Tencent: hy3:free
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: a direct no-think mode by default, plus low and high chain-of-thought modes for complex math, coding, and multi-step problems. With a 256K context window, Hy3 targets long-horizon tasks, including improved coreference resolution, multi-turn constraint tracking, and stable tool-calling that generalizes across agent scaffoldings. Tencent positions it as a reliable, cost-effective option across coding, document processing, financial analysis, game development, and frontend design, with a strong emphasis on grounded, anti-hallucination behavior that answers when grounded and flags when evidence is missing rather than fabricating.
Pricing
Uptime
Performance
Usage & Ranking
Supported parameters
All providers = every upstream serving this model supports it. Some providers = depends on which upstream handles the request. Default = the value sent when you leave the parameter unset.
| Parameter | Providers | Default |
|---|---|---|
| frequency_penalty | All providers | Not sent by default |
| include_reasoning | All providers | - |
| logit_bias | Some providers | - |
| max_completion_tokens | Some providers | - |
| max_tokens | All providers | - |
| min_p | Some providers | - |
| presence_penalty | All providers | Not sent by default |
| reasoning | All providers | - |
| reasoning_effort | All providers | - |
| repetition_penalty | All providers | Not sent by default |
| response_format | Some providers | - |
| seed | All providers | - |
| stop | All providers | - |
| structured_outputs | All providers | - |
| temperature | All providers | 0.9 |
| tool_choice | All providers | - |
| tools | All providers | - |
| top_k | All providers | Not sent by default |
| top_p | All providers | 1 |