# Core.Today AI API — Video Generation Models

> Text-to-video and image-to-video models (Kling, Hailuo, Veo, Sora, Seedance, Wan, ...) available through the Core.Today unified API.

Source: https://console.core.today/docs/video-models
This file: https://console.core.today/llms/video-models.txt
All models: https://console.core.today/llms.txt

## API Usage

Base URL: https://api.core.today/v1
Auth header: X-API-Key: YOUR_API_KEY

1. POST /predictions with {"model": "<model id>", "input": {...}} -> returns job_id
2. GET /predictions/{job_id} -> poll until status is "completed" or "failed"
3. result contains output URL(s); add "is_public": true for a permanent public URL

## Models (46)

### Add Watermark — `charlesmccarthy/addwatermark`

Add a text watermark to any video — simple, fast brand protection for generated or user content at 2 credits per video.

- Provider: FullJourney
- Credits: 1 (per video)
- Speed: fast / Quality: standard
- Required params: video (string)
- Optional params: size=40, watermark=FULLJOURNEY.AI
- Example input:
```json
{
  "model": "charlesmccarthy/addwatermark",
  "input": {
    "video": "https://example.com/generated.mp4",
    "watermark": "CORE.TODAY",
    "size": 48
  }
}
```
- Full docs: https://console.core.today/docs/models/charlesmccarthy/addwatermark

### CogVLM2 Video — `chenxwh/cogvlm2-video`

Video understanding and captioning — ask free-form questions about a video and get detailed answers about actions, scenes, and content. Great for video search indexing and moderation prep.

- Provider: CogVLM
- Credits: 28 (per video query)
- Speed: medium / Quality: high
- Required params: input_video (string)
- Optional params: prompt=Describe this video., top_p=0.1, temperature=0.1, max_new_tokens=2048
- Example input:
```json
{
  "model": "chenxwh/cogvlm2-video",
  "input": {
    "input_video": "https://example.com/clip.mp4",
    "prompt": "Describe this video in detail, including actions and scene changes."
  }
}
```
- Full docs: https://console.core.today/docs/models/chenxwh/cogvlm2-video

### Google Gemini Omni Flash — `google/gemini-omni-flash`

Google Gemini Omni Flash text-to-video via Fal.AI. Generates a video directly from a descriptive text prompt — pacing and audio (dialogue, background music) are controlled in the prompt itself, in 16:9 or 9:16 at 3-10 second durations.

- Provider: Google
- Credits: 2320 (per second)
- Speed: fast / Quality: high
- Required params: prompt (string)
- Optional params: aspect_ratio=16:9, duration=8
- Example input:
```json
{
  "model": "google/gemini-omni-flash",
  "input": {
    "prompt": "A cinematic wide shot of a lighthouse on a rocky cliff at dusk, waves crashing below, the beam slowly sweeping across the dark sea.",
    "aspect_ratio": "16:9",
    "duration": 8
  }
}
```
- Full docs: https://console.core.today/docs/models/google/gemini-omni-flash

### Gen-4.5 — `runwayml/gen-4.5`

Runway's Gen-4.5 model, offering state-of-the-art video motion quality, prompt adherence, and visual fidelity for text-to-video and image-to-video generation.

- Provider: Runway
- Credits: 1400 (per 5s video (default) — billed per second (279/s, 5-10s))
- Speed: medium / Quality: ultra
- Required params: prompt (string)
- Optional params: image, duration=5, aspect_ratio=16:9, seed
- Example input:
```json
{
  "model": "runwayml/gen-4.5",
  "input": {
    "prompt": "A dense, verdant jungle world made up of small lego-like pieces. We see a rainbow chameleon running through the 3D world, the camera in and out of focus.",
    "duration": 10,
    "aspect_ratio": "16:9"
  }
}
```
- Full docs: https://console.core.today/docs/models/runwayml/gen-4.5

### Grok Imagine Video 1.5 — `xai/grok-imagine-video-1.5`

xAI's Grok Imagine Video 1.5 preview: image-to-video generation with synchronized audio. An upgraded successor to Grok Imagine Video with flat per-second pricing regardless of resolution.

- Provider: xAI
- Credits: 930 (per 5s video (default) — billed at 187 credits per second, duration 1-15s, same price at 480p and 720p, audio included)
- Speed: medium / Quality: high
- Required params: prompt (string), image (string)
- Optional params: duration=5, resolution=720p, aspect_ratio=auto
- Example input:
```json
{
  "model": "xai/grok-imagine-video-1.5",
  "input": {
    "image": "https://replicate.delivery/pbxt/PCRhFZ9wvsy2oylrpkZqa9VyAhDfe7VQi0jOKERQF6tX2ddF/download-4.png",
    "prompt": "Cinematic motion - the woman looks up out into the sunlight filtering into the room.",
    "duration": 5,
    "resolution": "720p",
    "aspect_ratio": "auto"
  }
}
```
- Full docs: https://console.core.today/docs/models/xai/grok-imagine-video-1.5

### Grok Imagine Video — `xai/grok-imagine-video`

Generate videos using xAI's Grok Imagine Video model. Supports text-to-video, image-to-video, and editing an existing short video clip.

- Provider: xAI
- Credits: 580 (per 5s video (default) — billed per second (117/s, 1-15s))
- Speed: fast / Quality: high
- Required params: prompt (string)
- Optional params: image, video, duration=5, resolution=720p, aspect_ratio=auto
- Example input:
```json
{
  "model": "xai/grok-imagine-video",
  "input": {
    "prompt": "a penguin walks away from the camera, towards a large snowy mountaintop in the distance",
    "duration": 5,
    "resolution": "720p",
    "aspect_ratio": "16:9"
  }
}
```
- Full docs: https://console.core.today/docs/models/xai/grok-imagine-video

### MiniMax Hailuo 2.3 — `minimax/hailuo-2.3`

Realistic human motion video generation with advanced character consistency and natural movement.

