Seedance 2.5
seedance2_5 Cinematic video up to 30 seconds at 480p, 720p, and 1080p, with a large reference budget for images, videos, and audio.
The API supports the models below. See pricing for per-model costs. Create an account to start building on Runway Dev.
HDR, pipeline formats, and upscaling an existing video are covered in Professional outputs.
44 models
Seedance 2.5
seedance2_5 Cinematic video up to 30 seconds at 480p, 720p, and 1080p, with a large reference budget for images, videos, and audio.
Seedance 2.0
seedance2 Cinematic video generation with fine-grained control over duration, ratio, and audio.
Seedance 2.0 Fast
seedance2_fast Faster cinematic video at 480p and 720p with duration, aspect ratio, references, and optional audio.
Seedance 2.0 Mini
seedance2_mini The most cost-efficient Seedance 2.0 tier: cinematic video at 480p and 720p with duration, aspect ratio, references, and optional audio.
Aleph 2.0
aleph2 Runway's flagship in-context video editing model with keyframe-guided control.
Gen-4.5
gen4.5 Runway's state-of-the-art text to video and image to video model.
Gen-4 Turbo
gen4_turbo Runway's fastest image to video model.
MiniMax H3
hailuo3 Multimodal video generation with text, image, video, and audio references.
MiniMax H3 Max
h3_max Text-to-video and image-to-video with first and last frames, and native audio at 480p and 768p.
WAN 3.0
wan3 Video generation with native audio, 2–30s duration, and image, video, and audio references at 480p, 720p, and 1080p.
WAN 3.0 Prime
wan3_prime High-speed video generation with native audio, 2–30s duration, and image, video, and audio references at 480p, 720p, and 1080p.
Grok Imagine Video 1.5
grok_imagine_1_5 Fast video generation with native audio, prompt-addressable image references, and audio-driven performance.
Grok Imagine Video 1.5 Lite
grok_imagine_1_5_lite Faster, lower-cost video from text or a start frame, at 480p, 720p, and 1080p.
HappyHorse 1.0
happyhorse_1_0 Video generation with native audio, flexible duration from 3–15s, and ten output ratios.
Veo 3.1
veo3.1 High quality video generation with audio and speech.
Veo 3.1 Fast
veo3.1_fast Faster video generation with audio and speech.
Gemini Omni Flash 1.1
gemini_omni_flash_1.1 Multimodal video with native audio, real-world grounding, and cinematic control.
Gemini Omni Flash
gemini_omni_flash Video generation and editing from text, an image, or a source video.
Act-Two
act_two Runway's motion capture model.
GPT Image 2.5 Sunburst
gpt_image_2_5_sunburst OpenAI's highest-quality image generation and editing model, up to 4K.
GPT Image 2.5 Flare
gpt_image_2_5_flare OpenAI's faster image generation model, up to 4K.
GPT Image 2
gpt_image_2 Image generation and editing, up to 4K.
Nano Banana 2
gemini_image3.1_flash Fast image generation with resolution tiers from 512px up to 4K.
Nano Banana Pro
gemini_image3_pro Image generation with 4K resolution support.
Nano Banana
gemini_2.5_flash Image generation and editing at one rate for any resolution.
Seedream 5.0 Pro
seedream5_pro Reasoning image editing with layer control and multi-reference fusion.
Seedream 5.0 Lite
seedream5_lite Image generation with multi-image fusion and reference editing.
Grok Imagine Image 2
grok_imagine_image_2 Image generation and editing from up to three references, across a wide range of aspect ratios.
Muse Image
muse_image Image generation and editing from multiple references, across eight aspect ratios.
Gen-4 Image Turbo
gen4_image_turbo Runway's fastest and most cost-efficient image model.
Gen-4 Image
gen4_image Runway's image generation model.
Characters
gwm1_avatars Generate a video of a character speaking from a text script or an audio file.
Magnific Precision Upscaler
magnific_precision_upscaler_v2 Image upscaling up to 16x with sharpness and grain controls.
Magnific Video Upscaler
magnific_video_upscaler_creative Video upscaling to 4K with creative detail.
Enhance Frame Rate
enhance_frame_rate Convert a video to a new frame rate.
Ruby
ruby Convert SDR video to true HDR, delivered as HEVC, ProRes, or an EXR sequence.
Eleven v4
eleven_v4 Expressive speech with audio tags like [laughs] and [whispers], in scripts up to 2,500 characters.
Eleven v3
eleven_v3 Expressive speech, with audio tags like [laughs] and [whispers] in the script.
Multilingual v2
eleven_multilingual_v2 Speech with nuanced intonation and emotion.
ElevenLabs Sound Effects
eleven_text_to_sound_v2 Turn text into sound effects.
ElevenLabs Voice Isolation
eleven_voice_isolation Remove background noise from audio.
