The models the Direct API offers, by Morphic model id, with the capabilities and options each one accepts.
You choose a model by its Morphic model id, a stable identifier Morphic issues for each model it offers, such as mdl_7rk2pq9vxa4m. Model ids are opaque: never parse one, and never build one yourself. They are the only model names the API accepts or returns.
This page is the model catalog; there is no model-listing endpoint, and the catalog is updated with each release. It lists capabilities and options, not prices or plan access, since both depend on your plan.
Every tool that runs a model takes an optional model_id:
{ "input" : { "prompt" : "A red vintage bicycle against a pastel wall" , "model_id" : "mdl_3hv8tq1nzc6e" } }
Omit model_id to use your organization's default for that capability.
A model that lacks the capability the call needs is refused with 422, naming the model ids that would have worked.
A model your plan does not include is refused with 403 plan_upgrade_required.
A model your organization's admin has switched off is refused with 403 model_disabled_by_organization. The same applies to resolution caps and audio the admin turned off. An admin can allow it for the API in Studio, under Settings > Groups, with API as a group member.
A retired id keeps working: it runs its replacement, and the response's result.model_id and the generation's model_id name the model that actually ran.
Voices: list_voices returns each voice's voice_id (a UUID) to pass as voice_id. Read them for the model you will use, since each model offers its own voices.
Direct API prices are set per organization and are not published here.
Quote a call before running it with plan_media; see Quote before you spend .
Read what it cost from the billing block of every response.
Your account contact can share your plan's rate sheet.
Field Meaning Model id what you pass as model_id to any tool that takes a model Name, description Morphic's display name and summary, for your own UI Capabilities the jobs the model can do; one model id covers all of them, and each tool picks the right one Default for the capabilities this model runs when a call names no model_id; when the model is the default on some plans only, those plans are named in brackets Status available; retiring, which still works and shows the date it stops running; or retired, which is still accepted and runs its replacement Options the aspect ratios, resolutions, durations, audio and reference inputs it accepts; a tool refuses anything else with 422, naming what is accepted
For example, a still image plus a prompt sent to generate_video runs image_to_video.
Capability Used by text_to_imagegenerate_imageimage_to_imageedit_image, inpaint_image, outpaint_imageimage_upscale, image_enhanceupscale_image, enhance_imagetext_to_video, image_to_video, frames_to_video, reference_to_videogenerate_videovideo_to_video, video_extendedit_videovideo_upscale, video_enhanceupscale_video, enhance_videolip_synclip_synctext_to_speech, dialogue, voice_changegenerate_speech, generate_dialogue, change_voicetext_to_music, text_to_sound_effectgenerate_music, generate_sound_effecttranscriptiontranscribe_media
Model id Name Output Capabilities Default for Status mdl_kgpcqzsd8epwFlux 2 Pro image text_to_image, image_to_image— available mdl_sf51g1e2rk6rSeedream 5.0 Pro image text_to_image, image_to_image— available mdl_pv2v5dqq2xjtSeedream 4.5 image text_to_image, image_to_image— available mdl_kv82p0xahewsZ-Image Turbo image text_to_image— available mdl_8yecvxyad57cKrea 3 image text_to_image, image_to_image— available mdl_ewq6kvyqtem4Krea 2 Large image text_to_image, image_to_image— available mdl_v843mwhdsfspKrea 2 Medium image text_to_image, image_to_image— available mdl_4sa3fdq371skNano Banana image text_to_image, image_to_image— available mdl_cqc9ed1bf0z6Nano Banana Pro image text_to_image, image_to_image— available mdl_emmgrhw0ms1aNano Banana 2 image text_to_image, image_to_image— available mdl_py99s8kz2b58Nano Banana 2 Lite image text_to_image, image_to_image— available mdl_4rkzbakq89peNano Banana 2.1 image text_to_image, image_to_image— available mdl_nakvwskfymspGPT Image 2 image text_to_image, image_to_image, inpaint, outpaint`inpaint` (paid plans), `outpaint` (paid plans) available mdl_3hrdyhgd2shfGPT Image 2.5 Flare image text_to_image, image_to_image— available mdl_1qfcyc2pgtbwGPT Image 2.5 Sunburst image text_to_image, image_to_image— available mdl_rxykgqr6kgggIdeogram 4.5 image text_to_image, image_to_image— available mdl_5caq9gh9zg8jIdeogram Vector image text_to_image, image_to_image— available mdl_g8nbx2hpvw9kIdeogram Vectorize image image_to_image— available mdl_r4gq9p4xyczfVeo 3.1 video text_to_video, image_to_video, frames_to_video, reference_to_video— available mdl_t4g7d55303y0Veo 3.1 Fast video text_to_video, image_to_video, frames_to_video, reference_to_video— available mdl_d874mwye1be0Gemini Omni Flash 1.1 video text_to_video, image_to_video, frames_to_video, reference_to_video, video_to_video— available mdl_s02bvp8hv7x5Seedance 1.5 video text_to_video, image_to_video, frames_to_video`text_to_video` (paid plans), `image_to_video` (paid plans) retiring on 2026-11-10 mdl_wc640n1tnhf3Seedance 2.0 video text_to_video, image_to_video, frames_to_video, reference_to_video, video_to_video, lip_sync— available mdl_jnrga4cvm33dSeedance 2.0 Fast video text_to_video, image_to_video, frames_to_video, reference_to_video, video_to_video, lip_sync— available mdl_xrpsjaqzz4bzSeedance 2.0 Mini video text_to_video, image_to_video, frames_to_video, reference_to_video, video_to_video, lip_sync— available mdl_87p2yqde0s80Seedance 2.5 video text_to_video, image_to_video, frames_to_video, reference_to_video, video_to_video, lip_sync— available mdl_m5z326kfdrptSeedance 2.5 Draft video text_to_video, image_to_video, frames_to_video, reference_to_video— available mdl_6te8xtvsj5k8Hailuo-02 video image_to_video, frames_to_video`frames_to_video` (paid plans) available mdl_7yxemvt3byx5Hailuo 2.3 video text_to_video, image_to_video— available mdl_ch4qvs1rs8z0Hailuo 2.3 Fast video text_to_video, image_to_video— available mdl_ckh1fenv6pt3MiniMax H3 video text_to_video, image_to_video, frames_to_video, reference_to_video`text_to_video` (free plans), `image_to_video` (free plans), `frames_to_video` (free plans), `reference_to_video` (free plans) available mdl_33zjrf7qkkcfMiniMax H3 Max video text_to_video, image_to_video, frames_to_video, reference_to_video— available mdl_9ye5fmg2w3dhMiniMax H3 Max Turbo video text_to_video, image_to_video, frames_to_video— available mdl_qv6whegyyjsrKling O3 video text_to_video, image_to_video, frames_to_video, reference_to_video, video_to_video`video_to_video` (paid