9"],"resolution_options":["720p","1080p","4k"],"max_input_images":3,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["reference-to-video"],"usage_notes":"Same usage notes as 'veo3-1-fast-reference-to-video'."},{"model_id":"veo3-1-fast-text-to-video","display_name":"Veo 3.1 Fast Text-to-Video","model_type":"video","provider":"Google","cost_per_generation":75.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":5000,"duration_options":["8s"],"aspect_ratio_options":["16:9","9:16"],"resolution_options":["720p","1080p","4k"],"max_input_images":0,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["text-to-video"],"usage_notes":"Text-to-video variant. Prompt only — no input images are consumed by this variant (if you need image inputs, use the first-and-last-frames or reference-to-video variant). Audio is always included. Duration is automatic."},{"model_id":"veo3-1-fast-text-to-video-1080p","display_name":"Veo 3.1 Fast Text to video (1080p)","model_type":"video","provider":"Google","cost_per_generation":90.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":5000,"duration_options":["8s"],"aspect_ratio_options":["16:9","9:16"],"resolution_options":["720p","1080p","4k"],"max_input_images":0,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["text-to-video"],"usage_notes":"Same usage notes as 'veo3-1-fast-text-to-video'."},{"model_id":"veo3-1-fast-text-to-video-4k","display_name":"Veo 3.1 Fast Text to video (4K)","model_type":"video","provider":"Google","cost_per_generation":220.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":5000,"duration_options":["8s"],"aspect_ratio_options":["16:9","9:16"],"resolution_options":["720p","1080p","4k"],"max_input_images":0,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["text-to-video"],"usage_notes":"Same usage notes as 'veo3-1-fast-text-to-video'."},{"model_id":"veo3-1-first-and-last-frames","display_name":"Veo 3.1 Quality First-and-Last-Frames","model_type":"video","provider":"Google","cost_per_generation":300.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":5000,"duration_options":["8s"],"aspect_ratio_options":["16:9","9:16"],"resolution_options":["720p","1080p","4k"],"max_input_images":2,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["first-and-last-frames"],"usage_notes":"Same usage notes as 'veo3-1-fast-first-and-last-frames'."},{"model_id":"veo3-1-first-and-last-frames-1080p","display_name":"Veo 3.1 Quality First and last frames (1080p)","model_type":"video","provider":"Google","cost_per_generation":320.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":5000,"duration_options":["8s"],"aspect_ratio_options":["16:9","9:16"],"resolution_options":["720p","1080p","4k"],"max_input_images":2,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["first-and-last-frames"],"usage_notes":"Same usage notes as 'veo3-1-fast-first-and-last-frames'."},{"model_id":"veo3-1-first-and-last-frames-4k","display_name":"Veo 3.1 Quality First and last frames (4K)","model_type":"video","provider":"Google","cost_per_generation":420.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":5000,"duration_options":["8s"],"aspect_ratio_options":["16:9","9:16"],"resolution_options":["720p","1080p","4k"],"max_input_images":2,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["first-and-last-frames"],"usage_notes":"Same usage notes as 'veo3-1-fast-first-and-last-frames'."},{"model_id":"veo3-1-lite-first-and-last-frames","display_name":"Veo 3.1 Lite — First and last frames","model_type":"video","provider":"Google","cost_per_generation":45.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":5000,"duration_options":["8s"],"aspect_ratio_options":["16:9","9:16"],"resolution_options":["720p","1080p","4k"],"max_input_images":2,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["first-and-last-frames"],"usage_notes":"Same usage notes as 'veo3-1-fast-first-and-last-frames'."},{"model_id":"veo3-1-lite-first-and-last-frames-1080p","display_name":"Veo 3.1 Lite First and last frames (1080p)","model_type":"video","provider":"Google","cost_per_generation":50.