Nano Banana 2.1 9:16: 768x1376, 1536x2752 or 3072x5504 for stories
The three 9:16 sizes Nano Banana 2.1 outputs and how to reach 1080x1920 for Stories and Reels covers with a 15 px vertical trim.
Models
The models behind Sume's video, image, speech, and music endpoints: ids, clip lengths, resolutions, aspect ratios, audio, references, and migration.
Start with: What AI models does Sume support? Every model id, by API surface
Wan 2.2 release date: July 28, 2025, and what the repo added
Wan 2.2's weights appeared on July 28, 2025. The README then adds S2V on Aug 26, Animate on Sep 19 and Diffusers on Nov 13. Dates, models and the 24 GB floor.
MiniMax H3 prompting guide: the h3-prompt-writing skill
MiniMax ships nine H3 prompting skills in its repo; one is portable via npx skills add. What is public, what is Hub-only, and how to use the output on Sume.
Nano Banana 2.1 3:2 print size at 300 dpi: 4.2 to 16.9 inches wide
How many inches a 3:2 Nano Banana 2.1 image prints at 300 dpi for 1K, 2K and 4K, and which tier to pay for on Sume for a 6x4 or larger print.
MiniMax H3 on a Mac: the h3.c Metal port, or a hosted job
MiniMax's integration index lists h3.c, a Metal-native MIT-licensed H3 port for Apple Silicon. What the index does and does not claim, and the hosted route.
Nano Banana 2.1 4:5 portrait: 928x1152 to 3712x4608, then 1080x1350
The 4:5 sizes Nano Banana 2.1 returns per tier and the 7 px crop that makes the 2K frame an exact 1080x1350 Instagram portrait.
Hy Image 3.5 Preview footnote watermark: 16 characters, none on Sume
Tencent's Hy Image 3.5 Preview can print a custom footnote of up to 16 characters in the lower right. Sume has no watermark field; how to add one yourself.
Nano Banana 2.1 0.5K: Google says unsupported, Sume lists 512
Google's docs say the 512px tier is not supported on Nano Banana 2.1, yet the Sume catalog lists 512. Which to trust, and how to check the row live.
HappyHorse 1.1 API watermark defaults to on: how to turn it off
Alibaba's HappyHorse 1.1 image-to-video API adds a Happy Horse text mark bottom-right unless you set watermark to false. What to check before delivery.
HunyuanVideo 1.5 prompt rewrite: the vLLM endpoints to set
HunyuanVideo 1.5 rewrites prompts by default through a vLLM endpoint you set; if none is set it runs without rewriting. The env vars, the flag, and the trade.
Nano Banana 2.1 16:9 output size: 1376x768 up to 5504x3072
What pixel size a 16:9 Nano Banana 2.1 image comes out at per tier, and the 15 px crop that turns the 2K frame into exact 1920x1080.
Qwen Image Max at $0.09375 vs Nano Banana 2.1 at $0.10: 100 images
On Sume, Qwen Image Max costs $0.09375 per image and Nano Banana 2.1 costs $0.10 at 1K. 100 images are $9.38 or $10.00. Ratios, resolution tiers and the pick.
Is Gemini Omni Flash free? No free tier; cheapest Sume clip is $0.11
Google's price page lists Not available for Omni Flash and Veo 3.1 on the free tier. The paid rates, and Sume's cheapest Omni clip (3 seconds at 360p).
Hy Image 3.5 Preview: 17.44 s median latency vs Sume's 30 s wait
OpenRouter shows a 17.44 s median for Hy Image 3.5 Preview. Sume lists no Hy row, but its image calls wait 30 s, then return a 202 job. Handle both.
Hy Image 3.5 Preview at 91.57% availability: retry math for 200 images
OpenRouter shows 91.57% availability for Hy Image 3.5 Preview. For 200 images that is about 17 failed first tries. The math, and Sume's failed-job billing.
Imagen 4 Ultra $0.075 or Fast $0.025 on Sume: 40 hero images
Sume lists Imagen 4 Fast at $0.025 and Imagen 4 Ultra at $0.075 per image. 40 hero images cost $1.00 or $3.00. Both take only five aspect ratios and no 4:5.