plans) available mdl_kxnke1e5c64vKling 3.0 video text_to_video, image_to_video, frames_to_video— available mdl_9wg2492cagxqKling 3.0 Turbo video text_to_video, image_to_video`text_to_video` (paid plans from 2026-11-10), `image_to_video` (paid plans from 2026-11-10) available mdl_sktgb96hhczzKling 4.0 video text_to_video, image_to_video, frames_to_video, reference_to_video, video_to_video— available mdl_zy306yrhanrzKling V3 Motion Control video video_to_video— available mdl_128x7cdrf5z2Runway Ruby video video_enhance— available mdl_nv0kcf1cvfevTopaz Standard V2 image upscale— available mdl_p6s3aqztggpwTopaz Proteus video upscale`upscale` available mdl_p5g9wrh9tjakTopaz Starlight Precise 2.6 video upscale— available mdl_k90zpha6jjrsTopaz Starlight Fast 2 video upscale— available mdl_4wgsv0br5626Topaz Astra 2 video upscale— available mdl_v1c4t818wsftTopaz Wonder 3.5 image upscale— available mdl_0a0zsm0p68v9Topaz Bloom 2 image upscale— available mdl_m7y28tyzh344Topaz Denoise image image_enhance`image_enhance` (paid plans) available mdl_3g9g4b7f4c1vTopaz Sharpen image image_enhance— available mdl_2y38g56mtby1Topaz Restore image image_enhance— available mdl_77vze5qxsabaTopaz Adjust Lighting image image_enhance— available mdl_aav1622cpgasTopaz Hyperion 2.5 video video_enhance`video_enhance` (paid plans) available mdl_83nkqpbtxwg2Topaz Nyx video video_enhance— available mdl_2rstmex03ca3Topaz Themis 2 video video_enhance— available mdl_ywvb00c4ygdqCrystal Image image upscale`upscale` available mdl_4hvp9jn623nyCrystal Video video upscale— available mdl_gvhet4g9qqseFlux Video video upscale— available mdl_p8nypk3yydj0Morphic Extend video video_to_video— available mdl_bp2fc8dy6q5eLuma Ray 3.2 Reframe video video_to_video— available mdl_p99v6e90k318Recast video reference_to_video, video_to_video— available mdl_pc191jv39a6yRecast Pro video reference_to_video, video_to_video— available mdl_1etjytvp14a9Reframe video video_to_video— available mdl_7gz2zmegw61pMorphic H3 video text_to_video, image_to_video, reference_to_video— available mdl_z2s6p1m52ngnMorphic H3 Ultra video text_to_video, image_to_video, reference_to_video— available mdl_qjbj92pchfdsByteDance Video video upscale— available mdl_8g4ty3by1c5sElevenLabs audio voice_change, text_to_music, text_to_sound_effect`voice_change`, `text_to_music`, `text_to_sound_effect` available mdl_xbxjt9z7wkk1ElevenLabs v4 audio text_to_speech, dialogue`text_to_speech` available mdl_g8045h3868f6Wan 3.0 video text_to_video, image_to_video, frames_to_video, reference_to_video`reference_to_video` (paid plans) available mdl_a1f9tn00qy7qWan 3.0 Prime video text_to_video, image_to_video, frames_to_video, reference_to_video— available mdl_4x2sa4w82gy8Happy Horse video text_to_video, image_to_video, reference_to_video— available mdl_pzydnm90f968Gemini 3.8 Flash TTS audio text_to_speech, dialogue— available mdl_mvwzsh3wyk33Gemini 3.8 Flash-Lite TTS audio text_to_speech, dialogue— available mdl_ra3hy3a397ybSeed Audio 1.0 audio text_to_speech, dialogue, text_to_music, text_to_sound_effect`dialogue` available mdl_f5y1v7de83bdMiniMax Music 3 audio text_to_music— available mdl_nv3cp228aq9tGoogle Lyria 3 audio text_to_music— available mdl_15xpqgmzpsd0Google Lyria 3.5 audio text_to_music— available mdl_nc2y4tvxhde9Google Lyria 3 Clip audio text_to_music— available mdl_g9p2apngr4h1xAI Grok TTS audio text_to_speech— available mdl_1pavem2p2qh5ElevenLabs v4 Turbo audio text_to_speech, dialogue— available mdl_catdq74qcq34Inworld TTS 2 audio text_to_speech— available mdl_r283w0rht2rsInworld TTS 2 Flash audio text_to_speech— available mdl_wapq8x5020zvFish Audio Drama 3 audio text_to_speech, dialogue— available mdl_82g43qtcqmbrVidu Q3 video text_to_video, frames_to_video— available mdl_ns11vydjd68hVidu Q3 Fast video text_to_video, frames_to_video— available mdl_5ag2xn68yre6Vidu Q4 video image_to_video, reference_to_video— available mdl_zsdtcwgcfh59Grok Imagine image, video text_to_image, image_to_image, text_to_video, image_to_video, reference_to_video, video_to_video`text_to_image`, `image_to_image` available mdl_s46fg2pvyyq1Grok Imagine Pro image image_to_image— available mdl_taxsk9yr1px5Grok Imagine 1.5 video text_to_video, image_to_video, reference_to_video— available mdl_f7yst7vypndcGrok Imagine Image 2.0 image text_to_image, image_to_image— available mdl_f69tthqkwwncQwen Edit Angles image image_to_image— available mdl_m6ck5frt6angQwen Image 2.1 image text_to_image, image_to_image— available mdl_mg9364gt8tf9Recraft V4.1 image text_to_image— available mdl_8bwn03gryceeRecraft V4.1 Pro image text_to_image— available mdl_h4rr1255y3gwRecraft V4.1 Flash image text_to_image— available mdl_2wk9jsm954qeLTX 2.5 video text_to_video, image_to_video, reference_to_video, lip_sync— available mdl_gtv6d0bf56ezLTX 2.5 Fast video text_to_video, image_to_video— available mdl_z771nx182pfvMorphic Edit image, video text_to_image, image_to_image, text_to_video, image_to_video, frames_to_video, video_to_video— available mdl_dg0bkv8gqczzFLUX 3 Max video text_to_video, image_to_video, frames_to_video— available mdl_v3m6k7ya8gxnSync V3 video lip_sync`lip_sync` available mdl_18ej026xxdaxVeed Fabric video lip_sync— available mdl_a2fp90bgh080Kling Lip Sync video lip_sync— available mdl_93nteqvn3dhvOmniHuman 2.0 video lip_sync— available mdl_4b2m5g20rr5qMirelo SFX 2.0 video, audio video_to_video, text_to_sound_effect— available mdl_gvmfbpd64vv9Sonilo SFX video video_to_video— available
Photorealistic images and edits with sharp detail, from up to 10 reference images.
Model id mdl_kgpcqzsd8epwOutput image Capabilities text_to_image, image_to_imageDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_image16:9, 9:16, 4:3, 3:4, 1:1, 4:5, 5:4 (default 16:9) — — — — image_to_image1:1, 16:9, 9:16, 4:3, 3:4, 4:5, 5:4, auto (default auto) — — — 1–10 images
Cinematic realism and multilingual text, with precise multi-reference edits up to 1440p.
Model id mdl_sf51g1e2rk6rOutput image Capabilities text_to_image, image_to_imageDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_image16:9, 4:3, 5:4, 1:1, 4:5, 3:4, 9:16, auto (default auto) 1080p, 1440p (default 1080p) — — — image_to_image1:1, 16:9, 9:16, 4:3, 3:4, 4:5, 5:4, auto (default auto) 1080p, 1440p (default 1080p) — — 1–10 images
Strong multilingual typography for posters and branding, up to 4K.
Model id mdl_pv2v5dqq2xjtOutput image Capabilities text_to_image, image_to_imageDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_image16:9, 4:3, 5:4, 1:1, 4:5, 3:4, 9:16, auto (default auto) 1440p, 2160p (default 1440p) — — — image_to_image1:1, 16:9, 9:16, 4:3, 3:4, 4:5, 5:4, auto (default auto) 1440p, 2160p (default 1440p) — — 1–14 images
Ultra-fast text-to-image drafts for quick iteration.