- Provider: MiniMax
- Credits: 650 (per video)
- Speed: slow / Quality: ultra
- Required params: prompt (string)
- Optional params: duration=6, resolution=768p, prompt_optimizer=true, first_frame_image
- Example input:
```json
{
  "model": "minimax/hailuo-2.3",
  "input": {
    "prompt": "A young woman walking through a busy Tokyo street at night, realistic motion, natural gait, neon lights reflecting on wet pavement",
    "duration": "6",
    "aspect_ratio": "16:9"
  }
}
```
- Full docs: https://console.core.today/docs/models/minimax/hailuo-2.3

### MiniMax Hailuo 2.3 Fast — `minimax/hailuo-2.3-fast`

Lower-latency version of Hailuo 2.3 optimized for faster generation while maintaining good quality for human motion videos.

- Provider: MiniMax
- Credits: 450 (per video)
- Speed: medium / Quality: high
- Required params: prompt (string), first_frame_image (string)
- Optional params: duration=6, resolution=768p, prompt_optimizer=true
- Example input:
```json
{
  "model": "minimax/hailuo-2.3-fast",
  "input": {
    "prompt": "A businessman adjusting his tie and looking at the camera with a confident smile, office background, professional lighting",
    "duration": "3",
    "aspect_ratio": "16:9"
  }
}
```
- Full docs: https://console.core.today/docs/models/minimax/hailuo-2.3-fast

### Happy Horse 1.1 — `alibaba/happyhorse-1.1`

Alibaba's Happy Horse 1.1 generates videos from text, animates a single image, or builds a video from multiple reference images. Supports 720p and 1080p, 3-15 second durations, and five aspect ratios.

- Provider: Alibaba
- Credits: 2090 (per 5s 1080p video — billed per second (720p 326/s, 1080p 419/s))
- Speed: medium / Quality: high
- Optional params: prompt=, images=[], resolution=1080p, aspect_ratio=16:9, duration=5, seed
- Example input:
```json
{
  "model": "alibaba/happyhorse-1.1",
  "input": {
    "prompt": "The animal prances across the branch",
    "images": [
      "https://example.com/animal.png"
    ],
    "duration": 5,
    "resolution": "1080p"
  }
}
```
- Full docs: https://console.core.today/docs/models/alibaba/happyhorse-1.1

### MiniMax Hailuo-03 (H3) Image to Video — `minimax/h3/image-to-video`

MiniMax Hailuo-03 (H3) image-to-video via Fal.AI. 2K video generation from a first-frame image, 5-15 second duration, native audio, with optional first-to-last keyframe control via end_image_url.

- Provider: MiniMax
- Credits: 3020 (per second, tiered by resolution)
- Speed: medium / Quality: ultra
- Required params: prompt (string), image_url (string)
- Optional params: duration=5, resolution=2K, end_image_url
- Example input:
```json
{
  "model": "minimax/h3/image-to-video",
  "input": {
    "prompt": "The camera slowly pulls back from the scene, revealing the full landscape as clouds drift overhead and light shifts across the terrain.",
    "image_url": "https://storage.googleapis.com/falserverless/example_inputs/hailuo23/pro_i2v_in.jpg",
    "duration": 5,
    "resolution": "2K"
  }
}
```
- Full docs: https://console.core.today/docs/models/minimax/h3/image-to-video

### Kling v3 Omni Video — `kwaivgi/kling-v3-omni-video`

Kling Video 3.0 Omni: a unified multimodal video model that generates and edits video from text, images, reference images, and existing video. Combines text-to-video, image-to-video, reference-based generation, and video editing with native audio and multi-shot control.

- Provider: Kuaishou
- Credits: 2610 (per 5s pro (1080p) video, no audio (default) — billed per second: standard 391-521/s, pro 521-652/s, 4k 978/s)
- Speed: slow / Quality: ultra
- Required params: prompt (string)
- Optional params: start_image, end_image, reference_images, reference_video, video_reference_type=feature, keep_original_sound=true, generate_audio=false, mode=pro, aspect_ratio=16:9, duration=5, multi_prompt
- Example input:
```json
{
  "model": "kwaivgi/kling-v3-omni-video",
  "input": {
    "mode": "pro",
    "prompt": "A Wes Anderson style movie trailer with symmetrical framing and pastel colors, ending on the full cast standing on the hotel steps",
    "duration": 15,
    "aspect_ratio": "16:9",
    "generate_audio": true
  }
}
```
- Full docs: https://console.core.today/docs/models/kwaivgi/kling-v3-omni-video

### Kling v3 Video — `kwaivgi/kling-v3-video`

Kling Video 3.0: Kuaishou's flagship text/image-to-video model generating cinematic videos up to 15 seconds with multi-shot control, native audio, start/end frame images, and a dedicated 4K mode.

- Provider: Kuaishou
- Credits: 2610 (per 5s pro (1080p) video, no audio (default) — billed per second: standard 391/s, pro 521/s, 4k 978/s; with audio standard 587/s, pro 782/s (4k unchanged))
- Speed: slow / Quality: ultra
- Required params: prompt (string)
- Optional params: mode=pro, duration=5, start_image, end_image, aspect_ratio=16:9, multi_prompt, generate_audio=false, negative_prompt=
- Example input:
```json
{
  "model": "kwaivgi/kling-v3-video",
  "input": {
    "mode": "pro",
    "prompt": "First-person POV of a roller coaster plunging into the mouth of an erupting volcano. The track spirals down through rivers of glowing orange lava, sparks and embers flying past the camera. The coaster banks hard around a pillar of molten rock, then launches upward through a vent, bursting out of the volcano's crater into a dazzling sunset sky above the clouds. Wind roaring, riders screaming with excitement, the deep rumble of the volcano.",
    "duration": 15,
    "aspect_ratio": "16:9",
    "generate_audio": true
  }
}
```
- Full docs: https://console.core.today/docs/models/kwaivgi/kling-v3-video

### Kling v2.6 — `kwaivgi/kling-v2.6`

Kling 2.6 Pro: top-tier image-to-video with cinematic visuals, fluid motion, and native audio generation. Audio generation is enabled by default.

