Generate
Models
Pick the model yourself: prices differ by more than a hundred times between models. Image models run on the Image Router; video, lip-sync and captions models on the Video Router.
List models
GEThttps://api.dev.sume.com/v1/image-router/models
GEThttps://api.dev.sume.com/v1/video-router/models
Both need a key and return the models your workspace can run right now, with their capabilities and prices. Add /{model_id} for one model.
curl https://api.dev.sume.com/v1/image-router/models/gpt-image-2 \
-H "Authorization: Bearer $SUME_API_KEY"A model row
capabilities says which fields and values the model takes; pricing gives its price and its basis (per_image, per_second or per_second_by_resolution); constraints lists the rules in plain words.
{
"data": {
"id": "gpt-image-2",
"name": "ChatGPT Image 2",
"modality": "image",
"capabilities": {
"text_to_image": true,
"image_edit": true,
"aspect_ratios": [
"auto",
"1:1",
"16:9",
"9:16",
"4:3",
"3:4"
],
"qualities": [
"low",
"medium",
"high"
],
"max_images": 4,
"output_formats": [
"png",
"jpeg",
"webp"
]
},
"pricing": {
"basis": "per_image"
},
"constraints": [
"…"
]
}
}Models on Sume
Pass the id as model to the endpoint shown. Each name links to the model's page with examples. The list endpoints above are the live source; a model can be added before this table is.
Image
| Model id | Model | What it does | Endpoint |
|---|---|---|---|
gpt-image-2.5 | ChatGPT Image 2.5 | Generates and edits images · up to 4 per request | /v1/image-router/generate |
gpt-image-2.5-sunburst | ChatGPT Image 2.5 Sunburst | Generates and edits images · up to 4 per request | /v1/image-router/generate |
gpt-image-2 | ChatGPT Image 2 | Generates and edits images · up to 4 per request | /v1/image-router/generate |
nano-banana-2.1 | Nano Banana 2.1 | Generates and edits images · up to 4K · up to 4 per request | /v1/image-router/generate |
nano-banana-pro | Nano Banana Pro | Generates and edits images · up to 4K · up to 4 per request | /v1/image-router/generate |
seedream-5-lite | Seedream 5.0 Lite | Generates and edits images · up to 4 per request | /v1/image-router/generate |
seedream-4-5-edit | Seedream 4.5 | Generates and edits images · up to 4 per request | /v1/image-router/generate |
grok-image | Grok Imagine | Generates and edits images | /v1/image-router/generate |
seedream-v4 | Seedream 4.0 | Generates and edits images · up to 4 per request | /v1/image-router/generate |
qwen-image | Qwen Image | Generates and edits images · up to 4 per request | /v1/image-router/generate |
imagen-4-fast | Imagen 4 Fast | Generates images from text · up to 4 per request | /v1/image-router/generate |
imagen-4-ultra | Imagen 4 Ultra | Generates images from text · up to 2K · up to 4 per request | /v1/image-router/generate |
flux-2-pro | Flux 2 Pro | Generates and edits images · up to 4 per request | /v1/image-router/generate |
flux-2-flex | Flux 2 Flex | Generates and edits images · up to 4 per request | /v1/image-router/generate |
ideogram-v3 | Ideogram V3 | Generates and edits images · up to 4 per request | /v1/image-router/generate |
recraft-v4 | Recraft V4 | Generates images from text · up to 4 per request | /v1/image-router/generate |
qwen-image-max | Qwen Image Max | Generates images from text · up to 4 per request | /v1/image-router/generate |
qwen-image-layered | Qwen Image Layered | Edits images · up to 4 per request | /v1/image-router/generate |
ideogram-v4.5 | Ideogram 4.5 | Generates and edits images · up to 2K · up to 4 per request | /v1/image-router/generate |
Video
| Model id | Model | What it does | Endpoint |
|---|---|---|---|
seedance-2.5 | Seedance 2.5 | Generates video from text, an image, references · 480p to 1080p · 4–30 s · native audio | /v1/video-router/generate |
seedance-2-mini | Seedance 2.0 Mini | Generates video from text, an image, references · 480p to 720p · 4–15 s · native audio | /v1/video-router/generate |
seedance-2 | Seedance 2.0 | Generates video from text, an image, references · 480p to 1080p · 4–15 s · native audio | /v1/video-router/generate |
seedance-2-fast | Seedance 2.0 Fast | Generates video from text, an image, references · 480p to 720p · 4–15 s · native audio | /v1/video-router/generate |
kling-3 | Kling Video v3 Pro | Generates video from text, an image · 1080p · 4–15 s · native audio | /v1/video-router/generate |