Model id mdl_kv82p0xahewsOutput image Capabilities text_to_imageDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_image16:9, 4:3, 5:4, 1:1, 4:5, 3:4, 9:16 (default 16:9) — — — —
Fast, versatile, high-quality images and edits up to 1440p.
Model id mdl_8yecvxyad57cOutput image Capabilities text_to_image, image_to_imageDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_imageauto, 1:1, 4:5, 3:4, 2:3, 9:16, 5:4, 4:3, 3:2, 16:9, 21:9 (default auto) 1080p, 1440p (default 1080p) — — — image_to_imageauto, 1:1, 4:5, 3:4, 2:3, 9:16, 5:4, 4:3, 3:2, 16:9, 21:9 (default auto) 1080p, 1440p (default 1080p) — — 1–4 images
Photorealistic images and style transfer with sharp detail.
Model id mdl_ewq6kvyqtem4Output image Capabilities text_to_image, image_to_imageDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_image16:9, 4:3, 3:2, 1:1, 2:3, 4:5, 9:16 (default 16:9) — — — — image_to_image16:9, 4:3, 3:2, 1:1, 2:3, 4:5, 9:16 (default 16:9) — — — 1–10 images
Fast everyday images and artistic style transfer.
Model id mdl_v843mwhdsfspOutput image Capabilities text_to_image, image_to_imageDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_image16:9, 4:3, 3:2, 1:1, 2:3, 4:5, 9:16 (default 16:9) — — — — image_to_image16:9, 4:3, 3:2, 1:1, 2:3, 4:5, 9:16 (default 16:9) — — — 1–10 images
Fast, versatile everyday images and edits.
Model id mdl_4sa3fdq371skOutput image Capabilities text_to_image, image_to_imageDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_image21:9, 16:9, 4:3, 5:4, 1:1, 4:5, 3:4, 9:16 (default 16:9) — — — — image_to_image21:9, 16:9, 4:3, 5:4, 1:1, 4:5, 3:4, 9:16, auto (default 16:9) — — — 1–10 images
Rich detail and complex scenes, with edits from up to 14 references, up to 4K.
Model id mdl_cqc9ed1bf0z6Output image Capabilities text_to_image, image_to_imageDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_image21:9, 16:9, 4:3, 5:4, 1:1, 4:5, 3:4, 9:16, auto (default auto) 1080p, 1440p, 2160p (default 1080p) — — — image_to_image21:9, 16:9, 4:3, 5:4, 1:1, 4:5, 3:4, 9:16, auto (default auto) 1080p, 1440p, 2160p (default 1080p) — — 1–14 images
Fast, high-quality images and edits from up to 14 references, up to 4K.
Model id mdl_emmgrhw0ms1aOutput image Capabilities text_to_image, image_to_imageDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_image21:9, 16:9, 4:3, 5:4, 1:1, 4:5, 3:4, 9:16, auto (default auto) 540p, 1080p, 1440p, 2160p (default 1080p) — — — image_to_image21:9, 16:9, 4:3, 5:4, 1:1, 4:5, 3:4, 9:16, auto (default auto) 540p, 1080p, 1440p, 2160p (default 1080p) — — 1–14 images
The fastest, lowest-cost images and edits.
Model id mdl_py99s8kz2b58Output image Capabilities text_to_image, image_to_imageDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_image21:9, 16:9, 4:3, 5:4, 1:1, 4:5, 3:4, 9:16, auto (default auto) — — — — image_to_image21:9, 16:9, 4:3, 5:4, 1:1, 4:5, 3:4, 9:16, auto (default auto) — — — 1–14 images
Fast, polished designs with legible text and consistent subjects, up to 4K.
Model id mdl_4rkzbakq89peOutput image Capabilities text_to_image, image_to_imageDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_image21:9, 16:9, 4:3, 5:4, 1:1, 4:5, 3:4, 9:16, auto (default auto) 1080p, 1440p, 2160p (default 1080p) — — — image_to_image21:9, 16:9, 4:3, 5:4, 1:1, 4:5, 3:4, 9:16, auto (default auto) 1080p, 1440p, 2160p (default 1080p) — — 1–14 images
Strong prompt adherence and text rendering, with inpainting and outpainting, up to 4K.
Model id mdl_nakvwskfymspOutput image Capabilities text_to_image, image_to_image, inpaint, outpaintDefault for `inpaint` (paid plans), `outpaint` (paid plans) Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_image21:9, 16:9, 4:3, 5:4, 1:1, 4:5, 3:4, 9:16 (default 16:9) 1080p, 1440p, 2160p (default 1080p) — — — image_to_image21:9, 16:9, 4:3, 5:4, 1:1, 4:5, 3:4, 9:16, auto (default auto) 1080p, 1440p, 2160p (default 1080p) — — 1–10 images inpaint— — — — 2 images outpaint— — — — 1 image
Fast, high-quality everyday images and edits, up to 4K.
Model id mdl_3hrdyhgd2shfOutput image Capabilities text_to_image, image_to_imageDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_image21:9, 16:9, 4:3, 5:4, 1:1, 4:5, 3:4, 9:16 (default 16:9) 1080p, 1440p, 2160p (default 1080p) — — — image_to_image21:9, 16:9, 4:3, 5:4, 1:1, 4:5, 3:4, 9:16, auto (default auto) 1080p, 1440p, 2160p (default 1080p) — — 1–10 images
Precise, subject-preserving edits across many steps, up to 4K.
Model id mdl_1qfcyc2pgtbwOutput image Capabilities text_to_image, image_to_imageDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_image21:9, 16:9, 4:3, 5:4, 1:1, 4:5, 3:4, 9:16 (default 16:9) 1080p, 1440p, 2160p (default 1080p) — — — image_to_image21:9, 16:9, 4:3, 5:4, 1:1, 4:5, 3:4, 9:16, auto (default auto) 1080p, 1440p, 2160p (default 1080p) — — 1–10 images
Accurate text, typography and graphic design, with edits that change only what you ask.
Model id mdl_rxykgqr6kgggOutput image Capabilities text_to_image, image_to_imageDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_image16:9, 9:16, 4:3, 3:4, 1:1, 4:5, 5:4, 3:2, 2:3 (default 16:9) 1080p, 1440p (default 1440p) — — — image_to_image16:9, 9:16, 4:3, 3:4, 1:1, 4:5, 5:4, 3:2, 2:3, auto (default auto) 1080p, 1440p (default 1440p) — — 1–5 images
Scalable SVG logos, icons and flat illustrations.
Model id mdl_5caq9gh9zg8jOutput image Capabilities text_to_image, image_to_imageDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_image1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 4:5, 5:4, 2:1, 1:2, 3:1, 1:3 (default 1:1) — — — — image_to_imageauto, 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 4:5, 5:4, 2:1, 1:2, 3:1, 1:3 (default auto) — — — 1–5 images
Traces an image into a clean, editable SVG without changing it.
Model id mdl_g8nbx2hpvw9kOutput image Capabilities image_to_imageDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs image_to_image— — — — 1 image
Cinematic realism with dialogue, lip-sync and native audio, 4–8 s up to 4K.
