Understand this story
Tencent Hunyuan announced that Hy4 flash is now available on OpenRouter. It is a faster and cheaper version of Hy4, retaining a 1M context window and image input, and supporting optional reasoning; the company says it is suitable for agents, coding, and high-concurrency workloads. A 50% discount runs until November 30, at $0.035 per million input tokens and $0.14 per million output tokens. Previously, the Tencent Hunyuan team released Hy4 flash on November 16, with 224B total parameters (including 64B Engram parameters), 12B activated per token, support for multimodal input and a 1 million token context; the company says that on the WorkIndex benchmark set, the cost per task is 1/13 that of Hy4 preview and 1/20 that of Hy4, with decoding speed exceeding 150 tps, and it has already launched in products including Tencent Cloud TokenHub, WorkBuddy, and Yuanbao, with plans to open-source it.
AI-generated from public reports
Latest development · Report
Tencent Hunyuan Hy4 flash launches on OpenRouter, supporting 1M context and image inputDevelopments
2 confirmed developments
- Source:OpenRouter
- Source:IT Home · AI
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Nov 17
OpenRouterFirst-party
Tencent Hunyuan Hy4 flash launches on OpenRouter, supporting 1M context and image input
Tencent Hunyuan Hy4 flash is now live on OpenRouter. It is a faster, cheaper version of Hy4 that retains 1M context and image input. The model supports optional reasoning and is officially described as suitable for agents, coding, and high-concurrency workloads. There is a 50% discount until November 30: $0.035/M input, $0.14/M output.
IT Home · Artificial IntelligenceSelected
Tencent Hunyuan releases the Hy4 flash model: 224B total parameters, 12B activated, with a per-task cost about 5% of Hy4
The Tencent Hunyuan team has released Hy4 flash, with 224B total parameters (including 64B Engram parameters), 12B activated per token, and support for multimodal input and a 1 million token context. According to the official statement, on the WorkIndex evaluation set its per-task cost is 1/13 that of Hy4 preview and 1/20 that of Hy4, with decoding speed exceeding 150 tps. The model has already launched on products including Tencent Cloud TokenHub, WorkBuddy, and Yuanbao, and is planned to be open-sourced.
IT Home · AIRelated discussion
IT Home · AI joined this discussion
This post contributes to heat; it is not a formal report or confirmed fact.
Tencent HunyuanFirst-party
Tencent Hunyuan Hy4 flash launches on OpenRouter
Tencent Hunyuan announced that Hy4 flash is now available on OpenRouter at a limited-time 50% discount. Pricing is $0.035 per 1M input tokens, $0.1405 per 1M output tokens, and $0.0015 per 1M cached-read tokens; the company says it is suited for high-concurrency batch tasks.