A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.
Hy4 preview by tencent is offered by 17 providers on this page. Its official list price is $0.834 per 1M input tokens and $2.50 per 1M output tokens. The lowest paid channel is Vancine at $0.67 / $2.00 per 1M, about 1.4× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.
The context window is 1,024,000 tokens at the reference host, but hosts report different limits, from 1,000,000 to 1,048,576, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Vancine | Gateway | $0.67 | $2.00 | $0.034 | — | 1,024,000 | 64,000 | |
| Deep Infra tencent/Hy4-preview | Cloud | $0.83 | $2.50 | $0.042 | — | 1,048,576 ⚠ | 64,000 | |
| NanoGPT | Gateway | $0.83 | $2.50 | $0.042 | — | 1,048,576 ⚠ | 64,000 | |
| LLM Gateway | Gateway | $0.83 | $2.50 | $0.042 | — | 1,000,000 ⚠ | 65,536 | |
| Kilo Gateway | Gateway | $0.83 | $2.50 | $0.042 | — | 1,048,576 ⚠ | 64,000 | |
| Novita AI | Gateway | $0.83 | $2.50 | $0.042 | — | 1,000,000 ⚠ | 64,000 | |
| OpenRouter | Gateway | $0.83 | $2.50 | $0.042 | — | 1,048,576 ⚠ | 64,000 | |
| Hugging Face tencent/Hy4-preview | Cloud | $0.83 | $2.50 | — | — | 1,000,000 ⚠ | 64,000 | |
| Tencent TokenHubOfficial | First-party | $0.83 | $2.50 | $0.042 | — | 1,024,000 | 64,000 | |
| Vercel AI Gateway | Cloud | $0.83 | $2.50 | $0.042 | — | 1,024,000 | 64,000 | |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Interleaved thinking (reasoning between tool calls) is declared by 2 of 17 providers.