Model id mdl_r4gq9p4xyczfOutput video Capabilities text_to_video, image_to_video, frames_to_video, reference_to_videoDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_video16:9, 9:16 (default 16:9) 720p, 1080p, 2160p (default 1080p) 4, 6, 8 s, default 4 s optional — image_to_video16:9, 9:16, auto (default auto) 720p, 1080p, 2160p (default 1080p) 4, 6, 8 s, default 4 s optional 1 image frames_to_video16:9, 9:16, auto (default auto) 720p, 1080p, 2160p (default 1080p) 4, 6, 8 s, default 4 s optional 2 images reference_to_video16:9, 9:16 (default 16:9) 720p, 1080p, 2160p (default 1080p) 8 s, default 8 s optional 1–3 images
Faster Veo 3.1 clips with native audio, 4–8 s up to 4K.
Model id mdl_t4g7d55303y0Output video Capabilities text_to_video, image_to_video, frames_to_video, reference_to_videoDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_video16:9, 9:16 (default 16:9) 720p, 1080p, 2160p (default 1080p) 4, 6, 8 s, default 4 s optional — image_to_video16:9, 9:16, auto (default auto) 720p, 1080p, 2160p (default 720p) 4, 6, 8 s, default 4 s optional 1 image frames_to_video16:9, 9:16, auto (default auto) 720p, 1080p, 2160p (default 1080p) 4, 6, 8 s, default 4 s optional 2 images reference_to_video16:9, 9:16 (default 16:9) 720p, 1080p, 2160p (default 1080p) 8 s, default 8 s optional 1–3 images
Fast, affordable video and in-place video edits with native audio, up to 10 s.
Model id mdl_d874mwye1be0Output video Capabilities text_to_video, image_to_video, frames_to_video, reference_to_video, video_to_videoDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_video16:9, 9:16 (default 16:9) 360p, 720p, 1080p, 2160p (default 720p) 3–10 s, default 8 s always — image_to_video16:9, 9:16 (default 16:9) 360p, 720p, 1080p, 2160p (default 720p) 3–10 s, default 8 s always 1 image frames_to_video16:9, 9:16 (default 16:9) 360p, 720p, 1080p, 2160p (default 720p) 3–10 s, default 8 s always 2 images reference_to_video16:9, 9:16 (default 16:9) 360p, 720p, 1080p, 2160p (default 720p) 3–10 s, default 8 s always up to 10 images, up to 3 videos video_to_video— 360p, 720p, 1080p, 2160p (default 720p) — always 1 video
Consistent characters across multi-shot clips, up to 12 s at 1080p.
Model id mdl_s02bvp8hv7x5Output video Capabilities text_to_video, image_to_video, frames_to_videoDefault for `text_to_video` (paid plans), `image_to_video` (paid plans) Status retiring on 2026-11-10
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_video21:9, 16:9, 4:3, 1:1, 3:4, 9:16, auto (default auto) 480p, 720p, 1080p (default 1080p) 4–12 s, default 4 s optional — image_to_video21:9, 16:9, 4:3, 1:1, 3:4, 9:16, auto (default auto) 480p, 720p, 1080p (default 1080p) 4–12 s, default 5 s optional 1 image frames_to_video21:9, 16:9, 4:3, 1:1, 3:4, 9:16 (default 16:9) 480p, 720p, 1080p (default 1080p) 4–12 s, default 4 s optional 2 images
Multi-shot video with multi-reference character control and audio-driven generation, up to 15 s and 4K.
Model id mdl_wc640n1tnhf3Output video Capabilities text_to_video, image_to_video, frames_to_video, reference_to_video, video_to_video, lip_syncDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_video21:9, 16:9, 4:3, 1:1, 3:4, 9:16, auto (default auto) 2160p, 1080p, 720p, 480p (default 1080p) 4–15 s, default 5 s optional — image_to_video21:9, 16:9, 4:3, 1:1, 3:4, 9:16, auto (default auto) 2160p, 1080p, 720p, 480p (default 1080p) 4–15 s, default 5 s optional 1 image frames_to_videoauto, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 (default auto) 2160p, 1080p, 720p, 480p (default 1080p) 4–15 s, default 5 s optional 2 images reference_to_video21:9, 16:9, 4:3, 1:1, 3:4, 9:16, auto (default auto) 2160p, 1080p, 720p, 480p (default 1080p) 4–15 s, default 5 s optional up to 9 images, up to 3 videos, up to 3 audio clips video_to_video21:9, 16:9, 4:3, 1:1, 3:4, 9:16, auto (default auto) 2160p, 1080p, 720p, 480p (default 1080p) 4–15 s, default 5 s optional up to 9 images, 1–3 videos, up to 3 audio clips lip_sync21:9, 16:9, 4:3, 1:1, 3:4, 9:16, auto (default auto) 2160p, 1080p, 720p, 480p (default 480p) 4–15 s, default 5 s always up to 9 images, up to 3 videos, up to 3 audio clips
Faster Seedance 2.0 with the same controls, up to 15 s at 720p.
Model id mdl_jnrga4cvm33dOutput video Capabilities text_to_video, image_to_video, frames_to_video, reference_to_video, video_to_video, lip_syncDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_video21:9, 16:9, 4:3, 1:1, 3:4, 9:16, auto (default auto) 720p, 480p (default 720p) 4–15 s, default 5 s optional — image_to_video21:9, 16:9, 4:3, 1:1, 3:4, 9:16, auto (default auto) 720p, 480p (default 720p) 4–15 s, default 5 s optional 1 image frames_to_videoauto, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 (default auto) 720p, 480p (default 720p) 4–15 s, default 5 s optional 2 images reference_to_video21:9, 16:9, 4:3, 1:1, 3:4, 9:16, auto (default auto) 720p, 480p (default 720p) 4–15 s, default 5 s optional up to 9 images, up to 3 videos, up to 3 audio clips video_to_video21:9, 16:9, 4:3, 1:1, 3:4, 9:16, auto (default auto) 720p, 480p (default 720p) 4–15 s, default 5 s optional up to 9 images, 1–3 videos, up to 3 audio clips lip_sync21:9, 16:9, 4:3, 1:1, 3:4, 9:16, auto (default auto) 720p, 480p (default 480p) 4–15 s, default 5 s always up to 9 images, up to 3 videos, up to 3 audio clips
The lowest-cost Seedance 2.0, up to 15 s at 720p.
Model id mdl_xrpsjaqzz4bzOutput video Capabilities text_to_video, image_to_video, frames_to_video, reference_to_video, video_to_video, lip_syncDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_video21:9, 16:9, 4:3, 1:1, 3:4, 9:16, auto (default auto) 720p, 480p (default 720p) 4–15 s, default 5 s optional — image_to_video21:9, 16:9, 4:3, 1:1, 3:4, 9:16, auto (default auto) 720p, 480p (default 720p) 4–15 s, default 5 s optional 1 image frames_to_videoauto, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 (default auto) 720p, 480p (default 720p) 4–15 s, default 5 s optional 2 images reference_to_video21:9, 16:9, 4:3, 1:1, 3:4, 9:16, auto (default auto) 720p, 480p (default 720p) 4–15 s, default 5 s optional up to 9 images, up to 3 videos, up to 3 audio clips video_to_video21:9, 16:9, 4:3, 1:1, 3:4, 9:16, auto (default auto) 720p, 480p (default 720p) 4–15 s, default 5 s optional up to 9 images, 1–3 videos, up to 3 audio clips lip_sync21:9, 16:9, 4:3, 1:1, 3:4, 9:16, auto (default auto) 720p, 480p (default 480p) 4–15 s, default 5 s always up to 9 images, up to 3 videos, up to 3 audio clips
Clips up to 30 s with multi-reference control, video editing and extension, up to 1080p.
