Skip to content

Tencent · Image

Hunyuan Image V3

Tencent 🇨🇳ImageHunyuanImage family
From Empiriolabs's listing:
Open-source text-to-image model on a multimodal Mixture-of-Experts architecture with photorealistic detail and strong multilingual text rendering.
llminfo IQ
89.2
Market median price
$0.10 /image
Listings
8
Providers
7

Evidence and sources

🤗 tencent/HunyuanImage-3.0llminfo IQ 89.2, ranked among image generation models. From 42 benchmarks. A fair amount of data behind it.How llminfo IQ is computedReleased 28 Sep 2025Maker HQ: CN (according to Tencent's own website)
Sources: LMArena data, AI/ML API data, EmpirioLabs data, llminfo researchPrimary data from LMArena from AI/ML API: name from EmpirioLabs: primary mode, description from llminfo research: release date

Advantages and trade-offs

Compared with 10 image generation models, picked mainly by popularity and IQ
We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 3 maker's prices; 8 market median prices.

Input & output

as stated by the model's providers
Text
Images

Listings

 NanoGPThunyuan-image-3Source: NanoGPTNot published by the provider$0.10
 Replicatetencent/hunyuan-image-3Sources: LiteLLM data, Replicate data docsNot published by the provider$0.08
 Empiriolabshunyuan-image-3Source: EmpirioLabs dataNot published by the provider$0.13
 fal.aifal-ai/hunyuan-image/v3/text-to-image · text-to-imageSources: Fal.ai data, LiteLLM dataNot published by the provider$0.10
 Venicehunyuan-image-v3Source: Venice.ai dataNot published by the provider$0.09

3 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Image generation

Arena ELO Text to ImageSource: LMArena data · Nov 2026
GenExam22 related benchmarks · 22 results
WISE VerifiedSource: WISE data

Human preference

Data credits: LMArena, CC BY 4.0 (licence) · GenExam (OpenGVLab), MIT (licence)

Also known as: fal-ai/hunyuan-image/v3/text-to-image, hunyuan image 3.0, hunyuan-image-3, hunyuan-image-3.0, hunyuan-image-v3, hunyuan-image-v3-text-to-image, hunyuan-image/v3/text-to-image, hunyuan/hunyuan-image-v3-text-to-image, hunyuanimage-3.0, replicate/tencent/hunyuan-image-3, tencent/hunyuan-image-3

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works