by Tencent· 5 months ago
World's largest open-source text-to-image model using MoE architecture with 64 experts.
Input Price
$0.03/M tokens
Output Price
$0.03/M tokens
Performance Profile
Top-tier image generation with photorealistic output and precise prompt adherence
Precise control over composition, style, and content through natural language prompts
Open weights — run locally, fine-tune on your own data, no API rate limits
80B total / 13B active parameter architecture for high-fidelity generation
vs similar-tier models
| Model | Input | Output | Context | Avg Score |
|---|---|---|---|---|
Hunyuan Image 3.0Current Tencent | $0.03 | $0.03 | N/A | 0.0 |
GPT-4o OpenAI | $2.50 | $10.00 | 128K | 81.1 |
Kimi K2.5 Moonshot AI | $0.45 | $2.20 | 256K | 92.3 |
Generate a single image
<$0.001Text prompt → 1024×1024 image
100 in · 1,000 out
Batch of 10 product images
<$0.001E-commerce product shots in different styles
1,000 in · 10,000 out
50 social media images
$0.0016A week's worth of branded social content
5,000 in · 50,000 out
100 marketing variations
$0.0033A/B test visuals for ad campaigns
10,000 in · 100,000 out
Product images
$0.99/mo
$0.03/day
Social media posts
$2/mo
$0.07/day
Marketing campaigns
$5/mo
$0.17/day
No ratings yet. Be the first to rate this model!
Sign in to rate this model and share your experience.
Sign in to leave a comment and join the discussion.
Tencent
Tencent's open-source video generation model with 8.3 billion parameters, featuring a novel Spatial-Temporal Self-Attention (SSTA) mechanism for improved temporal coherence. HunyuanVideo 1.5 supports diverse aspect ratios, variable frame rates, and extended clip durations, making it a versatile foundation model for the open-source video generation community.
Input
Free/M
Output
Free/M
Tencent
One of the largest open-source MoE models. Supports text sequences up to 256K tokens.
Input
$0.50/M
Output
$1.50/M
Context
256K
OpenAI
OpenAI's most advanced multimodal model. Excels at text, vision, and audio tasks with fast response times.
Input
$2.50/M
Output
$10.00/M
Context
128K
Moonshot AI
Moonshot AI's frontier multimodal MoE model with 1T total parameters (32B active). Tops SWE-bench and AIME 2025 benchmarks.
Input
$0.45/M
Output
$2.20/M
Context
256K
Google's most capable thinking model with breakthrough performance on reasoning and coding.
Input
$1.25/M
Output
$10.00/M
Context
1.0M