Model id mdl_87p2yqde0s80Output video Capabilities text_to_video, image_to_video, frames_to_video, reference_to_video, video_to_video, lip_syncDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_video21:9, 16:9, 4:3, 1:1, 3:4, 9:16, auto (default auto) 720p, 480p, 1080p (default 720p) 4–30 s, default 5 s optional — image_to_videoauto 720p, 480p, 1080p (default 720p) 4–30 s, default 5 s optional 1 image frames_to_videoauto 720p, 480p, 1080p (default 720p) 4–30 s, default 5 s optional 2 images reference_to_video21:9, 16:9, 4:3, 1:1, 3:4, 9:16, auto (default auto) 720p, 480p, 1080p (default 720p) 4–30 s, default 5 s optional up to 30 images, up to 10 videos, up to 10 audio clips video_to_videoauto 720p, 480p, 1080p (default 720p) 4–30 s optional up to 30 images, 1–10 videos, up to 10 audio clips lip_sync21:9, 16:9, 4:3, 1:1, 3:4, 9:16, auto (default auto) 720p, 480p, 1080p (default 480p) 4–30 s, default 5 s always up to 30 images, up to 10 videos, up to 10 audio clips
Fast, low-cost 480p previews of Seedance 2.5 that finalize to 1080p within 7 days.
Model id mdl_m5z326kfdrptOutput video Capabilities text_to_video, image_to_video, frames_to_video, reference_to_videoDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_video21:9, 16:9, 4:3, 1:1, 3:4, 9:16, auto (default auto) 480p 4–30 s, default 5 s optional — image_to_videoauto 480p 4–30 s, default 5 s optional 1 image frames_to_videoauto 480p 4–30 s, default 5 s optional 2 images reference_to_video21:9, 16:9, 4:3, 1:1, 3:4, 9:16, auto (default auto) 480p 4–30 s, default 5 s optional up to 30 images, up to 10 videos, up to 10 audio clips
Expressive character animation in single-shot 6 s clips.
Model id mdl_6te8xtvsj5k8Output video Capabilities image_to_video, frames_to_videoDefault for `frames_to_video` (paid plans) Status available
Capability Aspect ratios Resolutions Duration Audio Inputs image_to_video— — 6 s, default 6 s — 1 image frames_to_video— — 6 s, default 6 s — 2 images
Expressive characters and stylized motion in 6 s clips.
Model id mdl_7yxemvt3byx5Output video Capabilities text_to_video, image_to_videoDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_video— — 6 s, default 6 s — — image_to_video— — 6 s, default 6 s — 1 image
Faster Hailuo 2.3 clips with expressive, stylized motion.
Model id mdl_ch4qvs1rs8z0Output video Capabilities text_to_video, image_to_videoDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_video— — 6 s, default 6 s — — image_to_video— — 6 s, default 6 s — 1 image
Expressive characters and multi-reference composition, 5–15 s up to 1440p.
Model id mdl_ckh1fenv6pt3Output video Capabilities text_to_video, image_to_video, frames_to_video, reference_to_videoDefault for `text_to_video` (free plans), `image_to_video` (free plans), `frames_to_video` (free plans), `reference_to_video` (free plans) Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_video21:9, 16:9, 4:3, 1:1, 3:4, 9:16 (default 16:9) 768p, 1440p (default 1440p) 5–15 s, default 5 s — — image_to_video— 768p, 1440p (default 1440p) 5–15 s, default 5 s — 1 image frames_to_video— 768p, 1440p (default 1440p) 5–15 s, default 5 s — 2 images reference_to_video21:9, 16:9, 4:3, 1:1, 3:4, 9:16, auto (default 16:9) 768p, 1440p (default 1440p) 5–15 s, default 5 s — up to 9 images, up to 3 videos, up to 3 audio clips
Fast cinematic clips with strong prompt adherence and native audio, 5–15 s at 1080p.
Model id mdl_33zjrf7qkkcfOutput video Capabilities text_to_video, image_to_video, frames_to_video, reference_to_videoDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_video21:9, 16:9, 4:3, 1:1, 3:4, 9:16 (default 16:9) 480p, 768p, 1080p (default 768p) 5–15 s, default 5 s — — image_to_video— 480p, 768p, 1080p (default 768p) 5–15 s, default 5 s — 1 image frames_to_video— 480p, 768p, 1080p (default 768p) 5–15 s, default 5 s — 2 images reference_to_video21:9, 16:9, 4:3, 1:1, 3:4, 9:16, auto (default 16:9) 480p, 768p, 1080p (default 768p) 5–15 s, default 5 s — up to 9 images, up to 3 videos, up to 3 audio clips
Faster, lower-cost MiniMax H3 Max clips, 5–15 s at 1080p.
Model id mdl_9ye5fmg2w3dhOutput video Capabilities text_to_video, image_to_video, frames_to_videoDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_video21:9, 16:9, 4:3, 1:1, 3:4, 9:16 (default 16:9) 480p, 768p, 1080p (default 768p) 5–15 s, default 5 s — — image_to_video— 480p, 768p, 1080p (default 768p) 5–15 s, default 5 s — 1 image frames_to_video— 480p, 768p, 1080p (default 768p) 5–15 s, default 5 s — 2 images
Cinematic motion with labelled character references and video style transfer, up to 15 s and 4K.
Model id mdl_qv6whegyyjsrOutput video Capabilities text_to_video, image_to_video, frames_to_video, reference_to_video, video_to_videoDefault for `video_to_video` (paid plans) Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_video16:9, 9:16, 1:1 (default 16:9) 720p, 1080p, 2160p (default 720p) 3–15 s, default 5 s always — image_to_video— 720p, 1080p, 2160p (default 720p) 3–15 s, default 5 s always 1 image frames_to_video— 720p, 1080p, 2160p (default 720p) 3–15 s, default 5 s optional 2 images reference_to_video16:9, 9:16, 1:1 (default 16:9) 720p, 1080p, 2160p (default 720p) 3–15 s, default 5 s always 1–4 images, up to 1 video video_to_video— 720p, 1080p (default 720p) — optional 1 video
Cinematic visuals and fluid motion with native audio, up to 15 s and 4K.
Model id mdl_kxnke1e5c64vOutput video Capabilities text_to_video, image_to_video, frames_to_videoDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_video16:9, 9:16, 1:1 (default 16:9) 720p, 1080p, 2160p (default 720p) 3–15 s, default 5 s optional — image_to_video— 720p, 1080p, 2160p (default 720p) 3–15 s, default 5 s optional 1 image frames_to_video— 720p, 1080p, 2160p (default 720p) 3–15 s, default 5 s optional 2 images
Faster Kling 3.0 clips with native audio, up to 15 s at 1080p.
Model id mdl_9wg2492cagxqOutput video Capabilities text_to_video, image_to_videoDefault for `text_to_video` (paid plans from 2026-11-10), `image_to_video` (paid plans from 2026-11-10) Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_video16:9, 9:16, 1:1 (default 16:9) 720p, 1080p (default 720p) 3–15 s, default 5 s always — image_to_video— 720p, 1080p (default 720p) 3–15 s, default 5 s always 1 image
Cinematic clips up to 30 s with native audio, references and length-preserving edits.