- Provider: Kuaishou
- Credits: 1630 (per 5s video with audio (default) — billed per second (no audio 163/s, with audio 326/s))
- Speed: medium / Quality: ultra
- Required params: prompt (string)
- Optional params: start_image, negative_prompt=, aspect_ratio=16:9, duration=5, generate_audio=true
- Example input:
```json
{
  "model": "kwaivgi/kling-v2.6",
  "input": {
    "prompt": "A cinematic, low-angle tracking shot follows a cyclist from behind as they weave through busy New York City traffic. The camera then smoothly orbits around to the front, capturing the cyclist's determined expression.",
    "duration": 5,
    "aspect_ratio": "16:9",
    "generate_audio": true
  }
}
```
- Full docs: https://console.core.today/docs/models/kwaivgi/kling-v2.6

### Kling 2.5 Turbo Pro — `kwaivgi/kling-v2.5-turbo-pro`

Cinematic-grade video generation with enhanced motion and scene coherence. Top-tier Kling model for professional output.

- Provider: Kuaishou
- Credits: 810 (per video)
- Speed: medium / Quality: ultra
- Required params: prompt (string)
- Optional params: negative_prompt=, start_image, end_image, aspect_ratio=16:9, duration=5, image, guidance_scale
- Example input:
```json
{
  "model": "kwaivgi/kling-v2.5-turbo-pro",
  "input": {
    "prompt": "A samurai drawing a katana in slow motion, cherry blossoms falling, dramatic side lighting, cinematic depth of field, film grain",
    "duration": "5",
    "aspect_ratio": "16:9",
    "cfg_scale": "0.6"
  }
}
```
- Full docs: https://console.core.today/docs/models/kwaivgi/kling-v2.5-turbo-pro

### Kling v2.1 — `kwaivgi/kling-v2.1`

Kling v2.1 with 720p/1080p support and frame transition capabilities for smooth, high-quality video generation.

- Provider: Kuaishou
- Credits: 580 (per video)
- Speed: slow / Quality: ultra
- Required params: prompt (string), start_image (string)
- Optional params: mode=standard, duration=5, end_image, negative_prompt=
- Example input:
```json
{
  "model": "kwaivgi/kling-v2.1",
  "input": {
    "prompt": "Sweeping aerial view of cherry blossom trees along a river, petals floating in the wind, golden hour lighting, cinematic drone movement",
    "duration": "10",
    "aspect_ratio": "16:9",
    "cfg_scale": "0.5"
  }
}
```
- Full docs: https://console.core.today/docs/models/kwaivgi/kling-v2.1

### LatentSync — `bytedance/latentsync`

ByteDance's open-source lipsync — re-syncs a video's mouth movements to any audio track using latent diffusion. State-of-the-art open lipsync quality for dubbing and localization.

- Provider: ByteDance
- Credits: 220 (per run (runtime grows with video length))
- Speed: slow / Quality: high
- Optional params: video, audio, guidance_scale=1, seed=0
- Example input:
```json
{
  "model": "bytedance/latentsync",
  "input": {
    "video": "https://example.com/presenter.mp4",
    "audio": "https://example.com/korean-voiceover.mp3"
  }
}
```
- Full docs: https://console.core.today/docs/models/bytedance/latentsync

### MMAudio — `zsxkib/mmaudio`

Add AI-generated sound to any video (5M+ runs) — synthesizes synchronized audio (ambience, effects, foley) from the video content and an optional text prompt. The perfect finisher for silent AI-generated clips.

- Provider: MMAudio
- Credits: 11 (per generation)
- Speed: medium / Quality: high
- Optional params: prompt=, negative_prompt=music, video, duration=8, num_steps=25, cfg_strength=4.5, seed, image
- Example input:
```json
{
  "model": "zsxkib/mmaudio",
  "input": {
    "video": "https://example.com/generated-clip.mp4",
    "prompt": "ocean waves, seagulls, gentle wind"
  }
}
```
- Full docs: https://console.core.today/docs/models/zsxkib/mmaudio

### Pruna P-Video — `prunaai/p-video`

PrunaAI's fast video generator with a built-in draft mode for rapid creative iteration. Text-to-video, image-to-video, and audio-conditioned generation in a single endpoint, with clips up to 20 seconds — one of the longest durations on the platform.

- Provider: Pruna AI
- Credits: 240 (per second — 720p standard 47/s, 720p draft 13/s, 1080p standard 94/s, 1080p draft 24/s; duration 1-20s (default 5s at 720p standard = 240))
- Speed: fast / Quality: standard
- Required params: prompt (string)
- Optional params: image, last_frame_image, audio, duration=5, aspect_ratio=16:9, resolution=720p, fps=24, draft=false, prompt_upsampling=true, disable_safety_filter=true, save_audio=true, seed, no_op=false
- Example input:
```json
{
  "model": "prunaai/p-video",
  "input": {
    "fps": 24,
    "draft": false,
    "image": "https://replicate.delivery/pbxt/OejQrIXERvqS9kpygH9PfQZDOIdzkD6GKytAXxedNSyyRtej/9.png",
    "prompt": "The prune says \"And this, kids, is how you generate a video in less than 10 seconds\".",
    "duration": 5,
    "resolution": "720p",
    "save_audio": true,
    "aspect_ratio": "16:9",
    "prompt_upsampling": false
  }
}
```
- Full docs: https://console.core.today/docs/models/prunaai/p-video

### Pruna P-Video Avatar — `prunaai/p-video-avatar`

Pruna AI's talking-avatar video model — animates a single input image to speak provided text (voice_script) or an uploaded audio track, with selectable Gemini-family preset voices, language, and visual delivery prompt.

