Tencent: Hy-MT2-30B-A3B
Tencent's Hy-MT2-30B-A3B is designed for text-based tasks with an impressive context length of 8192 tokens and can generate up to 4096 completion tokens. It does not support tools, reasoning, or structured output, limiting its capabilities to plain text interactions. While this model might be suitable for users requiring a robust text handling capacity at a relatively lower price point-input costs $0.074 per thousand tokens and outputs cost $0.295 per thousand-the lack of benchmark coverage means its performance relative to other models remains unverified. Users who prioritize text-based applications without the need for complex reasoning or structured data processing should consider this model, especially if budget constraints are a factor.
- Model ID
- tencent/hy-mt2-30b-a3b
- Vendor
- tencent
- Released
- August 2026
- Tokenizer
- Other
- Input Modalities
- text
- Output Modalities
- text
- Max Output
- 4,096 tokens
- Tool Calling
- not supported
- Structured Output
- ✓ supported
- Reasoning Mode
- not supported
- Vision
- text only
- Audio
- no
- Moderated
- no
What it costs in practice
Computed from the current $0.07/M input and $0.29/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | under $0.01 |
| Classify 1,000 customer emails | 500k in / 50k out | $0.05 |
| A month of a busy support chatbot | 5M in / 2M out | $0.96 |
Similar models
Quick answers
- How much does Tencent: Hy-MT2-30B-A3B cost?
- $0.07 per million input tokens and $0.29 per million output tokens.
- What is Tencent: Hy-MT2-30B-A3B's context window?
- 8,192 tokens, roughly 12 pages of text in a single request.
- Does Tencent: Hy-MT2-30B-A3B support tool calling?
- It supports structured output.
- Can Tencent: Hy-MT2-30B-A3B process images?
- No, it is text-only on the input side.