brand-overlay | Brand Overlays | 2 | Add a hook title, a lower-third callout, a review card, a progress bar, a countdown timer, a price tag, an offer badge and a branded end card to any video. Exact text in your brand color. |
flux-3-video | FLUX 3 Video | 25 | FLUX 3 Video generation. Text-to-video or image-to-video up to 20 seconds with synchronized audio, or extend and transform an existing clip. |
google-gemini-omni-flash | Gemini Omni Flash 1.2 | 24 | Google Gemini Omni Flash 1.2: text, frames, references, or a source video into 3–15s clips with native audio at 360p to 4K. First/last frame, reference images and videos, edit or extend a clip. |
grok-r2v | Grok R2V | 10 | xAI Grok Imagine reference-to-video via Replicate. 1 to 7 reference images plus prompt for 1 to 10 second clips at 480p or 720p. |
grok-video-extend | Grok Video Extend | 1.5/sec | xAI Grok Imagine video extension. Continue an existing MP4 with a prompt-directed extension (2 to 10 seconds). |
happyhorse-1.0-r2v | Happy Horse Reference | 4/sec | Alibaba Happy Horse reference-to-video (1.0 or 1.1): multi-reference image input that preserves subject characters, driven by a text prompt. 720p / 1080p, 3-15 second clips. Version 1.1 runs at a lower per-second credit rate. |
happyhorse-1.0-t2v | Happy Horse 1.0 Text-to-Video | 4/sec | Text-to-video with 720p/1080p output and 3-15 second durations |
happyhorse-1.0-i2v | Happy Horse 1.0 Image-to-Video | 4/sec | Image-to-video animation with 720p/1080p output and 3-15 second durations |
happyhorse-1.0-video-edit | Happy Horse Video Edit | 5/sec | Alibaba Happy Horse 1.0 video edit: apply style transfer or local replacement to a source video using text prompts and optional reference images. 720p / 1080p, 3-15 second output. |
heygen-video | HeyGen Video 1.0 | 6.25 | HeyGen Video 1.0 via Runware. Text-to-video or image-to-video with sound built in: spoken dialogue, ambience and effects. 5 to 30 seconds, 480p to 2K. |
kling-4-0 | Kling 4.0 | 25 | Kling Video 4.0. Up to 30 seconds at 1080p with native audio and dialogue: text, start/end frames, reference images and videos, or edit an existing clip. Flash tier: faster and cheaper at 720p, up to 20 seconds. |
kling-avatar | Kling Avatar | 2/sec | Kling Avatar V2: turn a portrait plus an audio file into a talking avatar with audio-driven lip sync. Works on realistic humans, stylized characters, cartoons, and animals. |
kling-motion-control | Kling Motion Control v3 Standard | 3/sec | Kling Video v3 Standard motion control (720p) |
kling-motion-control-pro | Kling Motion Control v3 Pro | 4/sec | Kling Video v3 Pro motion control (1080p) |
kling-reference-to-video | Kling Reference to Video | 15 | Kling reference-driven video generation. Image or video references, Standard or Pro tier. |
kling-v2-6 | Kling 2.6 Pro | 25 | Kling Video v2.6 Pro. Text-to-video or image-to-video, 5 or 10 seconds, with audio generation. |
kling-video-v3-standard-text | Kling Video v3 Standard (Text) | 4/sec | Standard text-to-video with native audio |
kling-video-v3-standard-image | Kling Video v3 Standard (Image) | 4/sec | Standard image-to-video with native audio |
kling-video-v3-pro-text | Kling Video v3 Pro (Text) | 5.5/sec | Pro text-to-video with cinematic quality and native audio |
kling-video-v3-pro-image | Kling Video v3 Pro (Image) | 5.5/sec | Pro image-to-video with cinematic quality and native audio |
kling-video-edit | Kling Video Edit | 28 | Kling video-to-video edit. Standard or Pro, with optional reference images and audio preservation. |
luma-ray-3-2 | Luma Ray3.2 | 10 | Luma Ray3.2 video via Runware. Text-to-video, or image-to-video with a start frame and an optional end frame. 5 or 10 seconds, 360p to 1080p, silent. |
