Guides
Sume guides: the API, Formats, agents, models, media tools and pricing, each answer dated and sourced.
Threads API video max is 300 s: split a 21-minute talk into parts
The Threads API page lists video up to 300 seconds and 1 GB. Split a 21-minute recording into five trim requests with a small Python script. $0.02 per trim.
Make takes 300 webhook requests per 10 seconds: a Sume queue fits
Make accepts 300 incoming requests per 10 seconds. A 100-item Sume queue with per-item webhooks and 16 in flight stays far below that. When 429 and 400 matter.
Fliki API needs Premium; Sume lists API rate limits on Free too
Fliki says API access is on Premium and Enterprise only. Sume's docs list API key rate budgets from Free through Scale. What that means for cost.
Synthesia's 500 signup credits: 5 minutes of video or 1 survey reply
Synthesia lists 500 signup credits: about 5 minutes of video, 6 of lip-sync dubbing or 1 survey response at its listed rates. The same time on Sume in dollars.
MiniMax H3 defaults to 2K at MiniMax; on Sume the default is 768p
MiniMax's H3 page says 2K is the default. Sume's minimax-h3 runs native 480p or 768p with a 768p default; 2K and 4K are billed upscales.
Real estate listing voice-overs: 25 homes at 700 characters
25 listing narrations of 700 characters cost $0.385 on MAI-Voice-2.1, $0.263 on Flash, and $1.00 on Sume TTS as 25 jobs. See the batched figure.
30-second video ad on Sume: one clip or two joined, priced
One 30 s Seedance 2.5 clip is $17.33 at 720p; two joined 15 s Seedance 2 Fast clips are $9.17 with the $0.10 Timeline join. Wan 3.0 30 s is $3.75.
4K 3840x2160 for YouTube: Sume Timeline output stops at 2160 per edge
YouTube lists 35-45 Mbps for 4K. Sume Timeline allows even width and height from 256 to 2160, so 3840x2160 is refused. What you can render instead.
720x1280 vs 1080x1920 for a 60 s Short: 40 MB vs 63 MB
YouTube lists 5 Mbps for 720p and 8 Mbps for 1080p. A 60 second Short is 40.38 MB vs 62.88 MB with audio. Set output.width and height in Sume Timeline.
A 12-minute video job costs 24 status reads at 30 s and 360 at 2 s
Poll cadence arithmetic for Sume video jobs: 30-second polls, the 2-second SDK floor, and the 20-minute client deadline, with a runnable calculation.
AI avatar disclosure line as the first caption cue on a Sume clip
Tavus says disclosure features are still being worked on for realistic avatars. On a rendered Sume clip you can author the label yourself with caption cues.
Budget 250 product shots: read each Sume model's price in code
A short Python script reads the pricing line from Sume's per-model endpoints route and prints the cost of 250 product shots. Reference rules and a worked table.
Cancel queued video jobs when the offer changes: Pro plan example
On Pro, 4 jobs process and 20 wait in the queue (24 accepted). Only queued jobs can be canceled; a started job returns 409 job_generation_already_started.
Check a new Sume video model against your clip spec before you pay
Four catalog fields decide if a new video model fits your pipeline: durations, resolutions, ratios, and references. A Python check that submits no job.
Chinese and English text in images: Hy Image 3.5's claim, Sume's rows
OpenRouter says Hy Image 3.5 Preview renders Chinese and English text. Sume does not list it. How to test Chinese signage on the Sume rows that are listed.
Clef context: 65,536 on Cloudflare, 16,384 on the model card?
Cloudflare's Workers AI page lists 65,536 tokens of context for Clef; its Hugging Face card says 16,384 by default. Budget from the smaller. Cost math inside.
Cost of 200 five-second clips a month: hosted Sume ids vs a rented GPU
At Sume prices, 200 five-second clips cost $75 to $200 a month depending on id and resolution. The same sum for a rented GPU, with the break-even hours.
