Models
One name per model, however many providers serve it.
Tencent: Hy4 flash
Accepts- Text
- Image
Creates- Text
ToolsJSONReasoningHy4 flash is a cost-efficient variant of Hy4 from Tencent, served with roughly a quarter of the flagship's parameter count for lower latency and cost.
tencent/hy4-flashNov 16, 20261M context13,664 Toman/M input tokens51,240 Toman/M output tokensTencent: HY-World 2.1 Panorama
Accepts- Text
Creates- Image
HY-World 2.1 Panorama is a 360-degree panorama generation model from Tencent, part of the Hunyuan World family.
tencent/hy-world-2.1-panoramaNov 13, 20264K context750 Toman to 3,633 Toman an imageTencent: Hy4
Accepts- Text
- Image
Creates- Text
ToolsJSONReasoningThe official release of Hy4 delivers comprehensive and substantial improvements over Hy4 Preview, with particularly strong gains in agentic capabilities and performance across a wide range of long-horizon, real-world productivity…
tencent/hy4Nov 4, 20261M context150,304 Toman/M input tokens450,912 Toman/M output tokensTencent: Hy Image 3.5 Preview
Accepts- Text
- Image
Creates- Image
Hy Image 3.5 Preview is a unified image generation and editing model from Tencent.
tencent/hy-image-v3.5-previewOct 5, 2026100K contextEdits pictures750 Toman to 3,633 Toman an imageTencent: Hy4 preview
Accepts- Text
Creates- Text
ToolsJSONReasoningTencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total.
tencent/hy4-previewAug 28, 20261M context300,608 Toman/M input tokens901,824 Toman/M output tokensTencent: Hy-MT2-1.8B
Accepts- Text
Creates- Text
Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent.
tencent/hy-mt2-1.8bAug 20, 20268K context17,080 Toman/M input tokens64,904 Toman/M output tokensTencent: Hy-MT2-30B-A3B
Accepts- Text
Creates- Text
JSONHy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family.
tencent/hy-mt2-30b-a3bAug 20, 20268K context27,328 Toman/M input tokens109,312 Toman/M output tokensTencent: Hy-MT2-7B
Accepts- Text
Creates- Text
JSONHy-MT2-7B is a 7B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation.
tencent/hy-mt2-7bAug 19, 20268K context27,328 Toman/M input tokens109,312 Toman/M output tokensTencent: Hy3
Accepts- Text
Creates- Text
ToolsJSONReasoningHy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use.
tencent/hy3Jul 6, 2026262K context51,240 Toman/M input tokens211,792 Toman/M output tokens
9 of 581 models · Catalog updated 3 hours ago. · Free plan prices, in Toman at today's rate. Plans and prices