Model id mdl_sktgb96hhczzOutput video Capabilities text_to_video, image_to_video, frames_to_video, reference_to_video, video_to_videoDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_video21:9, 16:9, 9:16, 1:1 (default 16:9) 720p, 1080p (default 720p) 3–30 s, default 5 s always — image_to_video— 720p, 1080p (default 720p) 3–30 s, default 5 s always 1 image frames_to_video— 720p, 1080p (default 720p) 3–30 s, default 5 s always 2 images reference_to_videoauto, 21:9, 16:9, 9:16, 1:1 (default auto) 720p, 1080p (default 720p) 3–30 s, default 5 s always up to 10 images, up to 5 videos video_to_video— 720p, 1080p (default 720p) — always up to 10 images, 1 video
Transfers motion from a video onto a character image, keeping the face consistent.
Model id mdl_zy306yrhanrzOutput video Capabilities video_to_videoDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs video_to_video— — — optional 1 image, 1 video
HDR10, HLG or HDR ProRes delivery from SDR video.
Model id mdl_128x7cdrf5z2Output video Capabilities video_enhanceDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs video_enhance— — — — 1 video
High-resolution image upscaling.
Model id mdl_nv0kcf1cvfevOutput image Capabilities upscaleDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs upscale— — — — 1 image
Video upscaling with deep restoration.
Model id mdl_p6s3aqztggpwOutput video Capabilities upscaleDefault for `upscale` Status available
Capability Aspect ratios Resolutions Duration Audio Inputs upscale— — — — 1 video
Restores AI-generated video, fixing plastic skin, faces and text.
Model id mdl_p5g9wrh9tjakOutput video Capabilities upscaleDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs upscale— — — — 1 video
Fast, lower-cost generative video upscaling.
Model id mdl_k90zpha6jjrsOutput video Capabilities upscaleDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs upscale— — — — 1 video
Creative 4K upscaling of AI-generated video.
Model id mdl_4wgsv0br5626Output video Capabilities upscaleDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs upscale— — — — 1 video
Generative image upscaling with detail recovery.
Model id mdl_v1c4t818wsftOutput image Capabilities upscaleDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs upscale— — — — 1 image
Creative image upscaling and reinterpretation.
Model id mdl_0a0zsm0p68v9Output image Capabilities upscaleDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs upscale— — — — 1 image
Removes noise and grain from photos.
Model id mdl_m7y28tyzh344Output image Capabilities image_enhanceDefault for `image_enhance` (paid plans) Status available
Capability Aspect ratios Resolutions Duration Audio Inputs image_enhance— — — — 1 image
Fixes blur and soft focus in photos.
Model id mdl_3g9g4b7f4c1vOutput image Capabilities image_enhanceDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs image_enhance— — — — 1 image
Restores old or damaged photos.
Model id mdl_2y38g56mtby1Output image Capabilities image_enhanceDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs image_enhance— — — — 1 image
Corrects color and lighting in photos.
Model id mdl_77vze5qxsabaOutput image Capabilities image_enhanceDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs image_enhance— — — — 1 image
Converts SDR video to HDR.
Model id mdl_aav1622cpgasOutput video Capabilities video_enhanceDefault for `video_enhance` (paid plans) Status available
Capability Aspect ratios Resolutions Duration Audio Inputs video_enhance— — — — 1 video
Removes noise and grain from video.
Model id mdl_83nkqpbtxwg2Output video Capabilities video_enhanceDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs video_enhance— — — — 1 video
Fixes motion blur in video.
Model id mdl_2rstmex03ca3Output video Capabilities video_enhanceDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs video_enhance— — — — 1 video
Image upscaling with detail restoration.
Model id mdl_ywvb00c4ygdqOutput image Capabilities upscaleDefault for `upscale` Status available
Capability Aspect ratios Resolutions Duration Audio Inputs upscale— — — — 1 image
General-purpose video upscaling.
Model id mdl_4hvp9jn623nyOutput video Capabilities upscaleDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs upscale— — — — 1 video
Super-resolution video upscaling to 1080p, 2K or 4K.
Model id mdl_gvhet4g9qqseOutput video Capabilities upscaleDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs upscale— — — — 1 video
Seamlessly extends a video, up to 20 s.
Model id mdl_p8nypk3yydj0Output video Capabilities video_to_videoDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs video_to_video— 720p, 1080p (default 720p) 5–20 s, default 5 s optional 1 video
Reframes a clip to a new aspect ratio, keeping the footage and filling the new canvas.
Model id mdl_bp2fc8dy6q5eOutput video Capabilities video_to_videoDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs video_to_video9:16, 3:4, 1:1, 4:3, 16:9, 21:9 540p, 720p, 1080p (default 720p) — always 1 video
Replaces the people on screen while keeping the clip's motion, cuts and audio.
Model id mdl_p99v6e90k318Output video Capabilities reference_to_video, video_to_videoDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs reference_to_video— 768p, 1080p (default 1080p) — always 1–4 images, 1 video video_to_video— 768p, 1080p (default 1080p) — always 1–4 images, 1 video
Highest-fidelity recasting, each swap named in the prompt, keeping motion, cuts and audio.
Model id mdl_pc191jv39a6yOutput video Capabilities reference_to_video, video_to_videoDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs reference_to_video— 720p, 1080p (default 720p) — always 1–10 images, 1 video video_to_video— 720p, 1080p (default 720p) — always 1–10 images, 1 video
Reframes a clip to a new aspect ratio at low cost, filling the new canvas.
Model id mdl_1etjytvp14a9Output video Capabilities video_to_videoDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs video_to_video9:21, 9:16, 3:4, 1:1, 4:3, 16:9, 21:9 480p, 768p (default 768p) — always 1 video
Fast, affordable video with native audio from text, an image or references, 5–15 s up to 1440p.
Model id mdl_7gz2zmegw61pOutput video Capabilities text_to_video, image_to_video, reference_to_videoDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_video21:9, 16:9, 4:3, 1:1, 3:4, 9:16 (default 16:9) 480p, 768p, 1080p, 1440p (default 768p) 5–15 s, default 5 s always — image_to_video— 480p, 768p (default 768p) 5–15 s, default 5 s always 1 image reference_to_video21:9, 16:9, 4:3, 1:1, 3:4, 9:16, auto (default auto) 480p, 768p, 1080p, 1440p (default 768p) 5–15 s, default 5 s always up to 9 images, up to 3 videos, up to 3 audio clips
Morphic H3 at its highest quality, with native audio; slower renders.
Model id mdl_z2s6p1m52ngnOutput video Capabilities text_to_video, image_to_video, reference_to_videoDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_video21:9, 16:9, 4:3, 1:1, 3:4, 9:16 (default 16:9) 480p, 768p, 1080p, 1440p (default 768p) 5–15 s, default 5 s always — image_to_video— 480p, 768p (default 768p) 5–15 s, default 5 s always 1 image reference_to_video21:9, 16:9, 4:3, 1:1, 3:4, 9:16, auto (default auto) 480p, 768p, 1080p, 1440p (default 768p) 5–15 s, default 5 s always up to 9 images, up to 3 videos, up to 3 audio clips
Enhances AI-generated, user-made and old-film video.
Model id mdl_qjbj92pchfdsOutput video Capabilities upscaleDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs upscale— — — — 1 video
Songs, sound effects, and re-voicing a recording with its timing kept.
Model id mdl_8g4ty3by1c5sOutput audio Capabilities voice_change, text_to_music, text_to_sound_effectDefault for `voice_change`, `text_to_music`, `text_to_sound_effect` Status available
Capability Aspect ratios Resolutions Duration Audio Inputs voice_change— — — — 1 audio clip text_to_music— — 5–300 s, default 30 s — — text_to_sound_effect— — 0.5–22 s, default 5 s — —
Voiceovers, narration, voice cloning and multi-speaker dialogue.
