Guides
Sume guides: the API, Formats, agents, models, media tools and pricing, each answer dated and sourced.
HeyGen Stripe Projects API key vs how you get a Sume key
HeyGen lets an agent provision a key with stripe projects add heygen/api. Sume keys are created in the dashboard, workspace-scoped and shown once.
HeyGen studio video scene limit: 50 scenes, and Sume's 4-60 s plan
HeyGen studio videos allow 50 scenes and 30 minutes per scene. Sume multi-scene video_inputs share one 4-60 second window and one resolved avatar.
Is Runway free? 125 one-time credits, and Sume's Free plan
Runway has a $0 Free plan with 125 one-time credits; Standard is $15 per month. Sume's Free plan covers image generation with no card and 1 concurrent job.
Ken Burns effect API: Timeline stills are static holds
Sume Timeline holds a still image static; motion is accepted and ignored with a motion_ignored warning. zoompan is on the video filter allowlist.
AI kids story video generator: scenes of 2 to 30 seconds
Make a children's story video as one scene per request: wan-3.0 takes 2 to 30 seconds per scene, then join up to 200 slots in a Timeline 1.0 render.
Kling 4.0 21:9 ultrawide: check Sume's aspect ratios
Kling 4.0 supports 21:9 output. Sume documents 21:9 as a ratio, but each model lists its own supported_aspect_ratios, so read them before sending.
Kling 4.0 Flash early access: how to tell what Sume lists
Kling 4.0 Flash opened to a limited group on Sept 28 with full launch in October. On Sume, a model is callable when the live catalog lists it.
AI real estate walkthrough from photos: chain first/last-frame clips
Kling 4.0 takes up to 10 keyframes for a walkthrough. Sume takes a first and last frame per clip, so chain one clip per room pair and join them on a timeline.
Kling 4.0 stereo audio vs Sume's generate_audio flag
Kling 4.0 moves to two-channel stereo audio. Sume exposes generate_audio and per-model audio capability; check the catalog for what each model reports.
LinkedIn ad image size and AI-generated images in Campaign Manager
LinkedIn single image ads accept JPG, PNG or GIF up to 5 MB, and Campaign Manager has its own AI image tool. Which format to set on a Sume upload.
LinkedIn carousel ad specs: 2 to 10 cards, images only
LinkedIn carousel ads take 2 to 10 image cards up to 10 MB each, 1080x1080 recommended, no video. How to plan the cards with Sume's four-images-per-job limit.
LinkedIn in-stream video ads: up to 90 seconds, in testing
LinkedIn's video ad page says in-stream ads can run up to 90 seconds and are in testing. How to trim a clip to length and make a horizontal and vertical pair.
LinkedIn 4:5 ad image: 720x900, mobile only, no side borders
LinkedIn's vertical single image ad is 4:5 at 720x900 and serves on mobile only; 1:1.91 vertical images get side borders. How to request 4:5 on Sume.
LinkedIn video ad thumbnail and captions: JPG/PNG 2 MB, SRT
LinkedIn wants a JPG or PNG thumbnail up to 2 MB and text-only SRT captions. Sume extracts the frame still; its caption route burns text into the video.
Add a lower third name tag to a video with an API
Sume has no lower-third template. Burn a name and title as one authored caption cue with a newline, and set its height with design.placement.anchor_ratio.
Luma API 429 requests per minute: sliding window vs Sume
Luma counts requests in a sliding 60-second window and returns 429 if RPM or concurrent jobs fails. Sume returns 429 rate_limited: back off, reuse the key.
Luma API concurrent jobs limit vs Sume plan concurrency
Luma caps active generations per API client and answers 429 when full. Sume ties concurrency to your plan and queues extra jobs until queue_full.
Luma API video URL expires after 1 hour: what to do on Sume
Luma Agents API video URLs are presigned and expire after 1 hour. On Sume, a completed job is fetched with your API key from the /content endpoint.
Luma API X-Request-Id vs Sume x-sume-request-id
Luma's X-Request-Id echoes your header or is generated. Sume sends x-sume-request-id on every response; quote it, plus error.code, when you contact support.
Kling 3.0 4K on Luma: 147 credits per second, audio on or off
Luma lists Kling 3.0 at 2160p for 147 credits per second with or without audio; at 1080p it is 40 without and 49 with. Sume has a generate_audio field.
MiniMax H3 Max on Luma: credits per second in dollars
Luma lists MiniMax H3 Max at 18, 28 and 56 credits per second. Here is that in dollars by plan, and the per-second dollar rate Sume bills instead.
Ray 3.2 API aspect ratios and resolutions, and Sume's lists
Luma lists six Ray 3.2 aspect ratios (9:16 to 21:9) at 540p, 720p and 1080p. Sume reports ratios per model in supported_aspect_ratios and rejects size.
Luma Ray 3.2 extend with a generation id vs Sume per-clip jobs
Luma extends video from one prior generation id as start or end frame. Sume docs describe frame_images with first_frame or last_frame, a new job per clip.
