Hy Image 3.5 Preview is not in Sume's catalog: what to call instead
Sume's image catalog does not list Hy Image 3.5 Preview. Check with one jq call, then pick a listed model by price: Soul, gpt-image-2.5, Seedream or Flux.

Sume's image catalog does not list Hy Image 3.5 Preview, so there is no model id to send. If you are searching for it, you can check this yourself in one call, then pick from the rows that are listed.
This post says nothing about Hy Image's specs because Sume does not serve it; the facts below are Sume's own.
Check the catalog
GET /v1/images/models is the source of truth. This prints any id that mentions hy or tencent; empty output means it is not there.
curl -s "https://api.sume.com/v1/images/models" \
-H "Authorization: Bearer $SUME_API_KEY" \
| jq -r '.data[].id' | grep -i -E 'hy|tencent' || echo "not listed"Listed rows by price
If you want a low-cost general text-to-image model, start from these. Prices are Sume's, per image.
| Model id | Per image |
|---|---|
| higgsfield/soul | $0.005 |
| openai/gpt-image-2.5 (low, 1024) | $0.007375 |
| x-ai/grok-image | $0.025 |
| qwen/qwen-image | $0.025 |
| black-forest-labs/flux.2-pro | $0.0375 |
| bytedance-seed/seedream-5-lite | $0.04375 |
Let Sume pick
If you only need a competent image and not a specific family, model: "sume/auto" lets Image Router choose; Sume does not disclose which family ran. For repeatable looks, pin a listed id instead.
If the catalog changes
Catalogs move. Run the grep above again before you decide, and treat GET /v1/images/models as the only authority for what a Sume key can call.
- Retired ids are listed in the docs with their replacements, for example the retired Nano Banana 2 id runs as 2.1.
- Pin a model id in production; use
sume/autoonly when you do not care which family ran.
Sources
Related posts
More in Models
- Text-in-image bake-off: 20 prompts on 4 Sume models costs $7.00
Test text rendering in AI images for $7.00: 20 prompts on Ideogram 4.5, GPT Image 2.5, Qwen Image Max and Nano Banana 2.1, with the cost of each on Sume.
- AA text-to-video top 12: six you can call on Sume, six you cannot
Of the 12 models on the AA text-to-video board, six have a Sume id that takes a prompt-only request. The list, with Elo and Sume's price per minute.
- 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.
- TTS Router ids: sonic-3.6 to sonic-preview, one price book
Sume TTS Router lists sonic-3.6, sonic-3.5, sonic-3, sonic-latest and sonic-preview, all at the TTS 1.0 character price. What each id is and when to pin it.
Written by Sume