- Provider: Pruna AI
- Credits: 870 (per video, flat rate tiered by resolution)
- Speed: medium / Quality: high
- Required params: image (string)
- Optional params: resolution=720p, audio, voice=Zephyr (Female), voice_script=, voice_prompt=Say the following., voice_language=English (US), seed, video_prompt=The person is talking., negative_prompt=, strength_negative_prompt=0.5, disable_safety_filter=true, disable_prompt_upsampling=false, no_op=false
- Example input:
```json
{
  "model": "prunaai/p-video-avatar",
  "input": {
    "image": "https://example.com/presenter-photo.jpg",
    "voice_script": "Welcome to our new product launch. Today we're excited to show you what we've been building.",
    "voice": "Kore (Female)",
    "voice_language": "English (US)",
    "resolution": "1080p"
  }
}
```
- Full docs: https://console.core.today/docs/models/prunaai/p-video-avatar

### PixVerse V6 — `pixverse/pixverse-v6`

PixVerse's flagship video generation model. Generates cinematic videos with synchronized audio, multi-shot sequences with scene transitions, astonishing physics, and precise camera control at up to 1080p.

- Provider: PixVerse
- Credits: 810 (per 5s 540p video, no audio (default) — billed per second by quality x audio: 360p 116/162, 540p 162/209, 720p 209/278, 1080p 417/533 (no-audio/with-audio))
- Speed: medium / Quality: high
- Required params: prompt (string)
- Optional params: image, last_frame_image, quality=540p, duration=5, aspect_ratio=16:9, generate_audio_switch=false, generate_multi_clip_switch=false, negative_prompt=, seed
- Example input:
```json
{
  "model": "pixverse/pixverse-v6",
  "input": {
    "prompt": "E-commerce brand film for natural pure cotton loungewear, Japanese minimalist lifestyle aesthetic. Shot 1 (0-4s): warm morning sunlight through floor-to-ceiling windows, a woman in off-white loungewear holds a mug by the window, slow push-in. Shot 2 (4-8s): close-up of fabric texture as a breeze sways the hem, sunlight through the cotton. Shot 3 (8-12s): wide tracking shot as she walks toward a raw wood shelf, soft light and shadow. Shot 4 (12-15s): she sits gazing out the window, negative-space composition, slow pull out and fade. Sound: distant birdsong, fabric rustle, soothing acoustic guitar",
    "quality": "1080p",
    "duration": 15,
    "aspect_ratio": "16:9",
    "generate_audio_switch": true,
    "generate_multi_clip_switch": true
  }
}
```
- Full docs: https://console.core.today/docs/models/pixverse/pixverse-v6

### PixVerse V5 — `pixverse/pixverse-v5`

Advanced video generation with special effects capabilities and anime-optimized output, supporting multiple visual styles.

- Provider: PixVerse
- Credits: 24 (per video)
- Speed: slow / Quality: ultra
- Required params: prompt (string)
- Optional params: image, last_frame_image, quality=540p, aspect_ratio=16:9, duration=5, negative_prompt=, seed, effect=None
- Example input:
```json
{
  "model": "pixverse/pixverse-v5",
  "input": {
    "prompt": "An anime warrior charging through a battlefield with glowing energy sword, dramatic speed lines, vibrant colors, dynamic camera angles",
    "duration": 5,
    "aspect_ratio": "16:9",
    "quality": "720p",
    "style": "anime"
  }
}
```
- Full docs: https://console.core.today/docs/models/pixverse/pixverse-v5

### Luma Ray 3.2 — `luma/ray-3.2`

Luma's flagship Ray video model. Text-to-video and keyframe (start/end image) generation with optional HDR-encoded output and professional EXR export.

- Provider: Luma
- Credits: 1740 (per video, tiered by resolution, duration, and HDR)
- Speed: medium / Quality: ultra
- Required params: prompt (string)
- Optional params: aspect_ratio=16:9, resolution=720p, duration=5, hdr=false, exr_export=false, loop=false, start_image, end_image
- Example input:
```json
{
  "model": "luma/ray-3.2",
  "input": {
    "prompt": "A slow aerial pull-back over a misty mountain valley at sunrise, warm golden light breaking through the clouds.",
    "resolution": "1080p",
    "duration": 5,
    "hdr": true,
    "exr_export": true
  }
}
```
- Full docs: https://console.core.today/docs/models/luma/ray-3.2

### Luma Ray Flash 2 720p — `luma/ray-flash-2-720p`

Luma's Ray Flash 2 generates 5 or 9 second 720p videos faster and cheaper than Ray 2. Supports keyframe control via start and end images, seamless loops, and a rich library of camera motion concepts — the first Luma model on the platform.

