Multimodal video generation. Inspect each provider’s token or duration billing before comparing costs.
Official providers appear first. These are source-listed endpoints, not a ranking: resolutions, modes and billing units can differ.
USD 6.4 / million_tokensInput with video
USD 10.7 / million_tokensInput without video
USD 0.216 / usd_per_secondseedance-2.5 · resolution: default · Source estimate; final token settlement is listed separately.
USD 0.38488 / usd_per_secondseedance-2.5 · resolution: 1080P · Source estimate; final token settlement is listed separately.
USD 0.22992 / usd_per_secondseedance-2.5 · resolution: 1080P-input · Source estimate; final token settlement is listed separately.
USD 0.09608 / usd_per_secondseedance-2.5 · resolution: 480P · Source estimate; final token settlement is listed separately.
USD 0.0576 / usd_per_secondseedance-2.5 · resolution: 480P-input · Source estimate; final token settlement is listed separately.
USD 0.216 / usd_per_secondseedance-2.5 · resolution: 720P · Source estimate; final token settlement is listed separately.
USD 0.1296 / usd_per_secondseedance-2.5 · resolution: 720P-input · Source estimate; final token settlement is listed separately.
USD 10 / usd_per_million_tokensseedance-2.5 · token settlement: token
USD 6 / usd_per_million_tokensseedance-2.5 · token settlement: token-input
USD 7.92 / usd_per_million_tokensseedance-2.5 · token settlement: token-1080P
USD 4.73144 / usd_per_million_tokensseedance-2.5 · token settlement: token-1080P-input
USD 0.3425 / per secondbytedance/seedance-2-5, 1080p with video
USD 0.570 / per secondbytedance/seedance-2-5, 1080p no video
USD 0.190 / per secondbytedance/seedance-2-5, 720p with video
USD 0.315 / per secondbytedance/seedance-2-5, 720p no video
USD 0.085 / per secondbytedance/seedance-2-5, 480p with video
USD 0.140 / per secondbytedance/seedance-2-5, 480p no video
USD 0.0000107 / video_tokensSKU-specific source rate; check resolution, audio and duration before comparing.
USD 0.0000107 / video_tokens_without_audioSKU-specific source rate; check resolution, audio and duration before comparing.
USD 0.0000064 / video_tokens_with_video_inputSKU-specific source rate; check resolution, audio and duration before comparing.
USD $0.1028 / second of output videomodel variant: non_video_in · target resolution: 480p · or around 97 seconds for $10
USD $0.4304 / second of output videomodel variant: video_in · target resolution: 480p · or around 23 seconds for $10
USD $0.2312 / second of output videomodel variant: non_video_in · target resolution: 720p · or around 43 seconds for $10
USD $0.9676 / second of output videomodel variant: video_in · target resolution: 720p · or around 10 seconds for $10
USD 0.1025 / durationSecondText/Image to Video · 480p
USD 0.2304 / durationSecondText/Image to Video · 720p
USD 0.61354 / durationSecondText/Image to Video · 1080p
USD 0.1313 / durationSecondVideo-to-Video · 480p
USD 0.2953 / durationSecondVideo-to-Video · 720p
USD 0.73415 / durationSecondVideo-to-Video · 1080p
USD 0.8100 / source-listed starting priceDisplayed catalog starting price only. Final charge depends on duration, resolution, outputs and references. Not a fixed per-second or per-image quote.
USD 0.8100 / source-listed starting priceDisplayed catalog starting price only. Final charge depends on duration, resolution, outputs and references. Not a fixed per-second or per-image quote.
USD 0.9000 / source-listed starting priceDisplayed catalog starting price only. Final charge depends on duration, resolution, outputs and references. Not a fixed per-second or per-image quote.
USD 0.8100 / source-listed starting priceDisplayed catalog starting price only. Final charge depends on duration, resolution, outputs and references. Not a fixed per-second or per-image quote.
USD 0.9000 / source-listed starting priceDisplayed catalog starting price only. Final charge depends on duration, resolution, outputs and references. Not a fixed per-second or per-image quote.
USD 0.9900 / source-listed starting priceDisplayed catalog starting price only. Final charge depends on duration, resolution, outputs and references. Not a fixed per-second or per-image quote.
USD 1.1700 / source-listed starting priceDisplayed catalog starting price only. Final charge depends on duration, resolution, outputs and references. Not a fixed per-second or per-image quote.
USD 0.9900 / source-listed starting priceDisplayed catalog starting price only. Final charge depends on duration, resolution, outputs and references. Not a fixed per-second or per-image quote.
One vintage forest-green tram glides across an empty bridge at blue hour, reflected in still canal water. The camera tracks parallel at walking speed. Amber cabin lights pass behind dark window frames, faint overhead wire sparks, distant city ambience. Realistic wet stone, restrained film grain, one continuous shot, no readable signs.
A miniature bakery made entirely from felt and wool. A tiny wool fox baker lifts one round loaf from a small oven, and wisps of cotton steam rise above it. Slow stop-motion action, close tabletop lens, warm practical lighting, charming handmade imperfections. No words or logos.
Interior of a small modern library overlooking a rough ocean through a huge circular window. A sheer white curtain lifts in a breeze; sunlight moves across oak shelves. Slow lateral dolly, calm realistic architecture, tactile wood and linen, distant surf sound. No people, book titles or readable text.
More provider-selected examples on the original site. These are demonstrations, not a controlled Vidily benchmark.
