Hy-MT2-1.8B vs Hy4 flash
Hy-MT2-1.8B (Tencent) and Hy4 flash (Tencent) are listed at different prices. Hy4 flash costs less: $0.035 per 1M input tokens and $0.141 per 1M output tokens, against $0.044 and $0.177 for Hy-MT2-1.8B. Hy4 flash has the larger context window, 1,048,576 tokens against 8,192 for Hy-MT2-1.8B. Only Hy4 flash supports tool calling. Hy-MT2-1.8B accepts text and produces text; Hy4 flash accepts text and images and produces text.
Tencent: Hy-MT2-1.8B is a text-in, text-out translation model described as supporting 33 language pairs and five Chinese dialect and minority-language pairs, with an 8,192-token context. Tencent: Hy4 flash accepts text and images, produces text, supports tools, structured outputs, response formats, and reasoning, and has a 1,048,576-token context.
Compared from catalog data checked
Side by side
0.00 the better figure in a row| Specification | Hy-MT2-1.8B | Hy4 flash |
|---|---|---|
| Maker | Tencent | Tencent |
| Added to catalog | 20 Aug 2026 | 16 Nov 2026 |
| Input, per 1M tokens | $0.044 | $0.035 |
| Output, per 1M tokens | $0.177 | $0.141 |
| Cached input read, per 1M | n/a | $0.0015 |
| Context windowTokens | 8,192 | 1,048,576 |
| Max outputTokens | 4,096 | 65,536 |
| Accepts | text | image, text |
| Produces | text | text |
| Tool calling | No | Yes |
| Structured outputs | No | Yes |
| Reasoning effort control | No | No |
List prices through OpenRouter, in US dollars. Each model's page has its variants, price history and sample outputs.
What the same task costs
List price for one request, from the token counts shown. The same four tasks are priced on every model page.
| Task | Hy-MT2-1.8B | Hy4 flash |
|---|---|---|
| Answer a short question500 in / 300 out | $0.0001 | $0.0001 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0012 | $0.0010 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0017 | $0.0013 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.0069 | $0.0055 |
Which to choose
Choose Hy-MT2-1.8B if
No row of the table favours Hy-MT2-1.8B. The difference, if there is one, is in the answers it writes: try it on your own task.
Hy-MT2-1.8B detailsChoose Hy4 flash if
- Input tokens cost less: $0.035 against $0.044 per 1M
- Output tokens cost less: $0.141 against $0.177 per 1M
- Cached input costs less: $0.0015 against n/a per 1M
- You need the larger context window: 1,048,576 tokens against 8,192
- You need longer answers in one response: 65,536 tokens against 4,096
- It has to read images, which the other model does not
- You need tool calling
- You need answers in a fixed JSON schema
Neither maker's quality claims are repeated here. The reliable test is your own task: ask both the same question and read the two answers.