Model id mdl_xbxjt9z7wkk1Output audio Capabilities text_to_speech, dialogueDefault for `text_to_speech` Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_speech— — — — — dialogue— — — — —
Long clips up to 30 s with native audio and multi-shot narratives, from up to 10 references.
Model id mdl_g8045h3868f6Output video Capabilities text_to_video, image_to_video, frames_to_video, reference_to_videoDefault for `reference_to_video` (paid plans) Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_video16:9, 9:16, 1:1, 4:3, 3:4 (default 16:9) 480p, 720p, 1080p (default 1080p) 2–30 s, default 5 s optional — image_to_video— 480p, 720p, 1080p (default 1080p) 2–30 s, default 5 s optional 1 image frames_to_video— 480p, 720p, 1080p (default 1080p) 2–30 s, default 5 s optional 2 images reference_to_video16:9, 9:16, 1:1, 4:3, 3:4, auto (default auto) 480p, 720p, 1080p (default 1080p) 2–30 s, default 5 s optional up to 10 images, up to 5 videos, up to 5 audio clips, up to 1 document
Faster Wan 3.0 generations, up to 30 s with native audio.
Model id mdl_a1f9tn00qy7qOutput video Capabilities text_to_video, image_to_video, frames_to_video, reference_to_videoDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_video16:9, 9:16, 1:1, 4:3, 3:4 (default 16:9) 480p, 720p, 1080p (default 1080p) 2–30 s, default 5 s optional — image_to_video— 480p, 720p, 1080p (default 1080p) 2–30 s, default 5 s optional 1 image frames_to_video— 480p, 720p, 1080p (default 1080p) 2–30 s, default 5 s optional 2 images reference_to_video16:9, 9:16, 1:1, 4:3, 3:4, auto (default auto) 480p, 720p, 1080p (default 1080p) 2–30 s, default 5 s optional up to 10 images, up to 5 videos, up to 5 audio clips, up to 1 document
Cinematic motion and expressive characters with native audio, up to 15 s at 1080p.
Model id mdl_4x2sa4w82gy8Output video Capabilities text_to_video, image_to_video, reference_to_videoDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_video16:9, 9:16, 1:1, 4:3, 3:4 (default 16:9) 720p, 1080p (default 1080p) 3–15 s, default 5 s — — image_to_video— 720p, 1080p (default 1080p) 3–15 s, default 5 s — 1 image reference_to_video16:9, 9:16, 1:1, 4:3, 3:4 (default 16:9) 720p, 1080p (default 1080p) 3–15 s, default 5 s always 1–9 images
Expressive multilingual narration and dialogue, with audio tags for delivery.
Model id mdl_pzydnm90f968Output audio Capabilities text_to_speech, dialogueDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_speech— — — — — dialogue— — — — —
Fast, low-cost speech and dialogue in the Gemini 3.8 Flash TTS voices.
Model id mdl_mvwzsh3wyk33Output audio Capabilities text_to_speech, dialogueDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_speech— — — — — dialogue— — — — —
Voiceovers, voice cloning, dialogue, songs and sound effects.
Model id mdl_ra3hy3a397ybOutput audio Capabilities text_to_speech, dialogue, text_to_music, text_to_sound_effectDefault for `dialogue` Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_speech— — — — up to 1 image, up to 3 audio clips dialogue— — — — up to 1 image, up to 3 audio clips text_to_music— — — — up to 1 image, up to 3 audio clips text_to_sound_effect— — — — up to 1 image, up to 3 audio clips
Songs, vocals and instrumentals up to 5 min.
Model id mdl_f5y1v7de83bdOutput audio Capabilities text_to_musicDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_music— — 1–300 s, default 60 s — —
Songs, vocals and instrumentals, 30 s to 3 min.
Model id mdl_nv3cp228aq9tOutput audio Capabilities text_to_musicDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_music— — 30–180 s, default 30 s — —
Full songs with vocals and instrumentals, 30 s to 3 min.
Model id mdl_15xpqgmzpsd0Output audio Capabilities text_to_musicDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_music— — 30–180 s, default 120 s — —
30 s loops, jingles and background stingers.
Model id mdl_nc2y4tvxhde9Output audio Capabilities text_to_musicDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_music— — 30–30 s, default 30 s — —
Expressive multilingual speech with 5 built-in voices and inline speech tags.
Model id mdl_g9p2apngr4h1Output audio Capabilities text_to_speechDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_speech— — — — —
Faster ElevenLabs speech and dialogue with the same voices.
Model id mdl_1pavem2p2qh5Output audio Capabilities text_to_speech, dialogueDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_speech— — — — — dialogue— — — — —
Lifelike expressive narration with 130+ voices and strong multilingual support.
Model id mdl_catdq74qcq34Output audio Capabilities text_to_speechDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_speech— — — — —
Fast, low-cost speech with the Inworld TTS 2 voice catalog.
Model id mdl_r283w0rht2rsOutput audio Capabilities text_to_speechDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_speech— — — — —
Acted performances and dialogue directed in plain language, with inline sounds and pauses.
Model id mdl_wapq8x5020zvOutput audio Capabilities text_to_speech, dialogueDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_speech— — — — — dialogue— — — — —
Anime-cinematic motion with native audio, up to 16 s at 1080p.
Model id mdl_82g43qtcqmbrOutput video Capabilities text_to_video, frames_to_videoDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_video16:9, 9:16, 4:3, 3:4, 1:1 (default 16:9) 360p, 540p, 720p, 1080p (default 1080p) 1–16 s, default 5 s optional — frames_to_video— 360p, 540p, 720p, 1080p (default 1080p) 1–16 s, default 5 s optional 2 images
Faster anime-cinematic clips, up to 16 s at 1080p.
Model id mdl_ns11vydjd68hOutput video Capabilities text_to_video, frames_to_videoDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_video16:9, 9:16, 4:3, 3:4, 1:1 (default 16:9) 360p, 540p, 720p, 1080p (default 1080p) 1–16 s, default 5 s optional — frames_to_video— 360p, 540p, 720p, 1080p (default 1080p) 1–16 s, default 5 s optional 2 images
Up to 12 consistent subjects with native dialogue and sound, up to 4K.
Model id mdl_5ag2xn68yre6Output video Capabilities image_to_video, reference_to_videoDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs image_to_video— 540p, 720p, 1080p, 1440p, 2160p (default 720p) 3–16 s, default 5 s always 1 image reference_to_video16:9, 9:16, 4:3, 3:4, 1:1 (default 16:9) 540p, 720p, 1080p, 1440p, 2160p (default 720p) 3–16 s, default 5 s optional 1–12 images, up to 3 audio clips
Bold, stylized images, video and video remixes with native audio.
Model id mdl_zsdtcwgcfh59Output image, video Capabilities text_to_image, image_to_image, text_to_video, image_to_video, reference_to_video, video_to_videoDefault for `text_to_image`, `image_to_image` Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_image16:9, 4:3, 1:1, 3:4, 9:16 (default 16:9) — — — — image_to_image— — — — 1–3 images text_to_video16:9, 4:3, 1:1, 3:4, 9:16 (default 16:9) 480p, 720p (default 480p) 1–15 s, default 5 s always — image_to_video16:9, 4:3, 1:1, 3:4, 9:16, auto (default auto) 480p, 720p (default 480p) 1–15 s, default 5 s always 1 image reference_to_video16:9, 4:3, 1:1, 3:4, 9:16 (default 16:9) 480p, 720p (default 480p) 1–10 s, default 5 s always 1–7 images video_to_video— auto, 480p, 720p (default auto) — always 1 video
Bold image remixes from up to 3 references, up to 1440p.