Source-listed endpoints and pricing conditions. Variants are not unique base models; account quotes do not enter cheapest-price rankings.
Counts describe collected endpoints, not unique models or a guarantee of complete coverage. Price evidence may be a numeric rate or source billing text. Providers with no published endpoints are still awaiting collection.
25 endpoints · 1/2
Variants listed separately. Open a model to check units and conditions.
BytePlus ModelArk · video
Model sample · made by VidilyDreamina-Seedance-2.5 (official pricing label)Official ModelArk token pricing; input-with-video and input-without-video are different billing modes. Verify the request model ID in the console.
OpenRouter · videoModel sample · made by Vidilybytedance/seedance-2.5Seedance 2.5 is a video generation model from ByteDance. It is suited for long-form storytelling, multimodal reference-based generation, video editing, and video extension. It supports first-frame and
Model sample · made by Vidilybytedance/seedance-2-5, 1080p with videobytedance/seedance-2-5, 1080p with video
Model sample · made by Vidilybytedance/seedance-2-5, 1080p no videobytedance/seedance-2-5, 1080p no video
Model sample · made by Vidilybytedance/seedance-2-5, 720p with videobytedance/seedance-2-5, 720p with video
Model sample · made by Vidilybytedance/seedance-2-5, 720p no videobytedance/seedance-2-5, 720p no video
Model sample · made by Vidilybytedance/seedance-2-5, 480p with videobytedance/seedance-2-5, 480p with video
Model sample · made by Vidilybytedance/seedance-2-5, 480p no videobytedance/seedance-2-5, 480p no video
Model sample · made by Vidilybytedance/seedance-2.5/image-to-videoSeedance 2.5 (Image-to-Video) generates Hollywood-grade cinematic videos from reference images and text prompts with native audio-visual synchronization, director-level camera and lighting control, an
Model sample · made by Vidilybytedance/seedance-2.5/image-to-video-spicySeedance 2.5 Spicy Image to Video is a fast AI image-to-video generation model that creates high-quality cinematic clips from images, optimized for scalable content generation with smooth animations a
Model sample · made by Vidilybytedance/seedance-2.5/image-to-video-turboSeedance 2.5 (Image-to-Video Turbo) generates cinematic 720p/1080p videos from reference images —a faster, more affordable high-resolution tier with native audio-visual synchronization, director-level
Model sample · made by Vidilybytedance/seedance-2.5/text-to-videoSeedance 2.5 (Text-to-Video) generates Hollywood-grade cinematic videos from text prompts with native audio-visual synchronization, director-level camera and lighting control, and exceptional motion s
Model sample · made by Vidilybytedance/seedance-2.5/text-to-video-turboSeedance 2.5 (Text-to-Video Turbo) generates cinematic 720p/1080p videos from text prompts —a faster, more affordable high-resolution tier with native audio-visual synchronization, director-level cont
Model sample · made by Vidilybytedance/seedance-2.5/video-editSeedance 2.5 (Video-Edit) edits an input video from a natural-language prompt. The reference video drives subject identity, composition, and motion while the model rewrites lighting, style, weather, e
Model sample · made by Vidilybytedance/seedance-2.5/video-edit-turboSeedance 2.5 (Video-Edit Turbo) is the turbo tier for editing an input video from a natural-language prompt — faster, more affordable high-resolution output while preserving subject identity, composit
Model sample · made by Vidilybytedance/seedance-2.5/video-extendSeedance 2.5 (Video-Extend) extends an input video with a new cinematic continuation generated from its last frame and a natural-language prompt. Ready-to-use REST API, best performance, no coldstarts
Model sample · made by Vidilybytedance:seedance@2.5Seedance 2.5
fal.ai · videoModel sample · made by Vidilybytedance/seedance-2.5/image-to-videoDreamina Seedance 2.5 animates a single still into a native 30-second clip at up to 720p, extending one frame into continuous, coherent motion without the drift or stitching of shorter multi-clip work
fal.ai · videoModel sample · made by Vidilybytedance/seedance-2.5/reference-to-videoDreamina Seedance 2.5 generates video from up to 50 multimodal references images, video, audio, and style inputs, locking a character, set, and palette across a full 30-second take for production-grad
fal.ai · videoModel sample · made by Vidilybytedance/seedance-2.5/text-to-videoDreamina Seedance 2.5 generates native 30-second single-shot video at up to 720p from a single text prompt, reasoning about the whole shot at once so motion, lighting, and subject identity stay cohere
Model sample · made by Vidilyseedance-2.5seedance-2.5 · per_second
Replicate · videoModel sample · made by Vidilybytedance/seedance-2.5ByteDance's flagship multimodal video model with native audio, native 30-second generation, and large multimodal reference sets.
Runway · videoModel sample · made by Vidilyseedance2_5 (1080p)68 credits per second of output, plus 34 credits per second of input and reference video (combined video capped at 30 seconds); reference images and audio are free (80 credit minimum per generation)
Runway · videoModel sample · made by Vidilyseedance2_5 (480p)20 credits per second of output, plus 10 credits per second of input and reference video (combined video capped at 30 seconds); reference images and audio are free (80 credit minimum per generation)
Choose the exact output configuration above. Estimates use public source rates and show the applicable billing unit. The total is not a guaranteed checkout price.
A model listing proves availability, not a rate. Login-only pricing, missing conditions or stale evidence must be checked before comparison.
No. Comparable estimates are sorted by cost. Advertising belongs in separately labeled positions.