Hy-MT2-30B-A3B
General purposeTencent · Released August 2026
Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family.
It belongs to Tencent's Hunyuan family, where the Hy line covers general chat and the Hy-MT models specialise in translation.
Facts and pricing
- Provider
- Tencent
- Context window
- 8K tokens
- Input price
- 0.89 credits / 1M tokens ($0.074 raw)
- Output price
- 3.5 credits / 1M tokens ($0.29 raw)
- Vision (image input)
- No
- Tool calling
- No
- Extended reasoning
- No
Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.20x margin. Raw prices shown per 1M tokens.
Try Hy-MT2-30B-A3B now
What Hy-MT2-30B-A3B is best for
- Balanced everyday work: writing, questions, brainstorming and summarization
Example prompts
Prompts that suit a general purpose model like Hy-MT2-30B-A3B:
- Help me outline a talk about what I learned this year
- Compare these two paragraphs and tell me which is clearer and why
- Draft a polite reply declining this invitation
- Explain this concept with a concrete everyday analogy
Tencent family
| Model | Context | Input cr/M | Output cr/M | Released |
|---|---|---|---|---|
| Hy4 | 1.0M | 5.0 | 15.0 | November 2026 |
| Hy4 preview | 1.0M | 9.0 | 27.0 | August 2026 |
| Hy-MT2-1.8B | 8K | 0.53 | 2.1 | August 2026 |
| Hy-MT2-30B-A3B | 8K | 0.89 | 3.5 | August 2026 |
| Hy-MT2-7B | 8K | 0.89 | 3.5 | August 2026 |
| Hy3 | 262K | 0.99 | 4.0 | July 2026 |
| Hy3 preview | 262K | 2.2 | 7.2 | April 2026 |
| Hunyuan A13B Instruct | 131K | 1.7 | 6.8 | July 2025 |
Model comparisons
- Claude Opus 5.5 vs Claude Opus 5
- Claude Opus 5.5 vs GPT-6 Astra
- Claude Opus 5.5 vs GPT-6 Sol
- Claude Opus 5.5 vs Claude Sonnet 5
Frequently asked questions
- What is Hy-MT2-30B-A3B?
- Hy-MT2-30B-A3B is an AI model by Tencent. Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family.
- How much does Hy-MT2-30B-A3B cost on Zeplik?
- Input tokens cost 0.89 credits per million and output tokens 3.5 credits per million (1 credit = $0.10; the raw provider rates are $0.074 and $0.29 per million). New accounts start with free credits.
- How long can a conversation with Hy-MT2-30B-A3B be?
- Hy-MT2-30B-A3B has a 8K-token context window (8,192 tokens), which covers the conversation plus any documents you attach.
- Does Hy-MT2-30B-A3B support images and tools?
- Hy-MT2-30B-A3B is text-only and does not support tool calling.
Related models
Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total.
Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent.
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.
Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use.
More you can do with Hy-MT2-30B-A3B
- 468 AI skillsReady-to-run expert methods for writing, data, code and more, each running on Hy-MT2-30B-A3B 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.