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":5000,"duration_options":["8s"],"aspect_ratio_options":["16:9","9:16"],"resolution_options":["720p","1080p","4k"],"max_input_images":2,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["first-and-last-frames"],"usage_notes":"Same usage notes as 'veo3-1-fast-first-and-last-frames'."},{"model_id":"veo3-1-lite-first-and-last-frames-4k","display_name":"Veo 3.1 Lite First and last frames (4K)","model_type":"video","provider":"Google","cost_per_generation":190.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":5000,"duration_options":["8s"],"aspect_ratio_options":["16:9","9:16"],"resolution_options":["720p","1080p","4k"],"max_input_images":2,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["first-and-last-frames"],"usage_notes":"Same usage notes as 'veo3-1-fast-first-and-last-frames'."},{"model_id":"veo3-1-lite-reference-to-video","display_name":"Veo 3.1 Lite Reference to video","model_type":"video","provider":"Google","cost_per_generation":45.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":5000,"duration_options":["8s"],"aspect_ratio_options":["16:9"],"resolution_options":["720p","1080p","4k"],"max_input_images":3,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["reference-to-video"],"usage_notes":"Same usage notes as 'veo3-1-fast-reference-to-video'."},{"model_id":"veo3-1-lite-reference-to-video-1080p","display_name":"Veo 3.1 Lite Reference to video (1080p)","model_type":"video","provider":"Google","cost_per_generation":50.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":5000,"duration_options":["8s"],"aspect_ratio_options":["16:9"],"resolution_options":["720p","1080p","4k"],"max_input_images":3,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["reference-to-video"],"usage_notes":"Same usage notes as 'veo3-1-fast-reference-to-video'."},{"model_id":"veo3-1-lite-reference-to-video-4k","display_name":"Veo 3.1 Lite Reference to video (4K)","model_type":"video","provider":"Google","cost_per_generation":190.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":5000,"duration_options":["8s"],"aspect_ratio_options":["16:9"],"resolution_options":["720p","1080p","4k"],"max_input_images":3,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["reference-to-video"],"usage_notes":"Same usage notes as 'veo3-1-fast-reference-to-video'."},{"model_id":"veo3-1-lite-text-to-video","display_name":"Veo 3.1 Lite — Text to video","model_type":"video","provider":"Google","cost_per_generation":45.0,"estimated_time_seconds":130,"capabilities":{"prompt_max_chars":5000,"duration_options":["8s"],"aspect_ratio_options":["16:9","9:16"],"resolution_options":["720p","1080p","4k"],"max_input_images":0,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["text-to-video"],"usage_notes":"Same usage notes as 'veo3-1-fast-text-to-video'."},{"model_id":"veo3-1-lite-text-to-video-1080p","display_name":"Veo 3.1 Lite Text to video (1080p)","model_type":"video","provider":"Google","cost_per_generation":50.0,"estimated_time_seconds":130,"capabilities":{"prompt_max_chars":5000,"duration_options":["8s"],"aspect_ratio_options":["16:9","9:16"],"resolution_options":["720p","1080p","4k"],"max_input_images":0,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["text-to-video"],"usage_notes":"Same usage notes as 'veo3-1-fast-text-to-video'."},{"model_id":"veo3-1-lite-text-to-video-4k","display_name":"Veo 3.1 Lite Text to video (4K)","model_type":"video","provider":"Google","cost_per_generation":190.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":5000,"duration_options":["8s"],"aspect_ratio_options":["16:9","9:16"],"resolution_options":["720p","1080p","4k"],"max_input_images":0,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["text-to-video"],"usage_notes":"Same usage notes as 'veo3-1-fast-text-to-video'."},{"model_id":"veo3-1-text-to-video","display_name":"Veo 3.1 Quality Text-to-Video","model_type":"video","provider":"Google","cost_per_generation":300.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":5000,"duration_options":["8s"],"aspect_ratio_options":["16:9","9:16"],"resolution_options":["720p","1080p","4k"],"max_input_images":0,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["text-to-video"],"usage_notes":"Same usage notes as 'veo3-1-fast-text-to-video'."