Hunyuan Image 3.0
Hunyuan Image 3.0 is Tencent’s open-weight text-to-image model, served here as the Instruct version, which reasons about a prompt before generating. It suits detailed, instruction-heavy prompts of up to 3,000 characters.
Price per image
$0.09
Aspect ratios
8 ratios
default 1:1
Prompt limit
3,000
characters
Pricing
USD per imagePer image
$0.09
Optional upscale: $0.02 at 2x and $0.08 at 4x.
Examples
Specs
- Model ID
hunyuan-image-v3- Endpoint
POST /api/v1/image/generate- Aspect ratios
- 1:13:216:921:99:162:33:44:5
- Prompt limit
- 3,000 characters
- Steps
- default 20, max 50
- Added
- Mar 1, 2026
- Weights
- Open
Capabilities
Modalities
- Text
- Input
- Image
- Output
Features
- Image editing
- Not supported
- Multi-image editing
- Not supported
- Web-grounded generation
- Not supported
- Style references
- Not supported
- Upscale
- 2x and 4x
POST
/api/v1/image/generateRecommendedcurl https://api.venice.ai/api/v1/image/generate \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "hunyuan-image-v3",
"prompt": "A retro travel poster with the bold headline \"VENICE\" in large condensed serif type, sunset color palette",
"aspect_ratio": "1:1"
}'Privacy
Tier 1
Anonymized
Included
Tier 2 · this model
Private
Zero data retention, enforced by contract. Prompts and outputs aren’t stored.
Tier 3
TEE
Not available
Tier 4
End-to-end encrypted
Not available