Tencent
Chat with Tencent HY3 online
Tencent's 295B mixture of experts — frontier-class reasoning, small-model economics.
262.144K tokens
Contexto
128,000 tokens
Saída máxima
Rápido
Velocidade
Para o que você vai usar
Technical reasoning
Hard analysis at a cost that suits everyday use.
Coding help
Read, explain and rewrite code across a large context.
Bilingual work
Strong in English and Chinese in the same thread.
High-volume chat
Efficient inference makes long sessions practical.
Prompts to steal
Tuned to this model — click any line to copy.
Sobre o HY3
HY3 is Tencent's mixture-of-experts model, released in July 2026 and built for reasoning, agentic workflows and the kind of production traffic where cost per request matters as much as quality. On NinjaChat it is included in every plan, next to models from OpenAI, Anthropic, Google and Z.ai.
The architecture is the story. HY3 has 295 billion parameters in total but activates only about 21 billion for any given token, routing each one through the best 8 of 192 experts. That is why a model of its size can be served at a price closer to a small one, and it is the same design idea that made DeepSeek's V4 line competitive on cost.
It also exposes a configurable reasoning effort, so the model can think briefly on an easy turn and at length on a hard one rather than spending the same budget on everything. It handles about 262K tokens of context and is strong in both English and Chinese.
One honest limitation on NinjaChat: HY3 runs here without tool calling. Different hosts return tool arguments in inconsistent shapes for this model, so rather than ship something that breaks mid-agent-loop, it is served for reading, reasoning and writing. When a task needs function calls, GLM 5.3 and Kimi K3 sit in the same picker.
Como usar o HY3
Do zero ao seu primeiro resultado em menos de um minuto.
01
Create a NinjaChat account and choose a plan
02
Open chat and pick HY3 from the model list
03
Give it the full problem; it has room for 262K tokens
04
Ask it to think longer on the turns that deserve it
05
Switch to GLM 5.3 or Kimi K3 when the task needs tool calls
Dicas para resultados melhores
- Use it for reading, reasoning and writing rather than tool-driven agents
- Paste long documents directly
- Ask in Chinese or English; it handles both
- Say when a question is easy so it does not overthink
HY3 vs as alternativas
Comparações honestas — onde o {model} vence e onde não vence.
vs DeepSeek V4 Flash
Ver modeloConfigurable reasoning effort and strong bilingual work
DeepSeek V4 Flash has a larger context and tool calling
vs GLM 5.3
Ver modeloCheaper per message for everyday reasoning
GLM 5.3 is far stronger on hard engineering and supports tools
vs MiniMax M3
Ver modeloBetter suited to focused reasoning tasks
MiniMax M3 reads images and video and writes much longer answers
Perguntas frequentes
Além do chat — imagens e vídeo
Todo plano NinjaChat inclui 50+ modelos, um estúdio completo de imagens e geração de vídeo.
HY3, e mais 50.
Uma única assinatura cobre todos os modelos do NinjaChat, incluindo HY3.