},{"model_id":"veo3-1-text-to-video-1080p","display_name":"Veo 3.1 Quality Text to video (1080p)","model_type":"video","provider":"Google","cost_per_generation":320.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":5000,"duration_options":["8s"],"aspect_ratio_options":["16:9","9:16"],"resolution_options":["720p","1080p","4k"],"max_input_images":0,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["text-to-video"],"usage_notes":"Same usage notes as 'veo3-1-fast-text-to-video'."},{"model_id":"veo3-1-text-to-video-4k","display_name":"Veo 3.1 Quality Text to video (4K)","model_type":"video","provider":"Google","cost_per_generation":420.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":5000,"duration_options":["8s"],"aspect_ratio_options":["16:9","9:16"],"resolution_options":["720p","1080p","4k"],"max_input_images":0,"input_media_types":["image"],"supports_negative_prompt":false,"supports_sound":false,"video_audio":"included"},"requires_input_media":false,"input_media_types":["image"],"generation_types":["text-to-video"],"usage_notes":"Same usage notes as 'veo3-1-fast-text-to-video'."},{"model_id":"wan-2-5","display_name":"Wan 2.5","model_type":"video","provider":"Alibaba","cost_per_generation":155.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":800,"duration_options":["5s","10s"],"aspect_ratio_options":["16:9","9:16","1:1"],"max_input_images":1,"input_media_types":[],"supports_negative_prompt":true,"supports_sound":false,"video_audio":"included"},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-video","image-to-video"],"usage_notes":"5s/10s, 720p/1080p. Prompt max 800 chars. Text-to-video: omit source_media_urls. Image-to-video: exactly one image URL. duration 5s or 10s. negative_prompt supported. Output includes audio; no sound parameter.","cost_note":"Wan 2.5 cost varies by duration × resolution: 5s 720p = 93 cr, 10s 720p = 186 cr, 5s 1080p = 155 cr, 10s 1080p = 310 cr. Pass duration ('5'|'10') + resolution ('720p'|'1080p') or use a variant id like `wan-2-5-text-to-video-10s-1080p`."},{"model_id":"wan-2-5-image-to-video-10s-1080p","display_name":"Wan 2.5 Image-to-Video (10s 1080p)","model_type":"video","provider":"Alibaba","cost_per_generation":310.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":800,"duration_options":["5s","10s"],"aspect_ratio_options":["16:9","9:16","1:1"],"max_input_images":1,"input_media_types":[],"supports_negative_prompt":true,"supports_sound":false,"video_audio":"included"},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'wan-2-5'."},{"model_id":"wan-2-5-image-to-video-10s-720p","display_name":"Wan 2.5 Image-to-Video (10s 720p)","model_type":"video","provider":"Alibaba","cost_per_generation":186.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":800,"duration_options":["5s","10s"],"aspect_ratio_options":["16:9","9:16","1:1"],"max_input_images":1,"input_media_types":[],"supports_negative_prompt":true,"supports_sound":false,"video_audio":"included"},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'wan-2-5'."},{"model_id":"wan-2-5-image-to-video-5s-1080p","display_name":"Wan 2.5 Image-to-Video (5s 1080p)","model_type":"video","provider":"Alibaba","cost_per_generation":155.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":800,"duration_options":["5s","10s"],"aspect_ratio_options":["16:9","9:16","1:1"],"max_input_images":1,"input_media_types":[],"supports_negative_prompt":true,"supports_sound":false,"video_audio":"included"},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'wan-2-5'."},{"model_id":"wan-2-5-image-to-video-5s-720p","display_name":"Wan 2.5 Image-to-Video (5s 720p)","model_type":"video","provider":"Alibaba","cost_per_generation":93.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":800,"duration_options":["5s","10s"],"aspect_ratio_options":["16:9","9:16","1:1"],"max_input_images":1,"input_media_types":[],"supports_negative_prompt":true,"supports_sound":false,"video_audio":"included"},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'wan-2-5'."},{"model_id":"wan-2-5-text-to-video-10s-1080p","display_name":"Wan 2.5 Text-to-Video (10s 1080p)","model_type":"video","provider":"Alibaba","cost_per_generation":310.