Models
The models behind Sume's video, image, speech, and music endpoints: ids, clip lengths, resolutions, aspect ratios, audio, references, and migration.
Start with What AI models does Sume support? Every model id, by API surface
Wan 3.0 2-second clips: the shortest video length and what it costs
Wan 3.0's floor is 2 seconds, shorter than the 4-second minimum on Seedance 2.x models. Send duration 2 to wan-3.0; at 720p it costs $0.25 before the agent fee.
Wan 3.0 30-second video: one clip, no stitching
Wan 3.0 makes a single clip of up to 30 seconds with audio. Set duration to 30 on wan-3.0 in POST /v1/videos. Here is the request, the cost, and the limits.
Wan 3.0 document to video: what the model reads and what Sume passes
Alibaba's Wan 3.0 can read an uploaded document to make a video. On Sume's video API today wan-3.0 takes prompts, frames and media references, not a file input.
Wan 3.0 first and last frame: animate between two images
Wan 3.0 can make a clip that starts on one image and ends on another. On Sume, send frame_images with first_frame and last_frame to wan-3.0; last needs first.
Wan 3.0 omni reference video: images, clips and audio in one prompt
Omni reference means one request carries mixed references. Wan 3.0 takes up to 10 images, 5 videos and 5 audio tracks; on Sume, send them as input_references.
Wan 3.0 reference limits: how many images, videos and audio clips
Wan 3.0 reference-to-video takes up to 10 images, 5 video clips and 5 audio tracks. See the per-type caps, what Sume rejects with unsupported_capability, why.
Wan 3.0 thinking mode: why document and web page input needs it
fal says Wan 3.0 needs thinking mode to read a document or web page; Alibaba says prompt_extend must be true. What each means, and why Sume's wan-3.0 skips it.
Wan 3.0 vertical video: 9:16 for Reels, Shorts and TikTok
Wan 3.0 supports 9:16. Send aspect_ratio 9:16 to wan-3.0 for a vertical clip of 2 to 30 seconds at 480p, 720p or 1080p. Accepted ratios and cost.
Wan 3.0 vs MiniMax H3: clip length, ratios and reference caps
Wan 3.0 runs 2 to 30 s at up to 1080p; MiniMax H3 runs 5 to 15 s at 480p or 768p. Where they differ on Sume: ratios, reference caps and audio inputs.
Wan 3.0 vs Seedance 2.0: which model to call when
Wan 3.0 and Seedance 2.0 are both on Sume's video API. Wan runs 2 to 30 s and bills per second; Seedance 2.0 runs 4 to 15 s with a 21:9 frame. Pick by the job.
Wan 3.0 web page to video: link input and how to do it on Sume
Wan 3.0 can read a public web link to make a video on Alibaba's API. Sume's wan-3.0 has no link field, so fetch the page yourself and send text and images.
Is there one API for Kling, Seedance and Veo with a single bill?
Yes. fal, Replicate, Runway, Higgsfield and Sume bill several video models on one account. Which list Kling, Seedance and Veo, with units and limits.
Kling 3.0 API: text or image to video, limits and price
Kling 3.0 has an API: Kling's own, and multi-model APIs such as Sume's, where it is kling-3: 4–15 second clips from text or frames, audio optional.
Grok Imagine video API: image to video, 4–15 seconds
Grok Imagine Video 1.5 is on Sume's video API as image-to-video only: a first frame and a prompt give a 4–15 second silent clip at 480p or 720p.
Kling 3.0 vs Seedance 2.0: inputs, limits and price
On Sume, Kling 3.0 and Seedance 2.0 both make 4–15 s clips from text or frames. Seedance adds references and six ratios, and bills per token.
Wan 3.0 vs Seedance 2.5: 30-second clips, inputs and price
Wan 3.0 and Seedance 2.5 both make clips of up to 30 s with audio, frames and references. Wan starts at 2 s and bills per second, Seedance per token.
Seedance 2.5 vs MiniMax H3: length, resolution, audio, price
On Sume, Seedance 2.5 makes 4–30 s clips at up to 1080p with optional audio; MiniMax H3 makes 5–15 s at native 480p or 768p, always with audio.
Kling AI vs MiniMax: Kling 3.0 and MiniMax H3 APIs compared
On Sume, Kling 3.0 makes 4–15 s clips with audio you can turn off and no references; MiniMax H3 makes 5–15 s, always with sound, and takes references.
Higgsfield vs Kling AI: studio or model maker?
Kling makes the Kling models and sells its own apps and API. Higgsfield is a multi-model studio that also runs Kling 3.0. Access and billing compared.
Runway API Seedance: calling Seedance 2.5 and 2.0 on Runway
Yes, Runway's API serves Seedance: seedance2_5, seedance2, seedance2_fast and seedance2_mini. Inputs, limits and credits, and other ways to call Seedance.
Kling vs Wan: Kling 3.0 and Wan 3.0 by API compared
Kling 3.0 makes 4–15 s clips with no references; Wan 3.0 makes 2–30 s clips and takes image, video and audio references. Inputs and price compared.
Seedance 2.0 vs Gemini Omni Flash: inputs, audio and price
Seedance 2.0 makes 4–15 s clips with optional audio and audio references; Gemini Omni Flash 1.1 makes 3–10 s clips up to 4K, always with sound.
