Guides
Sume guides: the API, Formats, agents, models, media tools and pricing, each answer dated and sourced.
RMBG, image upscale and video upscale request fields side by side
The three Sume media tools take different bodies: image_url, upscale_factor 1-4, video_url, duration_seconds 1-30, enhancement_tier. One table, prices included.
Sume run webhook: 10 s timeout, so queue before you call a slow model
Sume gives your webhook 10 seconds per attempt, up to 10 attempts. Verify the signature, store the event, return 2xx, then call any slow model. Python verifier.
Does the Sume spend cap cover the agent's own model tokens?
No: Sume's cap excludes the agent's LLM turn; debited_usd_micros includes it. At list rates that turn is about $0.004 on Haiku 5.5 and $0.40 on Astra.
Sume TTS is 2.16x MAI-Voice-2.1 per character: where it still fits
At $47.50 per million characters Sume TTS costs 2.16x MAI-Voice-2.1 and 3.17x Flash, with no break-even at any length. What the extra buys, read 2026-10-08.
Upscale a 1280x720 thumbnail to 3840x2160: factor 3 or generate at 4K?
Factor 3 turns 1280x720 into 3840x2160 for $0.20; GPT Image 2.5 at 4K is $0.2225. For 36 thumbnails: $7.20 to upscale, $8.01 to regenerate.
MAI-Voice-2.1 audio in a Sume Timeline: 9 clips, 261 s
Sume does not list MAI-Voice. To use its audio in a Timeline, import the files, concat at $0.01, render 261 s as 5 minutes ($0.50). Read 2026-10-08.
Which 10 of 15 reference images to keep for Sume Omni reference video
Vidu Q4 Preview takes 15 reference images; Sume's Omni takes 10 plus 3 short clips. A role-by-role way to cut a 15-image brief down to 10 slots.
Write the Lyria brief from your shot list: a Python timestamp builder
Lyria responds to [m:ss-m:ss] section markers. A short Python script turns a 6-shot, 59-second shot list into a brief under the 5000-character limit.
YouTube AI use label on a face-swap clip: does it hurt monetization?
YouTube says its altered-content label has no monetization impact, while undisclosed realistic fakes can be penalised. What that means for a Sume face swap.
120 ms first partial vs a 600-second file job: pick the STT shape
MAI-Transcribe-2-Streaming lists ~120 ms to first partial; Sume STT is a file job capped at 600 s. Workloads, shapes and prices side by side, read 2026-10-08.
A 19-second single shot: which Sume video models take it in one job
Wan 3.0 and Seedance 2.5 take 19 s in one job ($4.75 and $27.01 at 1080p). Seedance 2.0, H3 and Omni top out at 15 s, 15 s and 10 s, so they need two jobs.
8:1 strips and 21:9 banners: which image models take them
Nano Banana 2.1 lists 8:1, 4:1, 1:4 and 1:8 on Sume; Pro stops at 21:9 and 9:16. Prices per image for each ratio choice, read 2026-10-08.
Add captions to a Vidu Q4 clip with Sume: what the caption API needs
Vidu Q4 Preview can voice characters. Sume's video captions API burns captions onto any public HTTPS clip; it fails on silent clips unless you send cues.
Cheapest possible job per Sume video model: shortest clip, lowest tier
Smallest valid job: Omni $0.1125 (3 s, 360p), Wan 3.0 $0.125 (2 s), H3 and H3 Max $0.3125 (5 s), Seedance 2.0 $0.7031, Seedance 2.5 $1.0747.
Count TTS characters first: Sume counts spaces and punctuation
Sume TTS bills every character including spaces and punctuation, up to 20,000 per request. A runnable Python counter prices a script on Sume and MAI.
Eight market beds in parallel: asyncio, one idempotency key each
Eight Music Router jobs with one Idempotency-Key per market and a metadata tag cost $1.00 and survive a retry without a second charge. A runnable Python script.
Gemini 3.8 Flash TTS vs Sume TTS: break-even 284 chars a minute
Gemini bills TTS by audio seconds, Sume by characters. Sume is cheaper only below 284.2 characters per audio minute on Flash (568.4 from 2027). Read 2026-10-08.
Kling motion control: a 2.4-second driver is billed as 3 seconds
Sume prices Kling 3.0 Motion Control per whole output second, rounded up. A 2.4-second driving video bills as 3 s, which is $0.4725 at $0.1575 per second.
MAI-Transcribe-2-Streaming lists no word timestamps; use batch
Microsoft's page shows word timestamps, diarization and keyword biasing for batch MAI-Transcribe-2 but not Streaming. Sume STT returns words. Read 2026-10-08.
Mistral Large 4 preview as your orchestrator, Sume as the renderer
Sume does not list Mistral Large 4. Let it plan in your own code and hand each video task to a Sume Agent Completion; Python sample with the required cap.
Most expensive single job per Sume video model: longest, top tier
The largest single job reserves $42.6465 on Seedance 2.5 (30 s, 1080p), $12.7575 on Seedance 2.0, $7.50 on Wan 3.0, $3.75 on Omni at 4K and $3.00 on H3 Max.
One 15-second ad in 3 ratios: render once, crop twice on Sume
A 15-second 1080p master on Wan 3.0 costs $3.75, and two $0.02 crops give 1:1 and 9:16 cutdowns for $3.79. Vidu Q4 at 540P is $0.675 per ratio.
One 640x640 render: TikTok 1:1 ad size and a square Short
A 640x640 square clears TikTok's 1:1 non-Spark minimum and fits YouTube's square-or-vertical Shorts rule. A 45-second render is $0.10 on Sume Timeline.
