Hy Image 3.5 lists 13 ratios; GPT Image 2.5 on Sume lacks six
OpenRouter's Hy Image 3.5 Preview ratio list has six ratios GPT Image 2.5 does not offer on Sume: 1:2, 1:4, 2:1, 2:3, 3:2 and 4:1. Which Sume rows list them.
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
Qwen Image Max at 10 cents or Qwen Image at 3: the edit gap
On Sume, Qwen Image Max is text-to-image only at 10 cents; Qwen Image is 3 cents and accepts reference images. Which to pick, and the 7-cent difference.
Grep for nano-banana-2 in your code: those calls bill as 2.1
Retired Nano Banana 2 ids still run on Sume, as 2.1 at 10 cents at 1K. A grep-and-replace plan so logs, tests and cost sheets name the model that ran.
Seedance 2 Mini at 1080p costs less than Seedance 2.5 at 720p: 10 s
A 10-second 9:16 clip: Seedance 2 Mini at 1080p is $4.26 on Sume, below Seedance 2.5 at 720p ($5.78). Full ladder for 2.5, 2.0, Fast and Mini inside.
Vidu Q4 takes 15 image refs: what Sume's reference limits are
Vidu Q4 Preview lists up to 15 image and 3 audio references. Sume does not list Vidu; Gemini Omni Flash 1.1 takes 10 images and 3 clips of 3 s, none audio.
Which Sume image model for what job: one price table, Oct 2026
Pick a Sume image model by job: thumbnails, product shots, text in images, edits and cheap drafts. One table with ids and billed cents, as of 2026-10-08.
4K AI video on Sume: Omni Flash $3.75 or an H3 upscale $2.00 for 10 s
Gemini Omni Flash 1.1 lists 4K natively: $3.75 for 10 s on Sume. MiniMax H3 bills 4K only as an upscale from 768p, about $2.00. What to check before you pay.
Edit a clip, swap a person, or move motion onto photos: 3 Sume models
Omni Flash edits a clip by prompt ($1.25 per 10 s, 720p), H3 Max Recast swaps people ($3.75, 768p), Genjutsu moves motion onto photos ($3.98, 480p).
Is Hy Image 3.5 Preview on Sume? Check the models list in code
Tencent's Hy Image 3.5 Preview is not in the Sume rows used here. How to confirm against GET /v1/images/models with a 12-line script instead of guessing an id.
Premium image models on Sume ranked: 7 to 27 cents a picture
ChatGPT Image 2.5 high is 7 cents on Sume, Nano Banana 2.1 and Qwen Image Max 10, Nano Banana Pro 19, ChatGPT Image 2 27. Ranked, with caveats.
Seedance 2.5 costs 1.53x Seedance 2.0 at 720p for 10 seconds
A 10 s 9:16 clip at 720p is $5.78 on Seedance 2.5 and $3.78 on Seedance 2.0 on Sume. What the extra $2.00 buys, and the ratio at 480p and 1080p.
Is MAI-Voice-2.1 on Sume? What Sume's audio docs list instead
Sume does not list MAI-Voice-2.1 or MAI-Transcribe-2. Here is what its docs do list for speech, transcripts, music and captions, with prices.
AI video with native audio: which Sume models let you turn it off
On Sume, only Kling v3 Pro prices audio separately (+$0.07/s). Gemini Omni and MiniMax always make audio; Grok Imagine and Genjutsu make none. Table inside.
How many aspect ratios each Sume image model lists, vs Hy's 14
Hy Image 3.5 Preview lists 14 aspect ratios. On Sume, Nano Banana 2.1 and Ideogram list 15, Grok and Flux 13, GPT Image 2.5 only 9. Full counts by row.
Hy Image 3.5 lists a 1.5K tier. No Sume image model does
Hy Image 3.5 Preview offers 1K, 1.5K, 2K and 4K. Sume's tier lists are 512, 1K, 2K, 4K or 1K/2K only. For about 1.5K, GPT rows take 1536x1536 as image_size.
