Hy3 preview
General purposeToolsTencent · Released April 2026
Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...
Facts and pricing
- Provider
- Tencent
- Context window
- 262K tokens
- Input price
- 2.0 credits / 1M tokens ($0.18 raw)
- Output price
- 6.6 credits / 1M tokens ($0.60 raw)
- Vision (image input)
- No
- Tool calling
- Yes
- Extended reasoning
- No
Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.10x margin. Raw prices shown per 1M tokens.
Try Hy3 now
Hy3 preview is a serving variant of Hy3, so Zeplik offers the Hy3 row and routes your prompt there.
What Hy3 preview is best for
- Balanced everyday work: writing, questions, brainstorming and summarization
- Long documents: the 262K-token window holds lengthy reports, contracts or papers whole
- Tool use and agents: reliably calls functions, so it can search, run skills and drive workflows
Tencent family
| Model | Context | Input cr/M | Output cr/M | Released |
|---|---|---|---|---|
| Hy4 preview | 1.0M | 9.2 | 27.5 | August 2026 |
| Hy-MT2-1.8B | 8K | 0.48 | 1.9 | August 2026 |
| Hy-MT2-30B-A3B | 8K | 0.81 | 3.2 | August 2026 |
| Hy-MT2-7B | 8K | 0.81 | 3.2 | August 2026 |
| Hy3 | 262K | 0.91 | 3.6 | July 2026 |
| Hy3 preview | 262K | 2.0 | 6.6 | April 2026 |
| Hunyuan A13B Instruct | 131K | 1.5 | 6.3 | July 2025 |
Frequently asked questions
- What is Hy3 preview?
- Hy3 preview is an AI model by Tencent. Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...
- How much does Hy3 preview cost on Zeplik?
- Input tokens cost 2.0 credits per million and output tokens 6.6 credits per million (1 credit = $0.10; the raw provider rates are $0.18 and $0.60 per million). New accounts start with free credits.
- How long can a conversation with Hy3 preview be?
- Hy3 preview has a 262K-token context window (262,144 tokens), which covers the conversation plus any documents you attach.
- Does Hy3 preview support images and tools?
- Hy3 preview is text-only and supports tool calling.
Related models
Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...
Hy-MT2-1.8B is a compact 1.8B-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...
Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and...
Hy-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.
Hy3 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. It supports a configurable reasoning effort:...
Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark...
More you can do with Hy3 preview
- 465 AI skillsReady-to-run expert methods for writing, data, code and more, each running on Hy3 preview or any model you pick.
- 997 integrationsConnect Gmail, Slack, GitHub, Notion and hundreds more so the assistant can work in your apps.
- Simple pricingPlus, Pro and Max plans with a monthly credit allowance that works across every model.