Blog
Sume blog: agent-native video generation, Avatar 1.0 orchestration, and production APIs for builders and coding agents.
One Sume image upscale costs the same as 22 seconds of video upscale
Sume image upscale is $0.20 per image and video upscale is $0.009 per second, so one image upscale buys 22.2 seconds of video. A cutout is $0.0225.
Nano Banana 2.1 has no 512px size in Google's guide; Sume lists 512
Google's guide says 512px is unsupported on Nano Banana 2.1, yet Sume's catalog enum for it starts at 512. How to test what a call returns.
Nano Banana 2.1 references: 10 objects, 4 characters vs Pro 6, 5, 3
Google splits Nano Banana 2.1 references into 10 objects and 4 characters, and Pro into 6 objects, 5 characters and 3 style images. How Sume's flat list maps.
Gemini Omni Flash 1.1 on Runway: 3.4 to 30 credits vs Sume
Runway prices Gemini Omni Flash 1.1 at 3.4 credits a second at 360p up to 30 at 4K, at $0.01 a credit. Sume's per-second rates at the same ends.
Runway's two Omni Flash ids: 10-11 credits vs 3.4-30 for 1.1
Runway lists gemini_omni_flash at 10 to 11 credits a second and gemini_omni_flash_1.1 at 3.4 to 30. Which is cheaper depends on resolution.
mask_url on ChatGPT Image 2: not listed, only the 2.5 rows take it
Sume lists mask_url only on ChatGPT Image 2.5 Flare and Sunburst. Sending it to ChatGPT Image 2 is rejected. What to do for a masked edit on the older row.
Photo to watercolor with ChatGPT Image 2: one reference, one prompt
The Sume docs use ChatGPT Image 2 with one reference photo and the prompt "make this scene look like a watercolor painting". The request and what to check.
Crop 9:16 to 2:3 for Pinterest: height 0.84375, then 1000x1500
A 1080x1920 clip becomes 1080x1620 (2:3) with a crop of height 0.84375. Pinterest's page recommends 1000 x 1500 for Showcase and Collections video.
Crop 3:4 to 2:3 for Pinterest: width 0.8889, x 0.0556 centered
A 1080x1440 clip becomes 960x1440 (2:3) by cropping width to 0.8889. Pinterest recommends 2:3 for Showcase and Collections; here are the numbers and request.
Creatify max video length: 2 min on Starter, 10 on Pro, vs Sume
Creatify's page caps Starter videos at 2 minutes and Pro at 10. Sume caps one avatar job at 60 seconds, so 10 minutes is ten jobs: $110.40 to $330.00.
Colossyan NEO vs NEO2 minutes: 20 and 0.5 on Starter, 30 and 10 on Pro
Colossyan lists two monthly minute pools, NEO and NEO2: 20 and 0.5 on Starter, 30 and 10 on Professional. How to compare that with Sume per second.
Crop 9:16 to 4:5 for Facebook feed: height 0.703125, y 0.148
A 1080x1920 clip becomes 1080x1350 (4:5) with a crop of width 1 and height 0.703125. Meta's Facebook feed page lists 4:5 at 1440x1800; here is the request.
Crop a 2:3 Pinterest video to 4:5 for Facebook: height 0.8333
A 1000x1500 Pinterest video becomes 1000x1250 (4:5) with a crop of height 0.8333. Facebook's feed page lists 4:5 at 1440x1800; request inside.
Omni Flash 4K, 10 seconds: a webhook-mode /v1/videos request body
One curl body for gemini-omni-flash-1.1 at 4K, 16:9, 10 seconds with audio and a callback_url, plus what the docs say the submit reserves and what it cannot.
Is Gemini 3.8 Flash TTS in the Live API? No, per Google's model page
Google's model page marks the Live API unsupported for Gemini 3.8 Flash TTS. For live voice use Gemini 3.8 Live; Sume TTS is for async audio jobs.
