Tencent Hunyuan API
Tencent Hunyuan, or Tencent HY, is Tencent's self-developed large-model family covering text, image, video and 3D for content production, knowledge Q&A and business automation. On Felo, the Tencent entry currently exposes Hy4, Tencent's flagship open-weight model, callable with a Felo API key and one balance.
- Models
- 4
- chat ×2 · image ×2
- Input per 1M
- $0.07–$0.417
- Output per 1M
- $0.281–$1.251
- Largest context
- 1.049M
What Tencent Hunyuan provides
Tencent describes Hunyuan as a common and multimodal large-model house fully developed in-house, covering text, image, video and 3D. It is positioned for content production, knowledge Q&A, business automation and similar enterprise scenarios, and is offered as an enterprise-grade service.
Developers reach the models through Tencent Cloud, including the international TokenHub API platform, alongside supporting tools and APIs for the wider Hunyuan family.
Tencent models on Felo
Felo currently lists one Tencent model, Hy4, Tencent's flagship open-weight model with a long context window and two reasoning modes. The table on this page is generated from the live catalog and is the authoritative list.
Access and pricing
Hy4 is published as open weights under Apache 2.0 and is served through Tencent Cloud's international TokenHub with the API model ID hy4-preview; checkpoints are also published on Hugging Face, ModelScope, GitCode and CNB. On Felo, Hy4 is billed per token at $0.417 per 1M input tokens and $1.251 per 1M output tokens, with cache reads at $0.021, deducted from your Felo balance.
Why use Tencent Hunyuan through Felo
One Felo key covers Tencent Hunyuan and the other providers in the catalog, so a Hy4 workflow can sit beside text, image or video models from other vendors on the same balance. No separate Tencent Cloud account is needed, and the model page lists the current price, context window and capabilities.
Who Tencent Hunyuan is for
Hy4 is positioned for real productivity work: software engineering, office and document generation, game prototyping and scientific research, with long-context enterprise tasks in mind. Felo lists only this text model from Tencent, so teams that need Hunyuan image, video or 3D models should use Tencent Cloud directly.
- Input per 1M
- $0.07
- Output per 1M
- $0.281
- Context
- 1.049M
- Max output
- 65.536K
- Input per 1M
- Not published
- Output per 1M
- Not published
- Context
- —
- Max output
- —
- Input per 1M
- $0.417
- Output per 1M
- $1.251
- Context
- 1.049M
- Max output
- 65.536K
- Input per 1M
- Not published
- Output per 1M
- Not published
- Context
- —
- Max output
- —
| Model | Input per 1M | Output per 1M | Context | Max output |
|---|---|---|---|---|
| $0.07 | $0.281 | 1.049M | 65.536K | |
| Not published | Not published | — | — | |
| $0.417 | $1.251 | 1.049M | 65.536K | |
| Not published | Not published | — | — |
Prices are published standard rates in USD per 1M tokens, before channel discounts.
Frequently asked questions
- What is Tencent Hunyuan?
- Tencent Hunyuan, or Tencent HY, is Tencent's self-developed large-model family covering text, image, video and 3D. It targets content production, knowledge Q&A and business automation, and is available through Tencent Cloud.
- Which Tencent models can I call through Felo?
- Felo currently lists one Tencent model, Hy4, Tencent's flagship open-weight reasoning model. The live model table on this page is authoritative.
- Do I need a Tencent Cloud account?
- No. Hy4 on this page is called with a Felo API key and paid from your Felo balance, so no separate Tencent Cloud account is required.
- How is Tencent Hunyuan billed on Felo?
- Hy4 is billed per token: $0.417 per 1M input tokens and $1.251 per 1M output tokens, with cache reads at $0.021. Each model page shows the current rate.
- What is Hy4 best for?
- Software engineering, office and document generation, game prototypes and scientific research, especially long-context productivity work. Teams that need Tencent image, video or 3D models should use Tencent Cloud directly.