minimax-h3 | MiniMax H3 | 4/sec | MiniMax H3: text-to-video, image-to-video, and reference-to-video (images, video and audio references) in one model. 2K or 768p output, 5-15s, native synced audio. Also carries H3 Max (cheaper 768p/480p, frames only), H3 Max Turbo (faster, tiered 768p/480p, frames only) and H3 Fast (480p, references). |
minimax-h3-max | MiniMax H3 Max | 2/sec | MiniMax H3 Max, the cheaper H3 sibling. Text-to-video and image-to-video at 768p (2 credits/sec) or 480p (1.5 credits/sec), 5-15s, native synced audio. No reference inputs. |
minimax-h3-max-turbo | MiniMax H3 Max Turbo | 1.25/sec | MiniMax H3 Max Turbo, the distilled, faster H3 Max. Text-to-video and image-to-video at 768p (1.25 credits/sec) or 480p (0.9 credits/sec), 5-15s, native synced audio. No reference inputs. |
minimax-h3-fast | MiniMax H3 Fast | 1.5/sec | MiniMax H3 Fast, the speed-optimized H3. Text-to-video, image-to-video and reference-to-video (images, video and audio references) at 480p, 1.5 credits/sec plus 1.75 credits per second of reference video (at most 15s) and 1 per reference image past the fifth, 5-15s, native synced audio. |
minimax-h3-turbo | MiniMax H3 Turbo | 7.5 | MiniMax H3 open weights, self-hosted with a step-distillation Turbo LoRA for fast, low-cost generation. Text, image, or reference to video at 480p or 720p with synced audio. |
omnihuman | OmniHuman | 5/sec | ByteDance OmniHuman 2.0. Audio-driven talking-head video with lip sync, up to 2 minutes. |
p-video | P-Video | 0.75/sec | Pruna P-Video 2 (and P-Video 1): video generation with text/image/audio conditioning, draft mode, and 720p/1080p outputs. |
p-video-2-pro | P-Video 2 Pro | 1/sec | Pruna P-Video 2 Pro: text or image to video with generated audio, 5 to 15 seconds at 24 fps, with start and end frame control. |
p-video-2-pro-reference | P-Video 2 Pro Reference | 1.25/sec | Pruna P-Video 2 Pro Reference: reference-to-video built on MiniMax H3. Up to 9 images, 3 video and 3 audio references, plus optional start and end frames, 480p or 768p, 5 to 15 seconds with native audio. keep_audio lip-syncs to your own song or line. |
p-video-2-pro-replace | P-Video 2 Pro Replace | 3/sec | Pruna P-Video 2 Pro Replace, built on MiniMax H3: swap one or two people in a video for the people in your pictures. Motion, camera, background, everyone else and the sound stay as they were. Up to 120 seconds, 480p or 768p. |
p-video-avatar | P-Video Avatar | 1/sec | Pruna P-Video 2 Pro Avatar: animate a portrait into a talking avatar from a script or an audio file, up to 3 minutes. 30 voices, 10 languages, 480p to 4K. |
p-video-edit | P-Video Edit | 2/sec | Pruna P-Video Edit: prompted edits on a clip up to 15 seconds, with up to 4 reference images. Keeps the original audio; draft mode for quick previews. |
p-video-upscale | P-Video Upscale | 0.6/sec | Pruna P-Video Upscale. Fast, low-cost video upscaling to 720p, 1080p, 2K, or 4K. Keeps the aspect ratio and the original audio. |
pixverse-v6 | PixVerse V6 | 10 | Pixverse V6 video generation via Runware. Text-to-video, image-to-video (start frame), or multi-clip (start + end frame). |
runway-gen-4-5 | Runway Gen-4.5 | 20 | Runway's Gen-4.5 video model. Text-to-video or image-to-video at 720p in five shapes, 5, 8 or 10 seconds, with cinematic camera work and believable motion. Clips are silent. |
seedance-2-high | Seedance 2 High | 6/sec | Higher-quality Seedance 2.0 video generation (supports 1080p) |
seedance-2-mini | Seedance 2 Mini | 2/sec | Cost-effective Seedance 2.0 Mini. Same creation flow at roughly half the credits (480p / 720p) |