- Provider: Luma
- Credits: 700 (per 5s video — billed at 140 credits/second; duration is 5 or 9 seconds (9s = 1260))
- Speed: fast / Quality: high
- Required params: prompt (string)
- Optional params: loop=false, concepts, duration=5, end_image, start_image, aspect_ratio=16:9, end_image_url, start_image_url
- Example input:
```json
{
  "model": "luma/ray-flash-2-720p",
  "input": {
    "loop": false,
    "prompt": "A cinematic anime character intimate closeup, she is sitting at a cafe on a busy city street in the morning, it is cold",
    "duration": 5,
    "aspect_ratio": "16:9"
  }
}
```
- Full docs: https://console.core.today/docs/models/luma/ray-flash-2-720p

### Real-ESRGAN Video — `lucataco/real-esrgan-video`

Video upscaling with Real-ESRGAN — enhance videos to FHD, 2K, or 4K frame by frame. The go-to open-source video upscaler for old footage and AI-generated clips.

- Provider: Real-ESRGAN
- Credits: 1280 (per run (cost varies strongly with video length/resolution))
- Speed: slow / Quality: high
- Required params: video_path (string)
- Optional params: resolution=FHD, model=RealESRGAN_x4plus
- Example input:
```json
{
  "model": "lucataco/real-esrgan-video",
  "input": {
    "video_path": "https://example.com/generated-clip.mp4",
    "model": "RealESRGAN_x4plus",
    "resolution": "4k"
  }
}
```
- Full docs: https://console.core.today/docs/models/lucataco/real-esrgan-video

### SadTalker — `cjwbw/sadtalker`

Talking-head video from a single photo and an audio track — animates the face with natural head motion and eye blinks, with optional GFPGAN face enhancement.

- Provider: SadTalker
- Credits: 91 (per run (runtime grows with audio length))
- Speed: slow / Quality: high
- Required params: source_image (string), driven_audio (string)
- Optional params: use_enhancer=false, pose_style=0, expression_scale=1, use_eyeblink=true, preprocess=crop, size_of_image=256, facerender=facevid2vid, still_mode=true
- Example input:
```json
{
  "model": "cjwbw/sadtalker",
  "input": {
    "source_image": "https://example.com/portrait.jpg",
    "driven_audio": "https://example.com/narration.wav",
    "preprocess": "full",
    "still_mode": true,
    "use_enhancer": true
  }
}
```
- Full docs: https://console.core.today/docs/models/cjwbw/sadtalker

### Seedance 2.0 — `bytedance/seedance-2.0`

ByteDance's next-generation multimodal video model with native synchronized audio. Combines up to 9 reference images, 3 videos, and 3 audio files in a single generation for character-consistent, lip-synced video creation, editing, and extension.

- Provider: ByteDance
- Credits: 2090 (per 5s 720p video — billed per second (480p 186/s, 720p 419/s, 1080p 1047/s, 4K 2327/s; with reference videos 480p 233/s, 720p 512/s, 1080p 1280/s, 4K 2908/s))
- Speed: medium / Quality: ultra
- Required params: prompt (string)
- Optional params: image, last_frame_image, reference_images=[], reference_videos=[], reference_audios=[], duration=5, resolution=720p, aspect_ratio=16:9, generate_audio=true, seed
- Example input:
```json
{
  "model": "bytedance/seedance-2.0",
  "input": {
    "prompt": "A cozy cabin in a snowy forest at night, warm light glowing from the windows, gentle snowfall, camera slowly pushing in through the trees",
    "duration": 7,
    "resolution": "720p",
    "aspect_ratio": "16:9",
    "generate_audio": true
  }
}
```
- Full docs: https://console.core.today/docs/models/bytedance/seedance-2.0

### Seedance 2.0 Fast — `bytedance/seedance-2.0-fast`

A faster, cheaper variant of Seedance 2.0 for quicker video generation with multimodal reference inputs (up to 9 images, 3 videos, 3 audios) and native audio, at 480p or 720p.

- Provider: ByteDance
- Credits: 1750 (per 5s 720p video, text/image input — billed per second (480p 163/s, 720p 349/s; with reference videos 480p 186/s, 720p 396/s))
- Speed: fast / Quality: high
- Required params: prompt (string)
- Optional params: image, last_frame_image, reference_images=[], reference_videos=[], reference_audios=[], duration=5, resolution=720p, aspect_ratio=16:9, generate_audio=true, seed
- Example input:
```json
{
  "model": "bytedance/seedance-2.0-fast",
  "input": {
    "prompt": "A cozy cabin in a snowy forest at night, warm light glowing from the windows, gentle snowfall, camera slowly pushing in through the trees",
    "duration": 7,
    "resolution": "720p",
    "aspect_ratio": "16:9",
    "generate_audio": true
  }
}
```
- Full docs: https://console.core.today/docs/models/bytedance/seedance-2.0-fast

### Seedance 2.0 Mini — `bytedance/seedance-2.0-mini`

Lighter, cheaper variant of ByteDance's Seedance 2.0. Native audio, multimodal reference inputs (images/videos/audio), text-to-video and image-to-video, capped at 720p (no 1080p/4K tier).

- Provider: ByteDance
- Credits: 1280 (per second, tiered by resolution and audio generation)
- Speed: fast / Quality: standard
- Required params: prompt (string)
- Optional params: image, last_frame_image, reference_images=[], reference_videos=[], reference_audios=[], duration=5, resolution=720p, aspect_ratio=16:9, generate_audio=true, seed
- Example input:
```json
{
  "model": "bytedance/seedance-2.0-mini",
  "input": {
    "prompt": "A young woman smiles at the camera and says \"This product is amazing!\" Bright studio lighting, gentle zoom-in.",
    "resolution": "720p",
    "aspect_ratio": "9:16",
    "generate_audio": true,
    "duration": 5
  }
}
```
- Full docs: https://console.core.today/docs/models/bytedance/seedance-2.0-mini

### Seedance 1 Lite — `bytedance/seedance-1-lite`

A lightweight ByteDance video generation model offering text-to-video and image-to-video support for 4-12 second videos at 480p, 720p, or 1080p resolution.