ElevenLabs Voice Dubbing
eleven_voice_dubbing Translate audio into other languages.
Multilingual Speech to Speech
eleven_multilingual_sts_v2 Change voice while preserving emotion and tone.
Seed Audio 1.0
seed_audio Speech, sound effects, and audio scenes from text, including cloned voices.
No models match.
Seedance 2.5 (seedance2_5) can render a faster 480p preview, then enhance that preview to 1080p. Use a preview to check a prompt, then pay the 1080p rate for the take you keep. See pricing for both rates.
Set draft to true on a normal text to video, image to video, or video to video request. Prompt, ratio, duration (including auto), references, audio, and seed work the same way as a full generation.
The preview is always 480p, and it is billed at the 480p rate. ratio still chooses the aspect ratio: a 720p or 1080p ratio is accepted, and the preview uses the 480p frame for that aspect (16:9 / 9:16 land on 854:480 / 480:854).
{ "model": "seedance2_5", "promptText": "A red panda walks through a lantern-lit alley", "ratio": "1280:720", "duration": 5, "draft": true}Poll the returned task until status is SUCCEEDED. The task id is what you pass to enhance it.
Enhancement is always a text to video request, including when the preview came from image to video or video to video. Send model and draftTaskId only. The 1080p video reuses the preview’s prompt, references, duration, seed, and audio setting — when the preview used duration: "auto", the enhancement uses the measured length. An enhance request that also includes promptText, ratio, duration, seed, audio, references, or draft is rejected.
{ "model": "seedance2_5", "draftTaskId": "11111111-1111-4111-8111-111111111111"}The preview task has to belong to the same account, have succeeded, and have been created with draft: true. Previews can be enhanced within 7 days of creation. The result is 1080p at the preview’s aspect ratio, billed at the 1080p rate for that output duration and any input video. The preview’s charge is unchanged.
| Model | Model ID | Category |
|---|---|---|
| Seedance 2.5 | seedance2_5 | Video |
| Seedance 2.0 | seedance2 | Video |
| Seedance 2.0 Fast | seedance2_fast | Video |
| Seedance 2.0 Mini | seedance2_mini | Video |
| Aleph 2.0 | aleph2 | Video |
| Gen-4.5 | gen4.5 | Video |
| Gen-4 Turbo | gen4_turbo | Video |
| MiniMax H3 | hailuo3 | Video |
| MiniMax H3 Max | h3_max | Video |
| WAN 3.0 | wan3 | Video |
| WAN 3.0 Prime | wan3_prime | Video |
| Grok Imagine Video 1.5 | grok_imagine_1_5 | Video |
| Grok Imagine Video 1.5 Lite | grok_imagine_1_5_lite | Video |
| HappyHorse 1.0 | happyhorse_1_0 | Video |
| Veo 3.1 | veo3.1 | Video |
| Veo 3.1 Fast | veo3.1_fast | Video |
| Gemini Omni Flash 1.1 | gemini_omni_flash_1.1 | Video |
| Gemini Omni Flash | gemini_omni_flash | Video |
| Act-Two | act_two | Video |
| GPT Image 2.5 Sunburst | gpt_image_2_5_sunburst | Image |
| GPT Image 2.5 Flare | gpt_image_2_5_flare | Image |
| GPT Image 2 | gpt_image_2 | Image |
| Nano Banana 2 | gemini_image3.1_flash | Image |
| Nano Banana Pro | gemini_image3_pro | Image |
| Nano Banana | gemini_2.5_flash | Image |
| Seedream 5.0 Pro | seedream5_pro | Image |
| Seedream 5.0 Lite | seedream5_lite | Image |
| Grok Imagine Image 2 | grok_imagine_image_2 | Image |
| Muse Image | muse_image | Image |
| Gen-4 Image Turbo | gen4_image_turbo | Image |
| Gen-4 Image | gen4_image | Image |
| Characters | gwm1_avatars | Real-time |
| Magnific Precision Upscaler | magnific_precision_upscaler_v2 | Upscale & HDR |
| Magnific Video Upscaler | magnific_video_upscaler_creative | Upscale & HDR |
| Enhance Frame Rate | enhance_frame_rate | Upscale & HDR |
| Ruby | ruby | Upscale & HDR |
| Eleven v4 | eleven_v4 | Audio |
| Eleven v3 | eleven_v3 | Audio |
| Multilingual v2 | eleven_multilingual_v2 | Audio |
| ElevenLabs Sound Effects | eleven_text_to_sound_v2 | Audio |
| ElevenLabs Voice Isolation | eleven_voice_isolation | Audio |
| ElevenLabs Voice Dubbing | eleven_voice_dubbing | Audio |
| Multilingual Speech to Speech | eleven_multilingual_sts_v2 | Audio |
| Seed Audio 1.0 | seed_audio | Audio |