Hunyuan Image 3.0 is Tencent’s native multimodal model for unified multimodal understanding and generation within an autoregressive framework. Its Mixture of Experts (MoE) architecture, the largest among open-source image generation models, has 80 billion parameters and 64 experts, and it produces photorealistic images that follow the prompt closely. It reasons with world knowledge to enrich sparse prompts with relevant details automatically, and scores well on text-to-image and integrated multimodal benchmarks.
$0.016
Share of requests served without a server error. Client errors (4xx) do not count.
Works with the OpenAI SDK pointed at our base URL. Every parameter is in the .
Images generated per day on NagaAI, counted since November 2026.
Hunyuan Image 3.0 is Tencent’s native multimodal model for unified multimodal understanding and generation within an autoregressive framework.
On NagaAI, Hunyuan Image 3 costs about $0.016 per image. You pay only for what you use, with no subscription.
It takes text as input and returns images.
Create an API key, copy the model ID from the top of this page and send requests with the OpenAI SDK pointed at NagaAI. The API section on this page has a ready example.
Not enough activity data to display a chart