- Provider: ByteDance
- Credits: 420 (per 5s 720p video — billed per second (480p 42/s, 720p 84/s, 1080p 168/s))
- Speed: fast / Quality: standard
- Required params: prompt (string)
- Optional params: fps=24, seed, image, duration=5, resolution=720p, aspect_ratio=16:9, camera_fixed=false, last_frame_image, reference_images
- Example input:
```json
{
  "model": "bytedance/seedance-1-lite",
  "input": {
    "prompt": "a woman walks in the park",
    "duration": 5,
    "resolution": "720p",
    "aspect_ratio": "16:9"
  }
}
```
- Full docs: https://console.core.today/docs/models/bytedance/seedance-1-lite

### Seedance 1 Pro — `bytedance/seedance-1-pro`

A pro version of Seedance that offers text-to-video and image-to-video support for 2-12 second videos, at 480p, 720p, and 1080p resolution.

- Provider: ByteDance
- Credits: 700 (per 5s 1080p video — billed per second (480p 28/s, 720p 56/s, 1080p 140/s; defaults to 1080p))
- Speed: medium / Quality: ultra
- Required params: prompt (string)
- Optional params: fps=24, seed, image, duration=5, resolution=1080p, aspect_ratio=16:9, camera_fixed=false, last_frame_image
- Example input:
```json
{
  "model": "bytedance/seedance-1-pro",
  "input": {
    "prompt": "The sun rises slowly between tall buildings. [Ground-level follow shot] Bicycle tires roll over a dew-covered street at dawn. The cyclist passes through dappled light under a bridge as the entire city gradually wakes up.",
    "duration": 5,
    "resolution": "1080p",
    "aspect_ratio": "16:9"
  }
}
```
- Full docs: https://console.core.today/docs/models/bytedance/seedance-1-pro

### Seedance 1 Pro Fast — `bytedance/seedance-1-pro-fast`

ByteDance's cinematic video generation model with fast generation speed and professional output quality.

- Provider: ByteDance
- Credits: 290 (per video)
- Speed: fast / Quality: high
- Required params: prompt (string)
- Optional params: fps=24, seed, image, duration=5, resolution=1080p, aspect_ratio=16:9, camera_fixed=false
- Example input:
```json
{
  "model": "bytedance/seedance-1-pro-fast",
  "input": {
    "prompt": "A sports car drifting around a mountain curve, dust and gravel flying, dramatic low angle, cinematic motion blur, golden hour",
    "duration": "5",
    "aspect_ratio": "16:9"
  }
}
```
- Full docs: https://console.core.today/docs/models/bytedance/seedance-1-pro-fast

### OpenAI Sora 2 — `openai/sora-2`

OpenAI's video generation model with realistic physics simulation and audio generation capabilities, producing highly coherent videos.

- Provider: OpenAI
- Credits: 930 (per video)
- Speed: slow / Quality: ultra
- Required params: prompt (string)
- Optional params: openai_api_key, input_reference, seconds=4, aspect_ratio=portrait
- Example input:
```json
{
  "model": "openai/sora-2",
  "input": {
    "prompt": "A glass marble rolls down a wooden ramp, bounces off the table edge, and splashes into a glass of water, slow motion, photorealistic",
    "duration": "10",
    "aspect_ratio": "16:9",
    "resolution": "1080p"
  }
}
```
- Full docs: https://console.core.today/docs/models/openai/sora-2

### OpenAI Sora 2 Pro — `openai/sora-2-pro`

OpenAI's most advanced synced-audio video generation model. The premium tier of Sora 2 with higher fidelity, up to 1024p resolution, and image-to-video via an input reference frame.

- Provider: OpenAI
- Credits: 2790 (per 4s standard (720p) video (default) — billed per second: standard 698/s, high (1024p) 1163/s; durations 4/8/12s)
- Speed: slow / Quality: ultra
- Required params: prompt (string)
- Optional params: seconds=4, resolution=standard, aspect_ratio=portrait, input_reference, openai_api_key
- Example input:
```json
{
  "model": "openai/sora-2-pro",
  "input": {
    "prompt": "Scottish Highland coo with ginger fur getting a parking ticket from a Glaswegian police officer speaking in a thick accent, parked on a double yellow line in a small Scottish town",
    "seconds": 4,
    "resolution": "standard",
    "aspect_ratio": "portrait"
  }
}
```
- Full docs: https://console.core.today/docs/models/openai/sora-2-pro

### MiniMax Hailuo-03 (H3) Text to Video — `minimax/h3/text-to-video`

MiniMax Hailuo-03 (H3) text-to-video via Fal.AI. State-of-the-art 2K video generation from a text prompt, 5-15 second duration, native audio, and wide aspect-ratio support (21:9 through 9:16).

- Provider: MiniMax
- Credits: 3020 (per second, tiered by resolution)
- Speed: medium / Quality: ultra
- Required params: prompt (string)
- Optional params: duration=5, resolution=2K, aspect_ratio=16:9
- Example input:
```json
{
  "model": "minimax/h3/text-to-video",
  "input": {
    "prompt": "A white kitten chases a butterfly across a sunlit garden. Gentle camera tracking, natural movement, soft afternoon light filtering through the leaves.",
    "duration": 5,
    "resolution": "2K",
    "aspect_ratio": "16:9"
  }
}
```
- Full docs: https://console.core.today/docs/models/minimax/h3/text-to-video

### Veed Lipsync v2 — `veed/lipsync/v2`

Veed Lipsync v2 via Fal.AI. Replaces a source video's mouth movements to articulate a new audio track — takes any source video + a new audio track and produces a lip-synced output video.