Seedream 5 Lite 4:5 portrait: render 1920x2400, resize to 1080x1350
Seedream 5 Lite lists 4:5 on Sume at $0.04375 per image. A 1920x2400 render shrinks to Instagram's 1080x1350 at an exact 0.5625 scale. 100 images cost $4.38.
Omni Flash 1.1 takes no audio reference: where a Short's voice goes
Gemini Omni Flash 1.1 accepts image and video references but not audio_url. For a voiced Short use native audio or a Timeline spine; 60 s is $7.60 at 720p.
H3 Max 4K request fails: H3 takes 2K and 4K as 768p upscales
minimax-h3-max accepts 480p, 768p or 1080p only. A 4K request belongs on minimax-h3, where it is a 768p upscale at $0.20 a second, $1.60 for 8 s on Sume.
Gemini Omni Flash 4K for a YouTube Short: what the extra $1.875 buys
A 10 s Omni Flash 1.1 clip is $1.875 at 1080p and $3.75 at 4K. Shorts top out at 1080p and Timeline outputs 1080x1920 by default, so 4K rarely reaches a viewer.
Recast 480p fails: resolution must be 768p or 1080p, priced by length
H3 Max Recast refuses 480p with 'resolution must be 768p or 1080p'. A 10-second source costs $3.75 at 768p and $5.625 at 1080p on Sume. The 5 to 30 s table.
Wan 3.0 duration 35 for a Short: max is 30 s, so split it: $8.75
Sume's Wan 3.0 accepts 2 to 30 seconds and the price tool refuses 35. A 35-second vertical Short at 1080p is a 30 s job ($7.50) plus a 5 s job ($1.25): $8.75.
Omni Flash rejects 768p: the resolution strings each video model takes
Omni takes 360p, 720p, 1080p or 4K; H3 takes 768p, not 720p. One table of the accepted resolution strings per model and the price range of each on Sume.
15-second vertical clip: MiniMax H3 768p $1.125 vs Wan 3.0 720p $1.875
For one 15 s 9:16 Short clip, MiniMax H3 at 768p is $1.125 and Wan 3.0 at 720p is $1.875. 768p is not 720p, so the pair is not like for like.
How many jobs make a 3-minute vertical video: 6, 12 or 18 by model
A 180 s vertical video needs 6 jobs on Wan 3.0 or Seedance 2.5, 12 on MiniMax H3 and 18 on Omni Flash 1.1, since each model has a different maximum clip length.
Jingle mascot clip: 6 s on Wan 3.0 with an audio_url reference, $0.75
A 6-second Wan 3.0 clip driven by an audio reference costs $0.375 at 480p, $0.75 at 720p and $1.50 at 1080p on Sume. Request shape included.
Python clip planner for a Short: split any length into model jobs
A short Python function splits a Short's length into equal whole-second jobs within each Sume video model's min and max, then prices them with Timeline.
GPT Image 2.5 at 1024px: xhigh is 3,122 output tokens, max is 7,024
Sume's docs give GPT Image 2.5 output estimates at 1024x1024: xhigh $0.09366, max $0.21072 at $30 per million tokens, i.e. 3,122 and 7,024 tokens.
GPT Image 2.5 quality auto reserves max: set quality yourself on Sume
On Sume, GPT Image 2.5 quality auto reserves max. At 1024px the max output estimate is $0.2634 with margin versus a $0.02475 low row. Set quality explicitly.
nano-banana-2 still works but runs as 2.1: check the stored job id
Sume retired Nano Banana 2: google/nano-banana-2 runs as Nano Banana 2.1 and the job stores the 2.1 id. A Python check and what you pay.
Nano Banana Pro vs 2.1 on Sume: 1.25x at 2K, 1.875x at 1K and 4K
Nano Banana Pro costs 1.875 times Nano Banana 2.1 at 1K and 4K on Sume but only 1.25 times at 2K ($0.1875 vs $0.15). A 200-image comparison at each tier.
Haiku 5.5 cache write vs read: break-even on a Sume tool catalog
Haiku 5.5 charges $0.125 per million to write cache and $0.01 to read it. For a 12,000-token Sume tool list the cache pays back on the first reuse.