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":800,"duration_options":["5s","10s"],"aspect_ratio_options":["16:9","9:16","1:1"],"max_input_images":1,"input_media_types":[],"supports_negative_prompt":true,"supports_sound":false,"video_audio":"included"},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'wan-2-5'."},{"model_id":"wan-2-5-text-to-video-10s-720p","display_name":"Wan 2.5 Text-to-Video (10s 720p)","model_type":"video","provider":"Alibaba","cost_per_generation":186.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":800,"duration_options":["5s","10s"],"aspect_ratio_options":["16:9","9:16","1:1"],"max_input_images":1,"input_media_types":[],"supports_negative_prompt":true,"supports_sound":false,"video_audio":"included"},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'wan-2-5'."},{"model_id":"wan-2-5-text-to-video-5s-1080p","display_name":"Wan 2.5 Text-to-Video (5s 1080p)","model_type":"video","provider":"Alibaba","cost_per_generation":155.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":800,"duration_options":["5s","10s"],"aspect_ratio_options":["16:9","9:16","1:1"],"max_input_images":1,"input_media_types":[],"supports_negative_prompt":true,"supports_sound":false,"video_audio":"included"},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'wan-2-5'."},{"model_id":"wan-2-5-text-to-video-5s-720p","display_name":"Wan 2.5 Text-to-Video (5s 720p)","model_type":"video","provider":"Alibaba","cost_per_generation":93.0,"estimated_time_seconds":120,"capabilities":{"prompt_max_chars":800,"duration_options":["5s","10s"],"aspect_ratio_options":["16:9","9:16","1:1"],"max_input_images":1,"input_media_types":[],"supports_negative_prompt":true,"supports_sound":false,"video_audio":"included"},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'wan-2-5'."},{"model_id":"wan-2-7-1080p","display_name":"Wan 2.7 (1080p)","model_type":"video","provider":"Alibaba","cost_per_generation":27.0,"estimated_time_seconds":235,"capabilities":{"prompt_max_chars":5000,"duration_options":["2s","3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"aspect_ratio_options":["16:9","9:16","1:1","4:3","3:4"],"max_input_images":1,"input_media_types":[],"supports_negative_prompt":true,"supports_sound":false,"video_audio":"included"},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Wan 2.7 — PER-SECOND pricing, priced separately at 720p vs 1080p; read the exact rate live from get_models / estimate (never assume). Free duration 2-15s. Pass the variant id `wan-2-7-720p` or `wan-2-7-1080p` as `model` (resolution is encoded in the id), plus duration (2-15) and generation_type.\n\nModes:\n  - text-to-video → omit source_media_urls; ratio 16:9 / 9:16 / 1:1 / 4:3 / 3:4; optional audio_url for a custom soundtrack.\n  - image-to-video → exactly one image URL in source_media_urls (first frame); optional last_frame_url for a first+last-frame transition.\n\nPrompt max 5000 chars; negative_prompt up to 500. Output includes audio; no sound parameter.","cost_note":"Wan 2.7 is PER-SECOND: credits = round(rate × duration), priced separately at 720p vs 1080p. Read the exact rate live from `get_models` / `estimate` — never assume. Pass the variant id `wan-2-7-720p` or `wan-2-7-1080p` plus duration (2-15s)."},{"model_id":"wan-2-7-720p","display_name":"Wan 2.7 (720p)","model_type":"video","provider":"Alibaba","cost_per_generation":19.0,"estimated_time_seconds":134,"capabilities":{"prompt_max_chars":5000,"duration_options":["2s","3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"aspect_ratio_options":["16:9","9:16","1:1","4:3","3:4"],"max_input_images":1,"input_media_types":[],"supports_negative_prompt":true,"supports_sound":false,"video_audio":"included"},"requires_input_media":false,"input_media_types":[],"generation_types":["text-to-video","image-to-video"],"usage_notes":"Same usage notes as 'wan-2-7-1080p'.","cost_note":"Wan 2.7 is PER-SECOND: credits = round(rate × duration), priced separately at 720p vs 1080p. Read the exact rate live from `get_models` / `estimate` — never assume. Pass the variant id `wan-2-7-720p` or `wan-2-7-1080p` plus duration (2-15s)."}],"total_count":163}