One minute of AI video: Runway Gen-4.5, Luma Ray3.2, Wan 3.0, Seedance
One minute of AI video costs $3.60 to $85.29 depending on the model: Runway $7.20, Luma Ray3.2 $3.60 to $14.40, Wan 3.0 $7.50 on Sume. Arithmetic inside.
Cost per viewer of a 20 second avatar clip at 10, 100 and 1,000 views
A rendered Sume avatar clip costs the same however many watch: $3.68 on standard. That is $0.368 per viewer at 10, $0.0368 at 100, $0.00368 at 1,000.
EU, UK or South Korea team: which open video weights you may use
HunyuanVideo and MiniMax H3 licenses exclude the EU, UK and South Korea. Wan 2.2 is Apache 2.0 and LTX-2.5 is worldwide with a revenue line.
Game NPC barks: 800 lines at 60 characters, voice cost
800 NPC lines of 60 characters are 48,000 characters: $0.72 on MAI-Voice-2.1-Flash, $1.056 on MAI-Voice-2.1, $8.00 on Sume as 800 jobs.
gemini-nano-banana-2.1 or google/nano-banana-2.1: which id Sume takes
Google's pricing page names the model gemini-nano-banana-2.1. Sume's image API takes google/nano-banana-2.1 and runs the old nano-banana-2 as 2.1.
Gemini Omni Flash 1.1 ranks 8th, 4th and 3rd on three AA boards
Gemini Omni Flash 1.1 is eighth on AA text-to-video, fourth on image-to-video and third on editing. On Sume it is one id at $0.125 a second at 720p.
Go httptest for a Sume poll loop: assert next_poll_after_seconds
A 29-line Go test: httptest answers in_progress with next_poll_after_seconds 30 twice, then completed, and asserts the loop slept 30 seconds twice.
Go net/http: a Sume video submit retry loop with one Idempotency-Key
A 30-line Go function using net/http that retries a Sume video submit on 429 and 503, reads Retry-After, and reuses one Idempotency-Key. Run on a stub.
Google says Imagen is shut down: test your Imagen call on Sume now
Google's Imagen page says Imagen models are shut down. Sume lists Imagen 4 Fast and Ultra separately. One catalog check and one request tell you if yours works.
GPT Image 2.5 for packaging text: default high, xhigh and max prices
GPT Image 2.5 on Sume defaults to quality high. At 1024x1024 the provider output is $0.09366 at xhigh and $0.21072 at max, about $0.117 and $0.263 billed.
Griffin-Lite 10 ms audio packets vs Sume's 4 second minimum clip
Two ends of avatar timing: Tavus Griffin-Lite streams audio in packets as small as 10 ms; Sume Avatar 1.0 plans clips of 4 to 12 seconds. What each fits.
H3 on vLLM-Omni: 87 s on 4 B300 for one clip, and the cost
MiniMax says an 8.7 s H3 clip takes about 87 s on 4 B300 GPUs. Turn that into GPU-seconds, a break-even rate, and compare with a 9 s Sume job.
HappyHorse 1.1 is 12th at 1,042 Elo: what ranks above it on Sume
HappyHorse-1.1 is 12th on the AA text-to-video board at $10.80 a minute. Sume does not list it; six Sume models rank above it. Per-minute prices inside.
Hosted video instead of a GPU: a Python submit-poll-download script
Replace a local H3 or Wan pipeline with three HTTP calls. A Python script that submits a minimax-h3 job to Sume, polls it and saves the MP4, with job states.
Is Wan 3.0 an upgrade on Wan 2.7? 113 Elo more on the AA editing board
On the AA video-editing board Wan 3.0 (1,187, $12.00 a minute) beats Wan 2.7 (1,074, $16.90) by 113 Elo. Sume lists Wan 3.0, not 2.7; it runs 2 to 30 s.
Kling 3.0 Omni is 9th for video editing at 1,000 Elo: Kling 3 on Sume
Kling 3.0 Omni (1080p Pro) is ninth on the AA video-editing board at $10.91 a minute. Sume lists kling-3 for generation: $8.40 or $12.60 a minute, 4 to 15 s.