Lip sync AI API options: photo or video input, limits, price
Lip sync APIs take a face and audio and return a talking clip. Some animate a photo, others redub an existing video. Inputs, limits and price units.
HeyGen text to speech API: endpoint, limits and price
HeyGen's API has a text to speech endpoint, POST /v3/voices/speech: up to 5,000 characters per call, catalog voices, word timestamps, $0.12 a minute.
Seedance 2.0 Fast vs Seedance 2.0 (and Mini): what differs
Seedance 2.0 Fast and Seedance 2.0 take the same inputs and 4–15 s lengths; the price differs: about $0.30 vs $0.38 a 720p second.
Seedance vs Seedream: ByteDance's video and image models
Seedance is ByteDance Seed's video model family; Seedream is its image model family. What each makes, takes, and costs through one API.
Kling vs Grok Imagine: Kling 3.0 and Grok Imagine Video 1.5
Kling 3.0 makes clips from text or an image, with an end frame and sound; Grok Imagine Video 1.5 animates one image, silent, for $0.0125/s.
AI video generator comparison table: price, length, sound
An AI video generator comparison on the same columns: billed rate, clip length, resolutions, sound and inputs for 11 video models, dated.
Seedance vs Sora 2: specs side by side after the shutdown
Sora 2 shut down on September 24, 2026. Its clip lengths, frame sizes, inputs, extensions and edits beside Seedance 2.0 and 2.5, which you can still call.
How to download Sora videos after the shutdown
To download Sora videos, open sora.chatgpt.com/sunset and click Export; OpenAI emails you when it's ready. Export soon: the data is deleted later.
Kling virtual try-on API: what it takes and returns
Kling's virtual try-on API takes one garment image and one person image and returns a try-on image, not a video. Fields, limits, price, and next steps.
Nano Banana MCP server for Claude: how to add one
To use Nano Banana in Claude, connect an MCP server that runs it. Which servers list it, how to add Sume's, and what a call looks like and costs.
Kling MCP: use Kling 3.0 from Claude Code or Cursor
Kling's own agent tool is a Skill. To call Kling 3.0 over MCP, connect a remote server that carries it, such as Sume's, which runs kling-3.
Seedance MCP: make Seedance 2.5 clips from Claude Code
To use Seedance over MCP, connect a remote server that runs it. On Sume's, generate_video takes four Seedance ids, with 30-second clips on 2.5.
Sora MCP server: why it stopped working and what to use
A Sora MCP server can't make video now: OpenAI shut the Sora API down on September 24, 2026. Point your MCP client at other video models instead.
FLUX MCP server: generate FLUX images from Claude
To use FLUX in Claude or Cursor, connect an MCP server that runs it. Which servers name FLUX, and how Sume's generate_image runs FLUX.2 Pro.
GPT Image MCP server: use GPT Image 2.5 in Claude or Cursor
To use GPT Image from Claude or Cursor, connect an MCP server that runs it. On Sume's, generate_image takes GPT Image 2.5 with masks and references.
Lyria MCP: generate music with Lyria 3.5 from Claude
Sume's hosted MCP server has a music_create tool that runs on Google Lyria 3.5 today: a prompt in, a job id back, an audio file on media.sume.com.
Dreamina vs Seedance: the app and the model it runs
Dreamina vs Seedance: Seedance is ByteDance Seed's video model; Dreamina is a creative app that runs it. When to use the app and when an API.
Runway ML alternatives for AI video: apps and APIs
Runway ML alternatives for AI video: fal, Higgsfield, Kling, Replicate and Sume compared on app vs API, models and billing, read 2026-09-28.
Multi-shot video generation: what it is and how to do it
Multi-shot video generation returns one clip with several cuts. Which APIs offer it (Kling 3.0, Runway) and how to build it shot by shot on Sume.
How does AI video generation work? Inputs, jobs, and limits
AI video generation turns a prompt, and optionally an image, into every frame of a short clip in one async job. What goes in, and why clips stay short.
AI video prompt JSON: what the keys actually do
A JSON prompt for AI video is still text: the model reads keys as words. Length, size and audio are request fields, not keys inside the prompt.
Seedance vs Grok Imagine: inputs, length, sound and cost
Grok Imagine Video 1.5 animates one image into a silent clip, billed per second. Seedance 2.x adds text, end frames, references and sound, billed by token.
FLUX.2 API pricing: Pro and Flex cost per image
FLUX.2 API pricing is per image. What FLUX.2 [pro], [flex] and the other variants cost on Black Forest Labs' API, and per image through Sume.
Is Kling AI Chinese? Who owns it and where it's based
Yes. Kling AI is developed by Kuaishou Technology, a Beijing-based company listed in Hong Kong. Who owns it, where its API runs, and other access.
Higgsfield AI vs Runway: apps, API, models and pricing
Higgsfield and Runway both sell a creative app and a video API billed in credits. How their models, API billing and job flow compare, from their pages.
Kling AI alternatives: other models, or Kling elsewhere
Kling AI alternatives: buy Kling 3.0 from fal, Higgsfield, Replicate, Runway or Sume, or switch to another maker's model. Dated table.