Ray 3.2 API for render farms: the Sume callback_url pattern
Luma pitches the Ray3.2 API for pipelines and render farms. On Sume, wire an async video job with callback_url, Idempotency-Key and a request id to log.
Luma Ray 3.2 video edit ignores aspect_ratio: Sume video_url edit
On Luma Ray 3.2 a video edit takes its aspect ratio from the source and ignores the field; reframing needs a target. Sume edits through video_url.
Seedance 2.0 4K price: Luma 261 credits/sec, Runway 150, Sume 1080p
Luma lists Seedance 2.0 at 4K for 261 credits per second; Runway's docs list 150. Sume's docs list seedance-2 at 480p, 720p and 1080p, with no 4K entry.
Veo 3.1 on Luma with audio: 280 credits per second, double 140
Luma lists Veo 3.1 at 140 credits per second without audio and 280 with, at 720p and 1080p. Google lists dollars per second. Sume has a generate_audio field.
Make a voice louder than the music: gain_db and duck_db ranges
In Timeline 1.0, raise the voice with audio.gain_db (-60 to 12) and lower the music bed with soundtrack.duck_db (0 to 20). Ranges and refusal codes.
Midjourney style reference API: input_references on Sume
Midjourney's srefs live in its own app. On Sume, carry a style with a public HTTPS reference image in input_references plus a prompt, on models that allow it.
Nano Banana batch API: Gemini's 24 h batch vs Sume async jobs
Gemini's Batch API trades up to 24 hours of turnaround for higher rate limits. Sume has no batch tier for images: send async or webhook jobs per request.
Nano Banana multiple images at once: n range vs Gemini's count
Google says Gemini won't always return the exact image count you ask for in a prompt. On Sume, set n, and read each model's n range from the catalog.
Nano Banana video to image: poster from a video via Sume stills
Google's Gemini API takes a video as context for a thumbnail or poster. Sume's images API takes image references only, so grab a still frame first.
Export one video as 9:16, 1:1 and 16:9 with the API
Call Timeline 1.0 three times with the same clip and a different output.width and height each time. Three renders cost $0.30 for a clip under a minute.
OpenAI Agents API durable sessions and Sume job ids
A durable OpenAI Agents API session continues across turns; a Sume render is a separate job. Keep the job id in the session and re-read it, never re-create.
OpenAI Agents Python MCP error content: reading Sume tool errors
openai-agents-python v0.20.0 keeps MCP error content with structured output. Sume tool failures arrive as isError text with code, message and http_status.
OpenAI Agents Python MCP non-text content as JSON: Sume results
openai-agents-python v0.20.0 serializes non-text MCP blocks as JSON. Sume tool results are text blocks, with media delivered as URLs inside the JSON.
OpenAI Agents Python MCP backoff ceiling vs Sume retry-after
Set the MCP retry backoff ceiling low enough that a Sume 429 with retry-after is honored first, and never retry a paid create without its idempotency key.
Does an OpenAI API key expire? Expiry dates and key rotation
OpenAI project keys can now carry an expiration date and orgs can cap lifetime. Sume documents no expiry field: rotate by minting a replacement key.
OpenAI async tool calling for long-running render jobs
OpenAI's async tool calling lets the model keep working while your tool runs. For a slow Sume render, return the job id fast, then wait in slices.
OpenAI image-encoding fix: rerun workflows with the right key
OpenAI fixed an image-encoding bug and advised retrying affected workflows. On Sume, a replayed idempotency key returns the original; use a new key to rerun.
mTLS instead of an API key? How Sume authenticates calls
OpenAI's docs list mutual TLS and workload identity federation. Sume authenticates API calls with one API key header and signs webhooks with HMAC.
Pinterest ad image size: 2:3, 1000x1500, 40-character title
Pinterest ad images: PNG or JPEG, 2:3 (1000x1500), 100-character title with about 40 showing. Why 1000x1500 clashes with Sume's x16 pixels rule.
Pinterest Collections ads specs: one hero, up to 24 secondaries
A Pinterest Collections ad shows one hero and three secondaries, then up to 24 secondaries fullscreen. No GIFs, desktop only. A batching plan for the assets.
Pinterest white-background Pins get a 4% overlay: what to do
Pinterest puts a faint #000000 layer at 4% opacity on white-background image Pins in light mode. Choose your generated background tone on purpose.
Pinterest Showcase ads specs: title Pin plus four cards
A Pinterest Showcase ad is one 2:3 title Pin plus up to four static cards, with up to three features per card. Plan it as one generated image set.
Pinterest video pin minimum length: 4 seconds, and which models fit
Pinterest's product specs set a 4-second minimum for video pins. seedance-2.5 starts at 4 seconds in Sume; wan-3.0 and Gemini Omni Flash can go shorter.
Podcast video clip in vertical format: 1080x1920 by default
Timeline 1.0 renders 1080x1920 MP4 by default, so a podcast clip is vertical unless you set output width and height. Cut, segment and render steps.
AI podcast intro music generator: one prompt, fixed price
Write a podcast intro as one Music Router prompt of 1 to 5000 characters. Every generation is charged the fixed Music price, whichever model id you route to.