- Provider: Veed
- Credits: 2440 (per video (flat rate, regardless of length))
- Speed: medium / Quality: high
- Required params: video_url (string), audio_url (string)
- Example input:
```json
{
  "model": "veed/lipsync/v2",
  "input": {
    "video_url": "https://v3.fal.media/files/monkey/q1fDPhrpfjfsaRmbhTed4_influencer.mp4",
    "audio_url": "https://v3.fal.media/files/rabbit/Ql3ade3wEKlZXRQLRbhxm_tts.mp3"
  }
}
```
- Full docs: https://console.core.today/docs/models/veed/lipsync/v2

### Google Veo 3.1 — `google/veo-3.1`

Google's state-of-the-art video generation model with built-in audio generation, producing cinematic-quality videos with synchronized sound.

- Provider: Google
- Credits: 7440 (per video)
- Speed: slow / Quality: ultra
- Required params: prompt (string)
- Optional params: aspect_ratio=16:9, duration=8, image, last_frame, reference_images=[], negative_prompt, resolution=1080p, generate_audio=true, seed
- Example input:
```json
{
  "model": "google/veo-3.1",
  "input": {
    "prompt": "A lone astronaut walks across a vast Martian desert at sunset, wind blowing dust, cinematic wide shot, dramatic orchestral score",
    "duration": "8",
    "aspect_ratio": "16:9",
    "generate_audio": true
  }
}
```
- Full docs: https://console.core.today/docs/models/google/veo-3.1

### Google Veo 3.1 Fast — `google/veo-3.1-fast`

Fast version of Veo 3.1 with audio generation, optimized for speed while maintaining high quality output.

- Provider: Google
- Credits: 2790 (per video)
- Speed: medium / Quality: high
- Required params: prompt (string)
- Optional params: aspect_ratio=16:9, duration=8, image, last_frame, negative_prompt, resolution=1080p, generate_audio=true, seed
- Example input:
```json
{
  "model": "google/veo-3.1-fast",
  "input": {
    "prompt": "Colorful street food being prepared at a night market, sizzling sounds, vibrant neon lights, handheld camera feel",
    "duration": "5",
    "aspect_ratio": "9:16",
    "generate_audio": true
  }
}
```
- Full docs: https://console.core.today/docs/models/google/veo-3.1-fast

### Video Utils — `nicolascoutureau/video-utils`

FFmpeg-powered video utilities (20M+ runs) — convert to mp4/gif, extract audio as mp3, or dump zipped frames, all with one task parameter. The Swiss-army knife for media pipelines.

- Provider: FFmpeg
- Credits: 5 (per operation)
- Speed: fast / Quality: standard
- Required params: task (string), input_file (string)
- Optional params: fps=0
- Example input:
```json
{
  "model": "nicolascoutureau/video-utils",
  "input": {
    "input_file": "https://example.com/meeting-recording.mp4",
    "task": "extract_video_audio_as_mp3"
  }
}
```
- Full docs: https://console.core.today/docs/models/nicolascoutureau/video-utils

### Wan 2.7 I2V — `wan-video/wan-2.7-i2v`

Alibaba Wan 2.7 image-to-video model. Animates a first frame (and optional last frame or continuation clip) with audio synchronization, up to 15 seconds, at 720p or 1080p.

- Provider: Alibaba
- Credits: 1740 (per second, tiered by resolution)
- Speed: medium / Quality: high
- Optional params: prompt=, first_frame, last_frame, first_clip, audio, negative_prompt=, resolution=1080p, duration=5, enable_prompt_expansion=true, seed
- Example input:
```json
{
  "model": "wan-video/wan-2.7-i2v",
  "input": {
    "first_frame": "https://example.com/product-shot.jpg",
    "prompt": "The product slowly rotates on a reflective surface as soft studio light sweeps across it.",
    "resolution": "1080p",
    "duration": 5
  }
}
```
- Full docs: https://console.core.today/docs/models/wan-video/wan-2.7-i2v

### Wan 2.7 T2V — `wan-video/wan-2.7-t2v`

Alibaba Wan 2.7 text-to-video model. Supports up to 15 seconds, audio synchronization for voice/music, multilingual prompts, and prompt expansion, at 720p or 1080p.

- Provider: Alibaba
- Credits: 1740 (per second, tiered by resolution)
- Speed: medium / Quality: high
- Required params: prompt (string)
- Optional params: negative_prompt=, audio, resolution=1080p, aspect_ratio=16:9, duration=5, enable_prompt_expansion=true, seed
- Example input:
```json
{
  "model": "wan-video/wan-2.7-t2v",
  "input": {
    "prompt": "A chef in a busy kitchen explains a recipe while chopping vegetables, warm natural lighting.",
    "audio": "https://example.com/narration-ko.mp3",
    "resolution": "1080p",
    "duration": 8
  }
}
```
- Full docs: https://console.core.today/docs/models/wan-video/wan-2.7-t2v

### Wan 2.5 I2V — `wan-video/wan-2.5-i2v`

Image-to-video model with lip sync support, animating still images into realistic videos with natural motion.

- Provider: Alibaba
- Credits: 1160 (per video)
- Speed: slow / Quality: ultra
- Required params: prompt (string), image (string)
- Optional params: negative_prompt=, audio, resolution=720p, duration=5, enable_prompt_expansion=true, seed
- Example input:
```json
{
  "model": "wan-video/wan-2.5-i2v",
  "input": {
    "prompt": "Person slowly smiling and turning their head to the left, gentle hair movement, natural facial expression transition",
    "image_url": "https://example.com/portrait.jpg",
    "aspect_ratio": "9:16",
    "duration": 5
  }
}
```
- Full docs: https://console.core.today/docs/models/wan-video/wan-2.5-i2v

### Wan 2.5 I2V Fast — `wan-video/wan-2.5-i2v-fast`

Fast image-to-video variant of Wan 2.5, optimized for rapid generation of animated videos from still images.

