Guides
Sume guides: the API, Formats, agents, models, media tools and pricing, each answer dated and sourced.
Content Credentials after download: check the file you deliver
C2PA 2.2 defines Content Credentials and a separate Soft Binding API. Sume's docs do not say a downloaded output keeps one, so check the delivered file.
Sume assets from the terminal: upload-url, complete, download
The Sume CLI registers an asset in three write-gated steps and reads it back with download-url or download. Flags, the confirm gate and what stays private.
Asset id or public HTTPS URL? What Sume inputs accept
Sume generation fields take public HTTPS URLs directly. Localhost, private, non-HTTPS, signed URLs and wrong content types are rejected. When an asset id helps.
sume --agent --json: what it redacts before you paste output
Sume CLI --agent mode redacts or summarizes URL-like and account fields where supported. What to still strip before pasting output into a ticket or chat.
sume jobs watch timed out: recover the job before you resubmit
A local wait that times out does not cancel a paid Sume job. Inspect it with jobs status, events and result, then download, instead of submitting again.
What not to log from an AI API: keys, signed URLs, private media
Safe to log: request ids, job ids, status and sanitized media metadata. Unsafe: API keys, signed URLs, raw private media URLs and excess user content.
Where did the Sume Credits page go? Billing & subscription
The dashboard surface once called Credits is now Billing & subscription: plan status, balance and manual top-ups. What the API can read and what it cannot.
Install the Sume CLI in CI: checksums and pinned release tags
The hosted installer verifies checksums.txt and will not overwrite another sume on PATH. To pin, swap latest for a release tag such as v0.1.6.
YouTube thumbnails.set now allows 50MB: what to upload from Sume
YouTube's API history says thumbnails.set went from 2MB to 50MB on 2026-09-14. A video-frames still at source size (jpeg or png) fits the listed types.
YouTube thumbnail sizes fhd, qhd and uhd: frames from a clip
YouTube's Data API added fhd (1080p), qhd (1440p) and uhd (4K) thumbnail sizes on 2026-09-11. Here is how Sume's video-frames max_edge lines up.
YouTube playlistImages.insert 50MB: cover art from a clip frame
YouTube's API history raised playlistImages.insert from 2MB to 50MB on 2026-09-14. A Sume video-frames still is a way to produce the image to send.
YouTube Shorts up to 3 minutes: trim a long video to fit
YouTube's help page says Shorts can run up to three minutes and must be square or vertical. Sume video-trim cuts a range from a longer clip into a new MP4.
TikTok video_cover_timestamp_ms: pick the cover frame in seconds
TikTok's Direct Post field video_cover_timestamp_ms takes milliseconds. Preview candidate frames with Sume video-frames, then multiply the chosen time by 1000.
TikTok API 10-minute video limit: trim a longer video with Sume
TikTok's media guide says a developer can send at most 10 minutes through initialize upload. Sume video-trim cuts up to 900 s from a 1800 s source into an MP4.
TikTok 3-minute videos: cut a longer clip to 180 seconds via API
TikTok's page says all creators can post 3-minute videos, some 5 or 10. Sume video-trim writes a 180 s MP4 from a longer clip so any creator can post it.
TikTok upload chunk size: 5-64 MB and 1000 chunks for AI video
TikTok's media guide sets 5 MB to 64 MB chunks, 1 to 1000 chunks and a 4GB maximum. Sume gives no file size control, so measure the MP4 before you split it.
TikTok API accepts MP4, WebM or MOV: which format Sume returns
TikTok's media guide lists MP4 (recommended), WebM and MOV. Sume video trim and timeline write an MP4, so a Sume result already matches the recommended type.
TikTok title 2200 UTF-16 runes vs burned-in captions from Sume
TikTok's Direct Post title allows 2200 UTF-16 runes. Burned-in captions are separate video pixels: Sume's video-captions job burns the exact cues text you pass.
Instagram Stories API video: 60 seconds max, trim with Sume
Meta's reference lists Stories video at 3 to 60 seconds, 100MB and 23-60 FPS. Sume video-trim writes a range at 24, 25, 30 or 60 fps to fit.
Instagram Stories vs Reels API limits, side by side with Sume caps
Meta lists Reels at 3 s to 15 min and 300MB, Stories at 3 to 60 s and 100MB. Sume video-trim can cut either from a longer clip, up to 900 s of output.
Instagram API: JPEG only, no MPO or JPS. Stills from a video frame
Meta's publishing guide says JPEG is the only image format and MPO and JPS are not supported. Sume video-frames returns jpeg by default, or png.
Instagram carousel limit of 10: make 10 stills from one video
Meta's guide limits carousels to 10 images, videos or a mix, and 100 API posts per 24 hours. Sume video-frames takes up to 24 times per call, so pick 10.
Instagram carousel crops to the first image: crop stills to match
Meta says carousel images are cropped based on the first image, default 1:1. Sume video-filter crop, then video-frames, gives stills that share one shape.
