Tencent
Hy3
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.
At a glance
- Input / 1M
- $0.08
- Output / 1M
- $0.33
- Context
- 262K
- Max output
- 128K
- Intelligence
- 25.3
- Released
- Jul 2026
Pricing
Hy3 API pricing
Per-token rates, plus what common tasks actually cost.
| Input tokensPer 1M tokens | $0.08 |
|---|---|
| Output tokensPer 1M tokens | $0.33 |
| Cached input (read)Per 1M tokens | $0.02 |
| Cache writePer 1M tokens | Not available |
Chat message
2K in, 500 out
$0.33
per 1,000 requests
Coding task
30K in, 4K out
$3.80
per 1,000 requests
Long document summary
150K in, 2K out
$13.04
per 1,000 requests
Benchmarks
Hy3 benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
25.3
Coding index
58.8
Agentic index
24.1
Specs
Context window and capabilities
What it can read, what it can write, and which API features it supports.
- Context window
- 262K tokens
- Max output
- 128K tokens
- Input types
- Text
- Output types
- Text
- Reasoning effort
- High, Low, None
- Release date
- July 6, 2026
- Tool calling
- Structured outputs
- JSON mode
- Reasoning
- Temperature
- Stop sequences
- Deterministic seed
- Verbosity control
Compare
Hy3 vs other models
See how Hy3 stacks up head to head on price, benchmarks, and features.
Hy3 vs DeepSeek V4.1 Flash
Tencent vs DeepSeek
See comparisonHy3 vs GLM 5.3 Flash
Tencent vs Z.ai
See comparisonHy3 vs MiMo-V2.6-Flash
Tencent vs Xiaomi
See comparisonHy3 vs Hy4 preview
Tencent vs Tencent
See comparison
Hy3 vs GPT-6 Luna
Tencent vs OpenAI
See comparisonHy3 vs DeepSeek V4 Flash 0731
Tencent vs DeepSeek
See comparisonMore Hy3 comparisons
- Hy3 vs Claude Opus 5.5
- Hy3 vs GLM 5.3
- Hy3 vs DeepSeek V4 Flash 0423
- Hy3 vs Step 5 Preview
- Hy3 vs Gemini 3.8 Flash
- Hy3 vs Muse Spark 1.3 Contributor
- Hy3 vs MiniMax M3
- Hy3 vs Solar Mini 4
- Hy3 vs MiMo-V2.5
- Hy3 vs DeepSeek V4 Pro 0423
- Hy3 vs Solar Pro 4
- Hy3 vs GPT-6 Luna Pro
- Hy3 vs Qwen3.8 Flash
- Hy3 vs Qwen3.7 Flash
- Hy3 vs Gemma 4 26B A4B
- Hy3 vs DeepSeek V3.2
- Hy3 vs MiMo-V2.5-Pro
- Hy3 vs Ling 3.0 Flash
- Hy3 vs Qwen3.7 Plus
- Hy3 vs MiniMax M2.7
- Hy3 vs Ling 3.0 Flash VL
- Hy3 vs Inkling Small
- Hy3 vs MiniMax M2.5
- Hy3 vs Ling 3.0 Flash Fin
- Hy3 vs Step 3.5 Flash
Alternatives
Hy3 alternatives
Similar models worth considering, and where each one has the edge.
DeepSeek
DeepSeek V4 Pro 0423
MiniMax
MiniMax M3
Upstage
Solar Pro 4
Want to learn about other models? Browse all models
FAQ
Frequently asked questions
How much does Hy3 cost?
Hy3 costs $0.08 per 1M input tokens and $0.33 per 1M output tokens through the API. A typical chat message costs about $0.33 per 1,000 messages.
What is the context window of Hy3?
Hy3 accepts up to 262K tokens of input and can write up to 128K tokens in a single response.
What is the best alternative to Hy3?
DeepSeek V4 Pro 0423 from DeepSeek is a strong alternative. It offers: higher intelligence score, larger 1.05m context.
Can I use Hy3 alongside other models?
Yes. Shortcut Chat sends one prompt to Hy3 and any other models you pick at the same time, so you can compare answers side by side.
Try Hy3 next to every other model.
Use Hy3 alongside all the other models. Use one at a time, or multiple together. Get the best answer from every AI.