Where can you use Gemini 3.8 Flash TTS today? API, Notebook, Vids
Google lists Gemini 3.8 TTS in the Gemini API, AI Studio, Gemini Notebook and Google Vids now; the Enterprise API is coming soon. What Sume offers instead.
HappyHorse 1.1 on Cloudflare: 2,500-character prompt limit
Cloudflare's HappyHorse 1.1 text-to-video page caps the prompt at 2,500 characters and clips at 3 to 15 seconds. HappyHorse is not in the Sume catalog.
HappyHorse 1.0 vs 1.1: which one renders 480P on Model Studio?
On Alibaba Model Studio only HappyHorse 1.1 lists 480P. Both versions take 3 to 15 seconds, and 1.0 adds a video-edit id. Neither is in Sume's catalog.
Crop 4:5 to 1:1 for a TikTok ad: height 0.8 and the 640x640 minimum
TikTok's in-feed page lists 1:1 with a 640x640 minimum. A 1080x1350 feed clip crops to 1080x1080 with height 0.8, y 0.1 centered, then clears it easily.
Is 4:5 allowed as a TikTok in-feed ad? The page lists three ratios
TikTok's in-feed spec lists 9:16, 16:9 and 1:1 for non-Spark ads, not 4:5. Crop a 4:5 master to 1:1, or build a 9:16 canvas with Sume Timeline.
Seedance 2.5 on Runway at 20 to 68 credits a second vs Sume tokens
Runway prices seedance2_5 at 20 to 68 credits a second plus input fees, or $0.20 to $0.68. Sume bills Seedance 2.5 per 1,000 video tokens instead.
Seedance 2.5 Draft mode on Runway: 480p proofs, and 480p on Sume
Runway's Oct 2 changelog adds Seedance 2.5 Draft mode for 480p drafts. Sume's seedance-2.5 also renders at 480p through its API; here is how they differ.
MAI-Voice-2.1 has three style lists: emotion, role and expressive
MAI-Voice-2.1 styles come in three vocabularies: 19 emotions, 6 roles and 11 expressive tags. Which voices use the expressive set, and how Sume differs.
MAI-Voice-2.1 whispering and shouting: the 19 voices that list both
Only 19 MAI-Voice-2.1 voices list whispering and shouting by our count. English-UK and Korean voices do not. Sume has no whisper switch.
MAI-Voice-2.1 is public preview, no SLA: plan ad voiceover around it
Microsoft's MAI-Voice-2.1 doc says public preview, no SLA. What that means for a campaign deadline, and how to keep a fallback voice ready.
MAI-Voice-2.1 has 97 voices: en-US has 7, es-ES and en-AU have 1 each
Microsoft's MAI-Voice-2.1 doc lists 97 prebuilt voices over 28 locales. We counted per locale: some have seven choices, others only one.
Facebook feed video ad minimum is 120 px; Sume's smallest is 256
Meta's Facebook feed video spec lists 120 px minimum sides. Sume Timeline renders even sizes from 256 to 2160, so the floor never blocks an upload.
Gemini voice remixing is 'coming soon': what Sume TTS can change today
Google says Gemini voice remixing for timbre, pitch, pace and accent is coming soon. Sume TTS today has speed, volume and an emotion string only.
Download a Sume video with curl: send the key to /content
The docs' curl call for GET /v1/videos/{id}/content sends the API key and follows redirects. A short script saves the MP4 and prints the 409 reason on failure.
Luma Ray3.2 API: the docs page still lists ray-2 and ray-flash-2
Luma says the Ray3.2 API is live. The docs page I read on Oct 7 lists only ray-flash-2 and ray-2. How to check before you code, and Sume's gap.
20-second product video: Omni caps at 10 s, Wan 3.0 does it in one
A 20-second product video is one Wan 3.0 job on Sume: $2.50 at 720p, $5.00 at 1080p. Omni caps at 10 seconds, so 20 seconds means two clips and a join.
Gemini Omni Flash edit on Sume: a Python preflight for bad fields
A 29-line Python preflight for Sume video-router edit requests on gemini-omni-flash-1.1: catches the fields the docs say it rejects before you pay for a job.
Python CI guard: fail the build on retired Veo, Imagen, Sora ids
Twenty-three lines of standard-library Python scan a repo for Veo 2/3, Imagen 4 and sora-2 ids with their shutdown dates, and exit 1 when one is found.
MiniMax H3 outputs 24 fps and 32 kHz stereo: what Sume's H3 adds
MiniMax's H3 open-source post lists 24 fps video and 32 kHz stereo audio, 4 to 15 s clips and 768p by default. Sume's minimax-h3 takes 5 to 15 s.
Python urllib: POST /v1/images, 200 or 202, after Imagen 4 Fast
imagen-4.0-fast-generate-001 ended Aug 17. A stdlib Python call to Sume's image route that reads the status code, then polls the job when the answer is 202.
Codex 0.160.0 MCP status for one server: confirm Sume with mcp_health
Codex 0.160.0 adds single-server MCP status discovery with thread connection reuse. Confirm the Sume session itself with mcp_health and tools_list.
Cursor project .cursor/mcp.json or global ~/.cursor/mcp.json for Sume?
Put a URL-only Sume entry in .cursor/mcp.json to share it with a repo, and keep any API key in an env variable in the global file, not in git.
Deno: time out a Sume video submit, then retry with the same key
A fetch that times out may still have created a job. A 20-line Deno submit retries only 408, 429, 5xx and timeouts, always with one Idempotency-Key.
Meta wants a fixed frame rate: set Timeline output.fps when clips mix
Meta's Facebook feed page requires a fixed frame rate. Sume Timeline takes output.fps 24, 25, 30 or 60, and mixed-rate sources are resampled with judder.
HappyHorse 1.1's five aspect ratios vs the Sume video catalog
HappyHorse 1.1 on Cloudflare takes 16:9, 9:16, 1:1, 4:3 and 3:4. Which Sume video models cover all five, and which do not.
Python guard: refuse a Short over 180 s before the render bills
A 20-line Python check that blocks a Shorts render over 180 seconds and prices the Sume Timeline minutes (10 cents each) before you submit.
Python urllib: honor retry-after on a Sume 429, back off without it
A stdlib retry for GET calls that sleeps for retry-after when the 429 carries it and for a capped exponential delay when it does not, with jitter.
Akool resolution 1080P to 16K by plan vs Sume Avatar video at 720p
Akool lists max resolution of 1080P on Starter, 4K on Pro, 8K on Pro Max and 16K on Business. Sume Avatar 1.0 talking video is 720p at this time.
Qwen Image 2.1 sizes (2752x1536, 2400x1792) vs Sume Qwen ratios
The Qwen-Image-2.1 card lists 2048x2048, 2400x1792 and 2752x1536. Sume qwen-image takes 13 aspect_ratio values instead of pixels. How they line up.
Check a reference image URL before sending it to Sume Images
Sume rejects localhost, private-network and non-HTTPS reference URLs before submission. A short Python pre-flight check that catches them first.
Akool max video length: 15 to 60 minutes by plan vs Sume's 60 s
Akool lists 15, 30, 45 and 60 minute maximum video lengths on its four paid plans. A Sume Avatar 1.0 job tops out at 60 seconds; here is the cost of the gap.
n8n 2.43.0: resume agents after waiting workflows, with Sume runs
n8n 2.43.0 (pre-release, Oct 6) resumes Preview agents after waiting workflows finish. Pair a long Sume run with one webhook, deduped on request_id.
Runway hailuo3 at 10-15 credits vs h3_max at 5-8, and Sume's H3 ids
Runway lists hailuo3 at 10 to 15 credits a second and h3_max at 5 to 8. Sume has minimax-h3 and minimax-h3-max at $0.0625 to $0.20 a second.