Instagram 3-second minimum for Reels: check clips before publishing
Meta lists Reels at 3 seconds minimum, but Sume video-trim accepts down to 0.2 s. Read duration_seconds from the trim result before you publish.
LinkedIn Videos API: 500MB or 5GB? Plan for the lower number
LinkedIn's Videos API page lists a 75kb to 500MB file size and a 5GB maximum. Sume states no output file size, so measure the MP4 first.
LinkedIn Videos API thumbnail: pick a still from the clip first
LinkedIn's Videos API page says a system thumbnail may be added if you upload none. Sume video-frames returns jpeg stills at times you choose.
LinkedIn video captions: English SRT only vs burned-in text
LinkedIn's Videos API takes one English caption file, shown with SRT. Sume video-captions burns your cues text into the video and does not accept SRT uploads.
LinkedIn 30-minute video: build 1800 s with Timeline
LinkedIn's Videos API lists three seconds to 30 minutes. Sume Timeline 1.0 renders up to 1800 s in one MP4 at $0.10 per output minute: 30 minutes is the cap.
Video API duration: whole seconds only, no 7.5 s clips
Sume's video duration is an integer and each model lists whole-second supported_durations. Ranges per model and how to pick one before you submit a job.
frame_images plus input_references in one request: which wins?
When a Sume video request carries both frame_images and input_references, frame_images wins and the job runs as image-to-video. What that means for references.
Video 1.0 reference_audio_urls: why audio alone is rejected
In Video 1.0, reference_audio_urls (1 to 3 URLs) requires at least one reference image or video. Field limits for images, videos and audio references.
routing_preset kling or grok on Video 1.0: accepted, then ignored
Video 1.0 still accepts the retired routing_preset values cost, speed, quality, grok and kling, but all of them run through Auto. How to pick a family instead.
Video 1.0 last frame: end_image_url needs image_url first
To set a last frame on Video 1.0, send end_image_url together with image_url. The docs list the modes: text, first frame, start and end frames, references.
Video 1.0 generate_audio: why the docs say to omit it
Sume's Auto family always generates audio for Video 1.0 requests, so the docs tell you to omit generate_audio. What the field does and where audio is optional.
first_frame_url and last_frame_url on Video 1.0: deprecated names
Video 1.0 still reads first_frame_url and last_frame_url, but the docs prefer image_url and end_image_url. The rename map and one rule about the end frame.
Video 1.0 duration vs duration_seconds: what if they differ?
Video 1.0 accepts duration and its alias duration_seconds. If you send both they must agree; the value is checked against the Auto serving family.
Video 1.0 bitrate_mode: still in the shape, rejected by Auto
bitrate_mode is retained in Video 1.0's legacy request shape but Auto rejects it. Omit it, and note that Gemini Omni Flash 1.1 has no bitrate_mode either.
Video 1.0 metadata field: stored on the job, not sent upstream
The metadata object on a Video 1.0 request is stored on the job as caller metadata and is not sent to the provider. Use it to tag jobs; the limits it has.
video.generation.completed on Sume? The webhook event map
OpenRouter sends video.generation.* events; Sume sends job.completed, job.failed or job.canceled with a signed body. What to change in a receiver.
OpenRouter video size parameter on Sume: 400 unsupported_parameter
On Sume every video model reports supported_sizes null, so a size parameter returns 400 unsupported_parameter. Send resolution and aspect_ratio instead.
OpenRouter video seed on Sume: no v1 model accepts it
OpenRouter lists seed for deterministic video generation. On Sume no v1 video model accepts seed: each reports seed false and the field is rejected.
OpenRouter video provider.options on Sume: rejected, not dropped
OpenRouter lists provider passthrough configuration. Sume v1 runs one backend per model, so a non-empty provider.options returns 400 unsupported_parameter.
google/veo-3.1 style ids vs Sume: bare video model ids
OpenRouter names video models org/slug, such as google/veo-3.1. Sume uses bare catalog ids like seedance-2 and never a provider prefix. How to port an id.
Activepieces 10-minute flow timeout and long Sume video jobs
Activepieces Cloud caps a flow run at 10 active minutes. Submit the Sume job async, pause the flow, and resume on the result instead of polling in a loop.
Activepieces subflow retried: keep Sume jobs from billing twice
A retried Activepieces subflow can re-run your Sume submit. Derive the Idempotency-Key from a stable input, not the attempt, so a retry returns the same job.
Activepieces sync webhook 408 at 30 seconds: use Sume async
An Activepieces /sync webhook returns 408 when no response arrives in 30 seconds. Call Sume in async mode, which answers 202 with a job id at once.
Activepieces wait for webhook: resume URL as Sume webhook_url
Pass an Activepieces waitpoint resume URL as Sume's webhook_url and the paused run resumes on the terminal job event. Know the retries and signature limits.
Amazon AI-generated people tag: contains-synthetic-performer
Amazon's seller post says photorealistic AI people in listings, A+ and shoppable videos need the XMP keyword contains-synthetic-performer. Tag the final file.