wan-3.0 | Wan 3.0 | Generates video from text, an image, references · 480p to 1080p · 2–30 s · native audio | /v1/video-router/generate |
grok-imagine-video-1.5 | Grok Imagine Video 1.5 | Generates video from an image · 480p to 720p · 4–15 s | /v1/video-router/generate |
minimax-h3 | MiniMax H3 | Generates video from text, an image, references · 480p to 4K · 5–15 s · native audio | /v1/video-router/generate |
minimax-h3-max | MiniMax H3 Max | Generates video from text, an image, references · 480p to 1080p · 5–15 s · native audio | /v1/video-router/generate |
gemini-omni-flash-1.1 | Gemini Omni Flash 1.1 | Generates video from text, an image, references, a source video · 360p to 4K · 3–10 s · native audio | /v1/video-router/generate |
h3-max-recast | H3 Max Recast | Generates video from references, a source video · 768p to 1080p · 5–30 s · native audio | /v1/video-router/generate |
vidu-q4 | Vidu Q4 | Generates video from an image · 720p to 1080p · 3–16 s · native audio | /v1/video-router/generate |
vidu-q4-reference | Vidu Q4 Reference | Generates video from references · 720p to 1080p · 3–16 s · native audio | /v1/video-router/generate |
veo-3.1 | Veo 3.1 | Generates video from text · 720p · 4–8 s · native audio | /v1/video-router/generate |
veo-3.1-fast | Veo 3.1 Fast | Generates video from text · 720p · 4–8 s · native audio | /v1/video-router/generate |
veo-3.1-lite | Veo 3.1 Lite | Generates video from text · 720p · 4–8 s · native audio | /v1/video-router/generate |
wand-vega-1.0-lite | WAND-Vega 1.0 Lite | Generates video from text · 768p to 4K · 4–15 s · native audio | /v1/video-router/generate |
wand-vega-1.0-pro | WAND-Vega 1.0 Pro | Generates video from text · 720p to 4K · 4–15 s · native audio | /v1/video-router/generate |
wand-vega-1.5-pro | WAND-Vega 1.5 Pro | Generates video from text · 720p to 4K · 4–15 s · native audio | /v1/video-router/generate |
mingmou-1 | Mingmou 1 | Generates video from text · 720p to 4K · 5–10 s | /v1/video-router/generate |
hunyuan-1.5 | Hunyuan 1.5 | Generates video from text · 720p to 4K · 5 s | /v1/video-router/generate |
hailuo-h3-regen | Hailuo H3 Regen | Generates video from a source video · 2K · 5–16 s | /v1/video-router/generate |
heygen-video-1 | HeyGen Video 1 | Generates video from text, an image, references · 480p to 2K · 5–15 s · native audio | /v1/video-router/generate |
Lip-sync
| Model id | Model | What it does | Endpoint |
|---|---|---|---|
veed-fabric-1.0 | VEED Fabric 1.0 | Makes a face say an audio track · 480p to 720p | /v1/video-router/generate |
veed-fabric-1.0-fast | VEED Fabric 1.0 Fast | Makes a face say an audio track · 480p to 720p | /v1/video-router/generate |
minimax-h3-max-lip-sync | MiniMax H3 Max Lip Sync | Makes a face say an audio track · 480p to 1080p | /v1/video-router/generate |
kling-avatar-2.0-pro | Kling Avatar 2.0 Pro | Makes a face say an audio track | /v1/video-router/generate |
kling-avatar-2.0 | Kling Avatar 2.0 | Makes a face say an audio track | /v1/video-router/generate |
infinitalk | InfiniteTalk | Makes a face say an audio track · 480p to 720p | /v1/video-router/generate |
omnihuman-1.5 | OmniHuman 1.5 | Makes a face say an audio track · 720p to 1080p | /v1/video-router/generate |
creatify-aurora | Creatify Aurora | Makes a face say an audio track · 480p to 720p | /v1/video-router/generate |
wan-2.2-speech-to-video | Wan 2.2 Speech to Video | Makes a face say an audio track · 480p to 720p | /v1/video-router/generate |
sync-lipsync-3 | Sync Lipsync 3 | Makes a face say an audio track | /v1/video-router/generate |
sync-lipsync-2-pro | Sync Lipsync 2 Pro | Makes a face say an audio track | /v1/video-router/generate |
sync-lipsync-2 | Sync Lipsync 2 | Makes a face say an audio track | /v1/video-router/generate |
kling-lipsync | Kling Lipsync | Makes a face say an audio track | /v1/video-router/generate |
latentsync | LatentSync | Makes a face say an audio track | /v1/video-router/generate |
veed-lipsync | VEED Lipsync | Makes a face say an audio track | /v1/video-router/generate |
infinitalk-video | InfiniteTalk Video | Makes a face say an audio track · 480p to 720p | /v1/video-router/generate |
pixverse-lipsync | PixVerse Lipsync | Makes a face say an audio track | /v1/video-router/generate |
Captions
| Model id | Model | What it does | Endpoint |
|---|---|---|---|
veed-subtitles | VEED Subtitles | Burns styled captions into a video · 1080p to 4K | /v1/video-router/generate |