Hy3 vs Hy4
Hy3 (Tencent) and Hy4 (Tencent) are listed at different prices. Hy3 costs less: $0.14 per 1M input tokens and $0.58 per 1M output tokens, against $0.417 and $1.251 for Hy4. Hy4 has the larger context window, 1,048,576 tokens against 262,144 for Hy3. Hy3 can write up to 235,929 tokens in one response, against 65,536 for Hy4. Hy3 accepts text and produces text; Hy4 accepts text and images and produces text.
Tencent: Hy3 accepts text and produces text, with a 262,144-token context and up to 128,000 output tokens. Tencent: Hy4 accepts text and images and produces text, with a 1,048,576-token context and up to 65,536 output tokens; both support tools, structured outputs, response formats, and reasoning.
Compared from catalog data checked
Side by side
0.00 the better figure in a row| Specification | Hy3 | Hy4 |
|---|---|---|
| Maker | Tencent | Tencent |
| Added to catalog | 6 Jul 2026 | 4 Nov 2026 |
| Input, per 1M tokens | $0.14 | $0.417 |
| Output, per 1M tokens | $0.58 | $1.251 |
| Cached input read, per 1M | $0.035 | $0.021 |
| Context windowTokens | 262,144 | 1,048,576 |
| Max outputTokens | 235,929 | 65,536 |
| Accepts | text | image, text |
| Produces | text | text |
| Tool calling | Yes | Yes |
| Structured outputs | Yes | Yes |
| Reasoning effort control | Yes | Yes |
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 | Hy3 | Hy4 |
|---|---|---|
| Answer a short question500 in / 300 out | $0.0002 | $0.0006 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0040 | $0.011 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0054 | $0.015 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.022 | $0.064 |
Which to choose
Choose Hy3 if
- Input tokens cost less: $0.14 against $0.417 per 1M
- Output tokens cost less: $0.58 against $1.251 per 1M
- You need longer answers in one response: 235,929 tokens against 65,536
Choose Hy4 if
- Cached input costs less: $0.021 against $0.035 per 1M
- You need the larger context window: 1,048,576 tokens against 262,144
- It has to read images, which the other model does not
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.