Mistral Large 4 on a 12-turn storyboard: tokens are 4% of the bill
Mistral Large 4 lists $1.36 input and $4.18 output per million tokens. A 12-turn run that makes six Wan 3.0 clips spends 4.3% of its total on tokens.
Nightly read-only MCP audit: Haiku 5.5 vs Mistral Large 4 cost
A 30-turn nightly audit over Sume's read-only MCP tools costs $0.02175 on Haiku 5.5 and $0.27615 on Mistral Large 4, about 12.7x more, on stated assumptions.
Ideogram 4.5 edit with 5 images: only the first is edited, $0.075
On Sume, Ideogram 4.5 edits the first image and treats up to four more as references. Medium costs $0.075 per image; omit aspect_ratio to keep the source shape.
Omni Flash 1.1 is billed in tokens: 5,792 per 720p second, in dollars
Google bills Gemini Omni Flash 1.1 at 5,792 output tokens per 720p second and $17.50 per million. The math to dollars, and the Sume per-second rate.
Kling 4.0 API price: not public yet; what you can call today on Sume
No public Kling 4.0 API price was found on 2026-10-09. Sume lists a kling-3 video id and Kling 3.0 Motion Control at $0.1575 per second, 1 to 30 seconds.
Nano Banana 2.1 1K image is 1,120 tokens: Google's $0.0336 explained
Google prices Nano Banana 2.1 image output at $30 per million tokens: a 1K image is 1,120 tokens, $0.0336. 2K and 4K implied token counts, Batch half price.
Edit a video with Gemini Omni Flash on Sume: fields allowed or refused
Omni Flash 1.1 edit mode on Sume takes one video_url plus a prompt, defaults to 720p, and refuses aspect_ratio, duration and other media fields.
Gemini Omni Flash references on Sume: 10 images, 3 videos of 3 s
Omni Flash 1.1 on Sume takes up to 10 reference images and 3 reference videos of at most 3 s each, so 9 s of video. No audio reference. Tags and costs.
GPT Image 1 retires Oct 23: a 20-prompt test on 2.5 for about $6.06
OpenAI lists gpt-image-1 for removal on October 23, 2026. Test 20 prompts at low, medium and high on gpt-image-2.5 through Sume for about $6.06 first.
Nano Banana 2.1 at 8:1 and 4K: 12288x1536, 18.87 megapixels
Google's size table puts Nano Banana 2.1 8:1 at 4K at 12288x1536, about 18.87 MP, larger than a 4096x4096 square. Sume lists 8:1 and 4K at $0.20 flat.
Gemini 3.8 TTS, v4 Turbo, Scribe v2: which can you call via Sume?
None of the three. Sume's catalog (read 2026-10-09) lists sume/tts-1.0, five Sonic router ids, sume/stt-1.0 and three music ids. What to do with their files.
Cheapest 10-second 1080p AI video on Sume: Gemini Omni Flash 1.1 $1.88
For a single 10-second 1080p-class clip, Gemini Omni Flash 1.1 is the cheapest Sume video row at $1.88; Seedance 2.5 is the dearest at $14.22. Read 2026-10-09.
Cheapest 10-second 480p AI video on Sume: Wan 3.0 $0.63
For a single 10-second 480p-class clip, Wan 3.0 is the cheapest Sume video row at $0.63; Seedance 2.5 is the dearest at $2.69. Read 2026-10-09.
Cheapest 11-second 720p AI video on Sume: MiniMax H3 $0.83
For a single 11-second 720p-class clip, MiniMax H3 is the cheapest Sume video row at $0.83; Seedance 2.5 is the dearest at $6.36. Read 2026-10-09.
Cheapest 12-second 1080p AI video on Sume: MiniMax H3 Max $2.40
For a single 12-second 1080p-class clip, MiniMax H3 Max is the cheapest Sume video row at $2.40; Seedance 2.5 is the dearest at $17.06. Read 2026-10-09.
Cheapest 12-second 480p AI video on Sume: Wan 3.0 $0.75
For a single 12-second 480p-class clip, Wan 3.0 is the cheapest Sume video row at $0.75; Seedance 2.5 is the dearest at $3.23. Read 2026-10-09.