30 seconds of footage: Omni, H3 Max with audio, or Wan plus a bed
Three routes to 30 seconds on Sume: Omni 3 x 10 s ($3.85), H3 Max 2 x 15 s ($3.10), or one Wan 3.0 clip plus a Lyria bed ($3.975). Arithmetic shown.
Which new text models can a Sume Format run name as model?
Format runs take a catalog id as model. Haiku 5.5, GLM 5.3 Flash and GPT-6 Astra are in Sume's registry; Mistral Large 4 and GLM 5.3 Fast are not.
Gemini Flash-Lite TTS lacks 29 languages that Flash covers
Google's table lists 132 languages for Gemini 3.8 Flash TTS and 103 for Flash-Lite, so 29 are Flash-only, including Thai, Swedish and Finnish. Read 2026-10-08.
Higgsfield Genjutsu motion transfer, 17 s at 480p: $6.7575 on Sume
Sume's higgsfield-genjutsu appears only when its provider is configured. When listed, 17 s at 480p is about $6.7575 and 720p $14.4713; check your catalog first.
Is GPT-6 Astra new this week? Sume has listed it since September
The OpenAI page for GPT-6 Astra states no release date. Sume's registry carries Astra with a rate card dated 2026-09-05, so it is not a new pick for Sume users.
GPT-6 Astra on Sume holds a $10 reserve per turn: wallet check
Sume's billing code reserves 1000 cents on an Astra turn (2000 with Fast) and releases what the turn does not use. Check wallet headroom before you pick it.
Haiku 4.5 in Sume's registry now points to Haiku 5.5: $1 to $0.10
Sume's registry retired Haiku 4.5 onto Haiku 5.5 with the successor set to always. List input drops from $1 to $0.10 per million; old rows keep the 4.5 card.
Haiku 5.5: cached tokens count toward the 100k price step
Anthropic counts cache reads and writes in a Haiku 5.5 prompt's length, so a 90k cached plus 15k fresh turn is billed at the over-100k rates. Worked example.
1,000 agent turns: Haiku 5.5 about $4, GPT-6 Astra about $400
At list rates, 1,000 turns of 30,000 input and 2,000 output tokens cost about $4 on Haiku 5.5 and $400 on GPT-6 Astra. The arithmetic and the cache effect.
How long can a Sume agent run take? Timeouts for slow models
Format runs are finalized at 90 minutes, or after 10 silent minutes once past 25. Agent Completions publish no deadline. Webhooks time out at 10 s per attempt.
MAI-Voice-2.1 ~550 ms vs Flash ~45 ms: does it matter for voiceover?
Microsoft lists ~550 ms and ~45 ms model-inference latency for MAI-Voice-2.1 and Flash. In series, 1,000 lines take 9.2 minutes vs 45 s. Read 2026-10-08.
Which BPM makes a 3 to 10 second Omni clip a whole number of bars?
Gemini Omni Flash 1.1 clips run 3 to 10 seconds. At 120 BPM a 10 s clip is 5 bars; at 128 BPM no whole-second length fits. A table of the BPMs that line up.
10 s Seedance 2 run: $3.78 cap plus $0.02 on Haiku or $2.40 on Astra
Ten seconds of Seedance 2 at 720p is $3.78 at Sume's price. Agent tokens sit outside the cap: about $0.024 on Haiku 5.5 or $2.40 on Astra over six turns.
Sume's image router lists 17 model ids on Oct 8, 2026; no Hy Image
The public Sume catalog on 2026-10-08 lists 17 model ids under Image Router. None is Tencent's Hy Image 3.5 Preview. See the list and the check.
Does the Sume spend cap cover the agent's own model tokens?
No: Sume's cap excludes the agent's LLM turn; debited_usd_micros includes it. At list rates that turn is about $0.004 on Haiku 5.5 and $0.40 on Astra.
A 20-turn agent session: Haiku 5.5 $0.03, Astra $3.10 with caching
Cache write on turn one, reads after: a 20-turn session with a 35k-token cached prefix costs about $0.031 on Haiku 5.5 and $3.10 on GPT-6 Astra. Arithmetic.