Luma Ray 3.2 HDR costs 2x SDR and EXR 3x: 5 s at 720p and 1080p
Luma lists a 5 s Ray 3.2 clip at $0.30 SDR, $0.60 HDR and $0.90 HDR plus EXR at 720p; $1.20, $2.40 and $3.60 at 1080p. Sume does not list Luma.
Luma Ray 3.2 video-to-video: 20 s, 64 keyframes, vs Omni edit on Sume
Luma's Ray 3.2 video-to-video keeps the source length up to 20 s and takes up to 64 keyframes. Sume does not list Luma; its edit route is Gemini Omni Flash 1.1.
Mac or Windows team: which open video models need Linux and CUDA?
HunyuanVideo and HunyuanVideo-1.5 list Linux; LTX-2.5's fastest decoder is Linux plus CUDA; H3 has a Mac route. What each page says and a hosted option.
MiniMax H3 4K hero clip vs 768p cutdowns: holiday ad cost
A 10-second MiniMax H3 clip is $0.75 at 768p, $1.625 at 2K and $2.00 at 4K on Sume. Five free reference images are included; extra ones are $0.10 each.
MiniMax H3 on a 12 GB RTX 3060: 480p only, 42 GB, and the price
MiniMax says 12 GB of VRAM runs 480p H3 clips with audio from a pruned int8 checkpoint of about 42 GB. What that buys, and a 480p clip on Sume costs.
minimax-h3 vs minimax-h3-max on Sume: price per clip at 768p and 1080p
At 768p, minimax-h3-max costs $0.10 a second on Sume against $0.075 for minimax-h3. 1080p exists only on Max. Per-clip prices for 5, 10 and 15 seconds.
Omni Flash forecast: 200, 500 or 2,000 eight-second clips a month
A monthly forecast for gemini-omni-flash-1.1 on Sume: 200, 500 or 2,000 eight-second clips cost $60 to $6,000 depending on resolution. Four-column table.
Nano Banana 2.1 4K batch: handle 200 and 202, reuse the key
A 4K Nano Banana 2.1 call can return 200 with the image or 202 with a job. A short Python handler, the retry rule, and what 4K costs: $0.20 per image on Sume.
Nano Banana 2.1 4K is 3.4x the 1K price at Google, 2x on Sume
Google bills 1,120 tokens at 1K and 3,780 at 4K for Nano Banana 2.1, a 3.375x gap. Sume's tiers go $0.10 to $0.20, 2x. Why the ratio differs.
A news app's Listen button: 5,000 backlog articles, voice cost
Voicing a backlog of 5,000 articles at 4,000 characters is 20 million characters: $440.00 on MAI-Voice-2.1, $300.00 on Flash, $950.00 on Sume TTS.
Nine Performance Max videos (3 ratios x 3 concepts): Sume cost
Three concepts in 16:9, 1:1 and 9:16 at 10 seconds each is 90 video seconds. At Wan 3.0 720p that is $11.25 on Sume; Seedance 2.5 is about $52.
Omni Flash resolution ladder on Sume: 0.3x, 1x, 1.5x, 3x of 720p
On Sume, Omni Flash 1.1 costs 0.3x at 360p, 1.5x at 1080p and 3x at 4K compared with its 720p rate of $0.125 a second. Per-clip prices at 8 and 10 seconds.
One idempotency key per model when a video fallback changes payload
Reusing an Idempotency-Key after switching video models returns 409 idempotency_conflict. Build the key from order, model, and prompt hash so retries stay safe.
Packaging label text test: 12 prompts on 3 Sume models, what it costs
Test Nano Banana 2.1, Imagen 4 Ultra and GPT Image 2.5 on 12 label-text prompts first: about $1.20, $0.90 and $1.40 on Sume. A short script runs it.
Python argparse CLI that checks seconds per Sume model first
A 25-line argparse CLI: choices reject unknown models, a duration check uses the documented limits, and --dry-run prints the body. Runs offline.