Hy3
Tencent · 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. It supports a configurable reasoning effort:...
Hy3 ranks #121 of 359 models in the default AI Benchmark Hub order (quality first, then cost). At $0.33 blended per million tokens, it is cheaper than 75% of models with published API pricing. Its 262,144-token context window is about the catalog median (262,144 tokens).
open weightstexttext->text
Context
Max context: 262144
Max output: 128000
Max output: 128000
Pricing
Input / 1M: 0.13
Output / 1M: 0.53
Blend / 1M: 0.33
Output / 1M: 0.53
Blend / 1M: 0.33
Quality
Quality index: —
Provider
Provider: Tencent
Moderated: no
Moderated: no
Monthly cost at this blended rate
Estimated API spend if every token is billed at $0.33per million (the blend of this model's input and output prices). Real bills depend on the input/output mix.
| Tokens / month | Est. cost (USD) |
|---|---|
| 1,000,000 | $0.33 |
| 10,000,000 | $3.30 |
| 100,000,000 | $33.00 |
Related models
Same lab, similar price, or similar quality — useful next comparisons.
More from Tencent
- Hy-MT2-1.8B$0.11 / 1M
- Hy-MT2-30B-A3B$0.18 / 1M
- Hy-MT2-7B$0.18 / 1M
- Hunyuan A13B Instruct$0.36 / 1M
- Hy3 preview$0.39 / 1M
Closest API price
- DeepSeek V3.2$0.33 / 1M
- DeepSeek Flash Latest$0.33 / 1M
- Qwen3 VL 30B A3B Instruct$0.33 / 1M
- DeepSeek V3.2 Exp$0.34 / 1M
- Qwen3.8 Flash$0.31 / 1M