13-second clip: MiniMax H3 768p $0.98, H3 Max $1.30 or $2.60 at 1080p
A 13 s clip on MiniMax H3 at 768p costs $0.975 on Sume, $1.30 on H3 Max at 768p and $2.60 at 1080p; both start at 5 s, and only H3 Max has 1080p.
A 19-second single shot: which Sume video models take it in one job
Wan 3.0 and Seedance 2.5 take 19 s in one job ($4.75 and $27.01 at 1080p). Seedance 2.0, H3 and Omni top out at 15 s, 15 s and 10 s, so they need two jobs.
27-second continuous shot: Wan 3.0 $6.75 vs three 9 s Omni jobs $5.06
A 27 s shot at 1080p is $6.75 on Wan 3.0 and $38.38 on Seedance 2.5, one job each; Omni needs three 9 s jobs ($5.06) because it stops at 10 s.
8:1 strips and 21:9 banners: which image models take them
Nano Banana 2.1 lists 8:1, 4:1, 1:4 and 1:8 on Sume; Pro stops at 21:9 and 9:16. Prices per image for each ratio choice, read 2026-10-08.
Agent Completion or Format run: where can you pick Haiku 5.5?
Only a Format run takes a catalog model id. An Agent Completion accepts model sume-agent and nothing else, so Haiku 5.5 is a Format-run choice.
GLM-5.3-FlashX costs $0.37 in on Z.ai; Sume lists Flash, not FlashX
Z.ai's pricing page lists Flash, FlashX and GLM-5.3, with no Fast row. Sume's registry has a GLM 5.3 Flash row only.
Can a Haiku 5.5 agent look at images? Sume's 30-image attachment rules
Anthropic says all current Claude models take image input. Sume accepts up to 30 images, 30 MB each, 500 MB total; Haiku 5.5 is a Format-run pick.
Knowledge cutoff for a trend-research agent: Astra Apr 30 vs Haiku Jun
GPT-6 Astra's cutoff is Apr 30, 2026; Claude Haiku 5.5's is Jun 2026. A video agent researching this week's trends needs tools either way. Sume lists both.
Sume's caption aligner runs on Haiku 5.5: what it means for you
A sidecar LLM step in Sume's video captions moved from Haiku 4.5 to Haiku 5.5. The card is $0.10 in, $0.50 out per million; why the change is small.
Sume's GLM 5.3 Flash card is $0.075 in; Z.ai's page says $0.15
Sume's registry prices GLM 5.3 Flash at $0.075 input and $0.25 output per million. Z.ai's pricing page lists $0.15 and $0.50. Here is what to do with that gap.
Thinking effort defaults: Haiku 5.5, Astra and GLM Flash on Sume
Anthropic defaults Haiku 5.5 to medium effort; OpenAI sets no Astra default. Sume's picker offers Astra Low, Medium, High (default High); Haiku, GLM have none.
Which Sume video models accept a music track as an audio reference?
Seedance 2.x, Wan 3.0, MiniMax H3 and H3 Max take audio references; Gemini Omni Flash 1.1 does not. Prices for 8 s plus a $0.125 bed.
ChatGPT Image 2 vs 2.5 at medium quality, 16:9: price on Sume
At 16:9 and medium quality, ChatGPT Image 2 bills $0.0525 per image on Sume and ChatGPT Image 2.5 bills $0.0105: five times less. Table, batch math and a swap.
Image-to-video prompt: write the motion, not the photo
When a photo is already pinned as the first frame, spend the prompt on motion, camera and sound, not on describing what the picture shows. A worked rewrite.
Nano Banana 2 is retired on Sume: same price on Nano Banana 2.1?
Sume retired google/nano-banana-2 and runs old requests as Nano Banana 2.1 at the same price card: $0.10 at 1K billed. Tiers, ids and what the job stores.
Replace one prop in a video with AI: bottle to apple edit prompt
Swap one object in a finished clip with gemini-omni-flash-1.1 on Sume: the docs example prompt, fields you cannot set, and an 8-second price.
MiniMax H3 Max on Sume: video, lip-sync and recast, which id to call
Three Sume ids carry the MiniMax H3 Max name: minimax-h3-max for video, a lip-sync route and h3-max-recast. What each takes, its window and its rate.