H3 Max Recast prompt: 2,000 characters, and the fields Sume rejects
The optional Recast prompt is capped at 2,000 characters, and aspect_ratio, generate_audio and frame fields are refused. A checker to run before a paid submit.
Retry cost of a mixed project: what a failed shot, 402 and replay bill
Six failure cases for an image, voice, music, video and render project, with the cost of the retry for each and the one mistake that pays for everything twice.
RMBG or upscale fails: image_not_fetchable and the HTTPS fix list
Sume cutout and upscale jobs need a public HTTPS image_url of at most 2,048 characters. Fix list for image_not_fetchable, 400 on model, 402 and 429 errors.
Same image as first and last frame: a 6-second loop on three models
A 6 s loop with one image as both first and last frame costs $2.27 on Seedance 2.0 at 720p, $0.60 on H3 Max at 768p and $0.75 on Omni at 720p.
Catalog says nano-banana-2, docs say 2.1: which id to send on Sume
On 2026-10-08 the Sume catalog Image Router entry still lists nano-banana-2, while the Image API docs say it runs as 2.1. Send google/nano-banana-2.1.
Sume STT: omit duration_seconds and you reserve one minute, not 570 s
The catalog says omitting duration_seconds reserves 1 minute; the maximum is 10 minutes ($0.10). A 570-second file lists at $0.095. Hold table, read 2026-10-08.
Sume TTS one-cent floor ends at 211 characters (vs MAI-Voice)
Sume TTS bills at least 1 cent a job; list price passes it at 211 characters. MAI-Voice-2.1 and Flash pass 1 cent at 455 and 667 characters. Read 2026-10-08.
Swap the backdrop on 90 product photos: mask edit or cutout plus plate
Three ways to change the background of 90 product photos on Sume: mask edit at medium $5.01, cutout with a plate per photo $4.25, or one shared plate $2.05.
Ten drafts and three finals a week: 30-second projects, wallet need
Weekly plan for 30-second mixed projects: ten drafts (480p, 0.5K stills) and three finals (1080p, 2K stills). Cost per tier, the week's total, the top-up.
TikTok 540x960 minimum: a 480p clip needs upscale factor 1.2, not 1.1
A 480-px-wide vertical clip fails TikTok's 540x960 floor. Sume video upscale starts at 1.1, which gives only 528 px. Use 1.2 or more; 25 clips cost $2.70.
TikTok's 540x960 minimum: Vidu Q4 540P or a Sume 720p clip?
TikTok's non-Spark ad minimum is 540x960 for 9:16. Sume's Omni at 360p falls below it; 720p clears it at $0.125/s. Vidu's release gives no pixel sizes.
Timeline's 0.5 s coverage rule on a 59-second spine: 58.5 is enough
Timeline accepts video slots that end at most 0.5 s before the end of the spine, so on a 59-second Short the slots must reach 58.5 seconds. Render is $0.10.
Inspect stills at max_edge 960: 540x960 views of a 9:16 ad
Video inspect max_edge 960 returns 9:16 stills at 540x960, TikTok's non-Spark minimum, so you review the ad at the smallest size it may run. 24 stills per call.
Video trim is async by default: mode sync waits 30 s, then poll
Video trim returns a job at once by default. Send mode sync to wait up to 30 s for a 200, else get 202 and poll status, then result. Never resubmit.
Vidu Q4 reference voice: audio references or TTS on Sume?
Vidu Q4 Preview adds reference voice. Sume does not list Vidu; some video rows take audio references, and TTS costs $0.0475 per 1,000 characters.
Voiceover spine: wav or mp3? 1,800 s is 158.76 MB or 28.8 MB
Timeline audio returns wav (sample-exact) or mp3 (smaller, padding at each edge). 1,800 s is 158.76 MB as 44.1 kHz mono wav vs 28.8 MB at 128 kbps.
Free checks before a TikTok ad: Timeline plan, filter check, not trim
Timeline plan and Video filter check are unbilled on Sume. Trim has no check. A 10-minute ad with one trim, one filter and one render totals $1.04.
Which Sume video models accept a music track as an audio reference?
Seedance 2.x, Wan 3.0, MiniMax H3 and H3 Max take audio references; Gemini Omni Flash 1.1 does not. Prices for 8 s plus a $0.125 bed.
A/B testing three image models on 50 prompts: what it costs on Sume
Fifty prompts on ChatGPT Image 2.5 medium, Seedream 5.0 Lite and Nano Banana 2.1 cost $0.825, $2.1875 and $5.00 on Sume. The full test and a script to run it.
Ad creative testing workflow with an API: five calls to a winner
A repeatable ad creative test on Sume: research hooks, generate variants, cut, caption and count the spend per variant. Five documented calls with prices.
Use your ad variant id as the Idempotency-Key on Sume
Name each ad variant once and send that name as the Idempotency-Key. Retries do not double-bill, and the receipt echoes it back so results map to your ad names.
Add a hand holding the product to a packshot with GPT Image 2.5
Turn a packshot into a hand-held photo: send the product photo and a hand or pose reference to openai/gpt-image-2.5. $0.0835 at high on Sume for one edit.
How do I add a voiceover and music to a timelapse video?
Narrate a 45-second timelapse with one TTS job, one music track and one Timeline render: 3 cents, $0.125 and $0.10, about 33 cents on Sume.
Add sunglasses or a hat to a person in an existing video (Omni edit)
Use Gemini Omni Flash 1.1 video_url edit on Sume to add an accessory to a person already in a clip. Prompt wording, a frame check list, and 4-second prices.
AI play-by-play voiceover for a sports highlight reel: how to time it
Write one line per play, ask TTS for sentence timings, and place each clip on its line: a 60-second reel costs about 14 cents on Sume. Not live commentary.