- Provider: Alibaba
- Credits: 790 (per video)
- Speed: medium / Quality: high
- Required params: prompt (string), image (string)
- Optional params: seed, audio, duration=5, resolution=720p, negative_prompt=, enable_prompt_expansion=true
- Example input:
```json
{
  "model": "wan-video/wan-2.5-i2v-fast",
  "input": {
    "prompt": "Person nodding gently and blinking naturally, subtle smile, realistic head movement",
    "image_url": "https://example.com/portrait.jpg",
    "aspect_ratio": "9:16",
    "duration": 5
  }
}
```
- Full docs: https://console.core.today/docs/models/wan-video/wan-2.5-i2v-fast

### Wan 2.5 T2V — `wan-video/wan-2.5-t2v`

Text-to-video model with audio synchronization support, producing high-quality videos from text prompts with natural motion.

- Provider: Alibaba
- Credits: 2320 (per video)
- Speed: slow / Quality: ultra
- Required params: prompt (string)
- Optional params: negative_prompt=, audio, size=1280*720, duration=5, enable_prompt_expansion=true, seed
- Example input:
```json
{
  "model": "wan-video/wan-2.5-t2v",
  "input": {
    "prompt": "A majestic eagle soaring over snow-capped mountains, dramatic aerial perspective, golden sunrise, National Geographic cinematography",
    "aspect_ratio": "16:9",
    "duration": 5
  }
}
```
- Full docs: https://console.core.today/docs/models/wan-video/wan-2.5-t2v

### Wan 2.5 T2V Fast — `wan-video/wan-2.5-t2v-fast`

Fast text-to-video generation variant of Wan 2.5, optimized for speed with good quality output.

- Provider: Alibaba
- Credits: 790 (per video)
- Speed: medium / Quality: high
- Required params: prompt (string)
- Optional params: negative_prompt=, audio, size=1280*720, duration=5, enable_prompt_expansion=true, seed
- Example input:
```json
{
  "model": "wan-video/wan-2.5-t2v-fast",
  "input": {
    "prompt": "Colorful autumn leaves falling in a park, gentle breeze, warm sunlight filtering through trees, peaceful atmosphere",
    "aspect_ratio": "16:9",
    "duration": 5
  }
}
```
- Full docs: https://console.core.today/docs/models/wan-video/wan-2.5-t2v-fast

### Wan 2.2 I2V Fast — `wan-video/wan-2.2-i2v-fast`

A very fast and cheap PrunaAI-optimized version of Alibaba's Wan 2.2 A14B image-to-video model. Turns a single still image plus a prompt into a short animated clip at 480p or 720p, with an optional frame-interpolation pass for smoother motion.

- Provider: Alibaba
- Credits: 260 (per output video (flat, not per-second) — 480p base 120, 480p+interpolate 150, 720p base 260, 720p+interpolate 340)
- Speed: fast / Quality: standard
- Required params: prompt (string), image (string)
- Optional params: last_image, resolution=480p, interpolate_output=false, num_frames=81, frames_per_second=16, go_fast=true, sample_shift=12, seed, disable_safety_checker=false, lora_weights_transformer, lora_scale_transformer=1, lora_weights_transformer_2, lora_scale_transformer_2=1
- Example input:
```json
{
  "model": "wan-video/wan-2.2-i2v-fast",
  "input": {
    "image": "https://replicate.delivery/pbxt/NRvtedaIOd3pdE0pTE3L9uavxJ53g33THGr0HF81M2olNOce/replicate-prediction-g8gbs3rbk9rme0crbhwatpsq04.jpg",
    "prompt": "Close-up shot of an elderly sailor wearing a yellow raincoat, seated on the deck of a catamaran, slowly puffing on a pipe. His cat lies quietly beside him with eyes closed, enjoying the calm. The warm glow of the setting sun bathes the scene, with gentle waves lapping against the hull and a few seabirds circling slowly above. The camera slowly pushes in, capturing this peaceful and harmonious moment.",
    "resolution": "480p",
    "go_fast": true
  }
}
```
- Full docs: https://console.core.today/docs/models/wan-video/wan-2.2-i2v-fast

### Wan 2.2 T2V Fast — `wan-video/wan-2.2-t2v-fast`

A very fast and cheap PrunaAI-optimized version of Alibaba's Wan 2.2 A14B text-to-video model. Generates short clips at 480p or 720p directly from a text prompt, with 30 FPS frame interpolation enabled by default — the text-to-video sibling of Wan 2.2 I2V Fast.

- Provider: Alibaba
- Credits: 240 (per output video (flat, not per-second) — 480p 120, 720p 240 (billed at the 720p rate if resolution is omitted))
- Speed: fast / Quality: standard
- Required params: prompt (string)
- Optional params: optimize_prompt=false, num_frames=81, aspect_ratio=16:9, resolution=480p, frames_per_second=16, interpolate_output=true, go_fast=true, sample_shift=12, seed, disable_safety_checker=false, lora_weights_transformer, lora_scale_transformer=1, lora_weights_transformer_2, lora_scale_transformer_2=1
- Example input:
```json
{
  "model": "wan-video/wan-2.2-t2v-fast",
  "input": {
    "prompt": "A sports car is driving very fast along a beach at sunset",
    "go_fast": true,
    "num_frames": 81,
    "resolution": "480p",
    "aspect_ratio": "16:9",
    "sample_shift": 12,
    "frames_per_second": 16
  }
}
```
- Full docs: https://console.core.today/docs/models/wan-video/wan-2.2-t2v-fast