Model id mdl_s46fg2pvyyq1Output image Capabilities image_to_imageDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs image_to_image— 1080p, 1440p (default 1080p) — — 1–3 images
Bold, stylized motion clips with native audio, up to 15 s at 1080p.
Model id mdl_taxsk9yr1px5Output video Capabilities text_to_video, image_to_video, reference_to_videoDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_video16:9, 4:3, 3:2, 1:1, 2:3, 3:4, 9:16 (default 16:9) 480p, 720p, 1080p (default 720p) 1–15 s, default 5 s always — image_to_video— 480p, 720p, 1080p (default 720p) 1–15 s, default 5 s always 1 image reference_to_video16:9, 4:3, 3:2, 1:1, 2:3, 3:4, 9:16 (default 16:9) 480p, 720p (default 480p) 1–15 s, default 5 s always 1–7 images
Bold, distinctive images and remixes up to 1440p.
Model id mdl_f7yst7vypndcOutput image Capabilities text_to_image, image_to_imageDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_image16:9, 4:3, 3:2, 1:1, 2:3, 3:4, 9:16 (default 16:9) 1080p, 1440p (default 1080p) — — — image_to_image— 1080p, 1440p (default 1080p) — — 1–3 images
Changes the camera angle and perspective of an image.
Model id mdl_f69tthqkwwncOutput image Capabilities image_to_imageDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs image_to_image1:1, 4:3, 3:4, 9:16, 16:9 (default 16:9) — — — 1 image
Typography, identity-preserving edits and transparent assets.
Model id mdl_m6ck5frt6angOutput image Capabilities text_to_image, image_to_imageDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_image21:9, 16:9, 4:3, 5:4, 1:1, 4:5, 3:4, 9:16 (default 16:9) — — — — image_to_image21:9, 16:9, 4:3, 5:4, 1:1, 4:5, 3:4, 9:16, auto (default auto) — — — 1–10 images
Logos, branding and design assets up to 4K.
Model id mdl_mg9364gt8tf9Output image Capabilities text_to_imageDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_image16:9, 9:16, 4:3, 3:4, 1:1, 4:5, 5:4 (default 16:9) 1080p, 1440p, 2160p (default 1080p) — — —
Higher-fidelity logos, branding and design assets up to 4K.
Model id mdl_8bwn03gryceeOutput image Capabilities text_to_imageDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_image16:9, 9:16, 4:3, 3:4, 1:1, 4:5, 5:4 (default 16:9) 1080p, 1440p, 2160p (default 1080p) — — —
Fast, low-cost logos and design assets.
Model id mdl_h4rr1255y3gwOutput image Capabilities text_to_imageDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_image16:9, 9:16, 4:3, 3:4, 1:1, 4:5, 5:4 (default 16:9) — — — —
Fast, affordable video with native audio, timed to music or dialogue.
Model id mdl_2wk9jsm954qeOutput video Capabilities text_to_video, image_to_video, reference_to_video, lip_syncDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_video16:9, 9:16 (default 16:9) 720p, 1080p (default 1080p) 6, 8, 10 s, default 6 s optional — image_to_video16:9, 9:16, auto (default auto) 720p, 1080p (default 1080p) 6, 8, 10 s, default 6 s optional 1 image reference_to_videoauto, 16:9, 9:16 (default auto) — — always up to 1 image, 1 audio clip lip_syncauto, 16:9, 9:16 (default auto) — — always 1 image, 1 audio clip
Fast video with native audio, up to 20 s and 4K.
Model id mdl_gtv6d0bf56ezOutput video Capabilities text_to_video, image_to_videoDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_video16:9, 9:16 (default 16:9) 720p, 1080p, 1440p, 2160p (default 1080p) 6, 8, 10, 12, 14, 16, 18, 20 s, default 6 s optional — image_to_video16:9, 9:16, auto (default auto) 720p, 1080p, 1440p, 2160p (default 1080p) 6, 8, 10, 12, 14, 16, 18, 20 s, default 6 s optional 1 image
Precise images up to 4K and realistic 5–20 s video, with in-place video edits that keep the source length.
Model id mdl_z771nx182pfvOutput image, video Capabilities text_to_image, image_to_image, text_to_video, image_to_video, frames_to_video, video_to_videoDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_image21:9, 2:1, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16, 1:2 (default 16:9) 1080p, 1440p, 2160p (default 1080p) — — — image_to_imageauto, 21:9, 2:1, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16, 1:2 (default auto) 1080p, 1440p, 2160p (default 1080p) — — 1–10 images text_to_video21:9, 2:1, 16:9, 4:3, 1:1, 3:4, 9:16 (default 16:9) 720p, 1080p (default 720p) 5–20 s, default 5 s optional — image_to_video— 720p, 1080p (default 720p) 5–20 s, default 5 s optional 1 image frames_to_video— 720p, 1080p (default 720p) 1–20 s, default 5 s optional 2–10 images video_to_video— 720p — always 1 video
Frontier realism at high speed, 5–20 s clips with native audio.
Model id mdl_dg0bkv8gqczzOutput video Capabilities text_to_video, image_to_video, frames_to_videoDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs text_to_video21:9, 2:1, 16:9, 4:3, 1:1, 3:4, 9:16 (default 16:9) 720p, 1080p (default 720p) 5–20 s, default 5 s optional — image_to_video— 720p, 1080p (default 720p) 5–20 s, default 5 s optional 1 image frames_to_video— 720p, 1080p (default 720p) 1–20 s, default 5 s optional 2–10 images
Fast, accurate lip-sync of a video to new audio.
Model id mdl_v3m6k7ya8gxnOutput video Capabilities lip_syncDefault for `lip_sync` Status available
Capability Aspect ratios Resolutions Duration Audio Inputs lip_sync— — — always 1 video, 1 audio clip
Photoreal talking video from an image and audio.
Model id mdl_18ej026xxdaxOutput video Capabilities lip_syncDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs lip_sync— 480p, 720p (default 480p) — always 1 image, 1 audio clip
Re-voices one speaker in an existing video, up to 60 s.
Model id mdl_a2fp90bgh080Output video Capabilities lip_syncDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs lip_sync— — — always 1 video, 1 audio clip
Talking video from a portrait and audio, up to 5 min.
Model id mdl_93nteqvn3dhvOutput video Capabilities lip_syncDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs lip_sync— — — always 1 image, 1 audio clip
Synced sound effects and foley for a video, or sound effects from text, up to 10 min.
Model id mdl_4b2m5g20rr5qOutput video, audio Capabilities video_to_video, text_to_sound_effectDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs video_to_video— — — always 1 video text_to_sound_effect— — 0.1–600 s, default 5 s — —
Adds synced sound effects to a video up to 10 min long, keeping its dialogue.
Model id mdl_gvmfbpd64vv9Output video Capabilities video_to_videoDefault for — Status available
Capability Aspect ratios Resolutions Duration Audio Inputs video_to_video— — — always 1 video
A retired id with a replacement is still accepted: it runs the model shown, and responses name that model's id. One with no replacement is refused.
Model id Name Runs instead — — —
If you have any trouble or have any questions, feel free to reach out. We're happy to help. Write to us at support@morphic.com .