seedance-2-5 | Seedance 2.5 | 6/sec | Seedance 2.5: text-to-video, first/last frame, and multimodal reference-to-video. Up to 30 seconds in one request with native audio in 11 languages. |
seedance-2-5-flash | Seedance 2.5 Flash | 4/sec | Seedance 2.5 Flash: the faster, lower-cost Seedance 2.5. Text-to-video, first/last frame, and reference-to-video, up to 30 seconds at 480p or 720p with native audio. |
seedance-2-5-video-edit | Seedance 2.5 Video Edit | 4.5/sec | Edit or extend an existing video with Seedance 2.5. Replace a subject, add or remove objects, or continue a clip forward or backward, with up to 50 reference materials. |
seedance-2-reference | Seedance 2 Reference | 20 | Seedance 2.0 multimodal reference-to-video. Combine up to 9 images, 3 video clips, and 3 audio tracks to guide characters, motion, and sound. |
seedance-video-edit | Seedance 2 Video Edit | 25 | Edit source videos with Seedance 2.0 using prompted changes, optional reference images, and 480p, 720p, or 1080p output. |
veo-3.1-fast | Veo 3.1 Fast | 4.5/sec | Faster generation at 4.5 credits per second with native audio (3 with generate_audio false) |
veo-3.1-standard | Veo 3.1 Standard | 12/sec | Higher quality at 12 credits per second with native audio (8 with generate_audio false) |
veo-3.1-lite | Veo 3.1 Lite | 1.5/sec | Runware-powered Lite variant at 1.5 credits/sec for 720p and 2 credits/sec for 1080p. No reference images, no audio generation, no 1:1 aspect ratio. |
video-autocaption | Video Autocaption | 5 | Animated word-by-word captions, placed clear of the TikTok, Reels and Shorts buttons. |
video-upscaler | Video Upscaler | 5 | FlashVSR video upscaling. Enhance video resolution up to 4K. |
wan-2.1-video | WAN 2.1 Video | 2.5/sec | WAN 2.1 (14B) text & image to video with LoRA support. 480p/720p, 1-5 second clips. |
wan-2.2-standard | WAN 2.2 Standard | 3 | Premium quality with enhanced detail |
wan-2.2-plus | WAN 2.2 Plus | 3 | Official Alibaba model with 1080p support |
wan-2.2-i2v-spicy | WAN 2.2 Image-to-Video | 5 | Image-to-video with WAN 2.2. Animate a starting image. 480p or 720p, 5s or 8s clips. |
wan-2.2-replace | WAN 2.2 Replace | 10 | WAN 2.2 character replacement. Swap a character in a source video while preserving scene and motion. |
wan-2.6-standard | WAN 2.6 Standard | 2/sec | Higher quality, 720p/1080p support |
wan-2.6-flash | WAN 2.6 Flash | 1.5/sec | Fast and affordable image-to-video |
wan-2.7-i2v-spicy | WAN 2.7 Image-to-Video | 12.5 | Image-to-video with WAN 2.7. Animate a starting image with optional driving audio. 720p or 1080p, 2–15 second clips. |
wan-2.7-t2v | WAN 2.7 Text-to-Video | 2/sec | Text-to-video with audio sync, 720p/1080p output, and 2-15 second durations |
wan-2.7-i2v | WAN 2.7 Image-to-Video | 2/sec | Image-to-video and video continuation with optional last-frame control and audio sync |
wan-3-0-video | WAN 3.0 | 10 | Alibaba WAN 3.0 video. Text-to-video with optional reference images or first/last frame control, native audio, up to 30 seconds. |
wan-reference-to-video | WAN Reference to Video | 2/sec | Alibaba WAN reference-to-video. Up to 5 image/video references with multi-shot support. |
wan-video-character-swap | WAN Video Character Swap | 3.4/sec | Alibaba WAN character swap. Combine a character image with a reference video to produce a new clip. |
wan-video-edit | WAN 2.7 Video Edit | 4.5/sec | Alibaba WAN 2.7 video editing. Modify an existing clip via prompt with optional reference images. |
xai-video | Grok Video | 7.5 | xAI Grok Imagine video. Text-to-video or image-to-video, 1-15 seconds at 480p or 720p. Image-to-video can use the Grok Imagine 1.5 backbone for natively-synchronized audio. |
xai-video-edit | Grok Video Edit | 15 | xAI Grok Imagine Video edit. Transform short clips via Replicate. |