Providers and ModelsTencent

Hunyuan Image 3

Hunyuan Image 3
Tencent · Image Generation
POST /v1/images/generations

Open-source text-to-image model on a multimodal Mixture-of-Experts architecture with photorealistic detail and strong multilingual text rendering.

At a glance

FieldValue
Model idhunyuan-image-3
Model release date2025-09-28
Input modalitiesText
Output modalitiesImage
Context window-
Weight precision-
Featuresphotorealistic, multilingual
Native inferenceNo
NewNo
Supported endpointsPOST /v1/images/generations
Alternate model idstencent/hunyuan-image-3

Pricing

ChargeSpecRate
Standardper image$0.13

Example request

$curl https://api.empiriolabs.ai/v1/images/generations \
>  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
>  -H 'Content-Type: application/json' \
>  -d '{"model": "hunyuan-image-3", "prompt": "a misty forest at dawn", "size": "1024x1024"}'

Parameters

ParameterTypeRequiredDefaultDescription
promptstringyes-Text prompt.
sizeenumno"1024x1024"Output resolution. Square, portrait, and landscape presets. · Allowed: 1024x1024, 768x1024, 1024x768, 1024x1536, 1536x1024, 512x512
num_imagesnumberno1Number of images to generate. Each is billed separately. · Range: 1 – 4
negative_promptstringno""What to avoid in the output.
num_inference_stepsnumberno28Diffusion steps. More = higher fidelity, slower. · Range: 10 – 50
guidance_scalenumberno7.5Classifier-free guidance. Higher = follows prompt more strictly. · Range: 1.0 – 20.0
seednumberno-Reproducibility seed.
response_formatenumno"url"url (default) returns a signed URL; b64_json returns inline base64. · Allowed: url, b64_json

Notes

Diffusion image model with configurable steps and guidance scale.

Content safety

  • Generated images pass an automated content-safety check. An image flagged as explicit is not returned. Because the image is generated before the check runs, a flagged generation is still billed.

Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/hunyuan-image-3.