Vai al contenuto principale

Tencent HunyuanAdded Mar 1, 2026Image generationPrivateOpen weights

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.

hunyuan-image-v3POST https://api.venice.ai/api/v1/image/generate
Price per image
$0.09
Aspect ratios
8 ratios
default 1:1
Prompt limit
3,000
characters

Pricing

USD per image
Per 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/generateRecommended
curl 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