TTencent · Released Jul 6, 2026
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:...
- Released
- Jul 6 2026
- Context window
- 262K 128K out
- Input / 1M tokens
- $0.13 from Free
- Output / 1M tokens
- $0.53 from Free
Where to run it
27 providers compared
Free to try on Tencent TokenHub, OrcaRouter, OpenCode, Kenari — free endpoints are often limited-time and rate-limited. Included in Tencent Token Plan, OpenCode Go. Cheapest: NanoGPT at $0.066 / $0.26 per 1M input / output tokens — 76% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| Tencent TokenHubfree · may be limited-time | Free | Free | Free | 256K | 128K | — | Free |
| OrcaRouterfree · may be limited-time | Free | Free | — | 256K | 128K | — | Free |
| OpenCodefree · may be limited-time | Free | Free | Free | 190K | 64K | — | Free |
| Kenarifree · may be limited-time | Free | Free | — | 256K | 128K | — | Free |
| Tencent Token Plansubscription plan | Plan | Plan | Plan | 256K | 128K | — | Plan |
| OpenCode Gosubscription plan | Plan | Plan | Plan | 256K | 128K | — | Plan |
| NanoGPT | $0.066 | $0.26 | $0.029 | 262K | 128K | — | Cheapest |
| Deep Infra | $0.13 | $0.53 | $0.033 | 262K | 128K | — | +101% |
| TencentFP8 | $0.13 | $0.53 | $0.033 | 262K | 128K | 100%24h | +102% |
| Kilo Gateway | $0.13 | $0.53 | $0.033 | 262K | 128K | — | +102% |
| SiliconFlow | $0.13 | $0.53 | $0.033 | 262K | 262K | — | +102% |
| DevPass (LLM Gateway) | $0.13 | $0.53 | $0.033 | 262K | 128K | — | +102% |
| Eden AI | $0.13 | $0.53 | $0.033 | 256K | 128K | — | +102% |
| Novita | $0.14 | $0.58 | $0.035 | 262K | 236K | 100%24h | +118% |
| GMICloudBF16 | $0.14 | $0.58 | $0.035 | 262K | 236K | 99.9%24h | +118% |
| Vercel AI Gateway | $0.14 | $0.58 | $0.035 | 262K | 262K | — | +118% |
| LLM Gateway | $0.14 | $0.58 | $0.035 | 262K | 262K | — | +118% |
| Requesty | $0.14 | $0.58 | $0.035 | 262K | 262K | — | +118% |
| Jalapeno Cloud | $0.14 | $0.58 | — | 203K | 128K | — | +118% |
| Novita AI | $0.14 | $0.58 | $0.035 | 262K | 262K | — | +118% |
| Hugging Face | $0.14 | $0.58 | — | 262K | 128K | — | +118% |
| CommandCode | $0.14 | $0.58 | $0.035 | 256K | 128K | — | +118% |
| Phala | $0.15 | $0.64 | $0.04 | 262K | 236K | 100%24h | +138% |
| Kenari | $0.15 | $0.63 | $0.015 | 256K | 128K | — | +138% |
| AIHubMix | $0.16 | $0.63 | $0.039 | 256K | 128K | — | +139% |
| CrossModel | $0.16 | $0.64 | $0.04 | 262K | 131K | — | +145% |
| OrcaRouter | $0.18 | $0.59 | $0.059 | 256K | 128K | — | +147% |
| AtlasCloudFP8 | $0.20 | $0.80 | $0.05 | 262K | 131K | 100%24h | +206% |
| AI/ML API | $0.28 | $1.10 | $0.069 | 262K | 131K | — | +320% |
Benchmarks
Benchmark scores
No benchmark scores yet — Epoch AI hasn't evaluated Hy3. Scores appear here automatically once it does.
Specs
Details
- Model ID
tencent/hy3- Developer
- Tencent
- Release date
- Jul 6, 2026 ·
- Context window
- 262,144 tokens
- Max output
- 128,000 tokens
- API price
- $0.13 / $0.53 per 1M input / output tokens
- Providers
- 27
- Input types
- text
- Reasoning
- Yes
- Tool calling
- Yes
- Open weights
- Yes
- Free tier
- No
Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.