4:5, 9:16 and 16:9 together: 15 of 19 Sume image models list all three
Which Sume image models list 4:5, 9:16 and 16:9 in one catalog row, which four miss 4:5, and what each costs per image.

Fifteen of the 19 Sume image models list 4:5, 9:16 and 16:9 together, so one model can cover an Instagram feed post, a Story and a YouTube thumbnail. The four that miss 4:5 are Higgsfield Soul, Grok Imagine, Imagen 4 Fast and Imagen 4 Ultra. Every model lists 9:16 and 16:9.
The 15 that cover all three
Pass aspect_ratio in the request, for example 4:5 for a portrait feed post. 4:5 is Instagram portrait (1080x1350). Nano Banana Pro sends 4:5 natively at about 928x1152 at 1K, and exact 1080x1350 comes from a documented post-step through job target_pixels.
| Model | Billed per image |
|---|---|
| Qwen Image | 3 cents |
| Flux 2 Pro | 4 cents |
| Seedream 4.0 | 4 cents |
| Recraft V4 | 5 cents |
| Seedream 4.5 | 5 cents |
| Seedream 5.0 Lite | 5 cents |
| Flux 2 Flex | 7 cents |
| ChatGPT Image 2.5 | 7 cents |
| ChatGPT Image 2.5 Sunburst | 7 cents |
| Ideogram V3 | 8 cents |
| Ideogram 4.5 | 8 cents |
| Nano Banana 2.1 | 10 cents |
| Qwen Image Max | 10 cents |
| Nano Banana Pro | 19 cents |
| ChatGPT Image 2 | 27 cents |
The four that miss 4:5
These models list 9:16 and 16:9, so a vertical Story or a wide thumbnail works, but a 4:5 request returns 400 unsupported_parameter. The nearest substitute is 3:4, which Imagen lists, or 2:3, which Soul and Grok list.
Grok Imagine adds the phone ratios 9:19.5 and 9:20, which no other model lists.
| Model | Billed per image | Nearest portrait ratios |
|---|---|---|
| Soul (Higgsfield) | 1 cents | 9:16, 3:4, 2:3 |
| Grok Imagine | 3 cents | 2:3, 3:4, 9:16, 9:19.5, 9:20 |
| Imagen 4 Fast | 3 cents | 9:16, 3:4 |
| Imagen 4 Ultra | 8 cents | 9:16, 3:4 |
Practical pick
If one model has to serve three placements, the cheapest full-coverage row is Qwen Image, which lists all three and bills 3 cents. At 5 cents Seedream 5.0 Lite adds image editing. Set the ratio per request, never rely on a crop, and confirm with the live descriptor from GET /v1/images/models.
Edge cases to know
Ratio support is per model, and a request that sets a value the model does not list is rejected with 400 unsupported_parameter rather than adjusted. On edit calls, aspect_ratio: auto matches the reference image, and leaving the field out is not equivalent. Always read supported_parameters from the catalog before you pin a tier or ratio.
For a three-placement campaign, one prompt at three ratios costs 9 cents on Qwen Image, 12 on Flux 2 Pro, 15 on Seedream 5.0 Lite and 21 on GPT Image 2.5 at high. A set of 50 products is therefore $4.50, $6.00, $7.50 or $10.50. Pick the row, then pin the three ratios in code so a copy-paste never sends a ratio the row does not list.
Sources
Related posts
More in Models
- 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.
- AI video news Oct 1-8, 2026: Vidu Q4 Preview, Kling 4.0, Sume coverage
Vidu Q4 Preview launched Oct 7 and kling.ai headlines Kling 4.0. We checked Runway, Luma and Veo, and which of them Sume lists.
- Audio API launches, Oct 1-8 2026: dates, prices and what Sume covers
A dated calendar of speech, voice and music releases from Sep 28 to Oct 8, 2026, each with the number the vendor published, and which ones Sume lists.
- background: transparent on the Sume image API: two GPT rows only
Transparent PNGs from the Sume image API need background: transparent, which only the two GPT Image 2.5 rows list. See the request, price and the 400 elsewhere.
Written by Sume