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: 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.
tencent/hy3
- Context
- 262k tokens
- Completion cap
- 128,000
- Tools
- Yes
- JSON
- Yes
- Released
- 2026-07-06
Call it from Geek Hub
Same OpenAI SDK. Change the base URL and the model id.
curl https://api.geekhub.mx/v1/chat/completions \
-H "Authorization: Bearer $GEEKHUB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "tencent/hy3",
"messages": [{"role": "user", "content": "Hola"}]
}'Get an API keyFrequently asked questions
- What is 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: 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. Hy3 runs on the Geek Hub API (OpenAI-compatible). Model id: tencent/hy3.
- Is Hy3 free?
- No. Input is $0.1439 per 1M tokens and output is $0.5756 per 1M tokens on Geek Hub (markup included).
- What is the context length of Hy3?
- Hy3 has a 262k tokens context window. It supports up to 128,000 completion tokens.
- Does Hy3 support tool calling and structured outputs?
- Hy3 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
- When was Hy3 released?
- Hy3 was released on 2026-07-06.
More models from Tencent
- Hunyuan A13B InstructHunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thou
- Hy-MT2-1.8BHy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for struc
- Hy-MT2-30B-A3BHy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for
- Hy-MT2-7BHy-MT2-7B is a 7B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delim
- Hy3 previewHy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled,