{"slug": "new-model-available-tencent-hy4-flash", "title": "New Model Available: Tencent: Hy4 Flash", "summary": "Tencent released Hy4 Flash, a text generation model built for efficient conversational and instruction-following tasks, with support for long-context processing, streaming and tool use. The model is listed at $0.056 per million input tokens and $0.2248 per million output tokens, with read pricing of $0.0024 per million tokens, 1.05M context, 1.28s latency and 108 tokens per second throughput on the AI Gateway. Tencent positions Hy4 Flash for chat assistants, workflow automation and general-purpose text generation.", "body_md": "Hy4 Flash is a text generation model from Tencent designed for efficient conversational and instruction-following tasks. It supports long-context processing, streaming, and tool use, making it suitable for chat assistants, workflow automation, and general-purpose text generation.\n\n[Back to Models](https://zenmux.ai/models)\n\n## Providers\n\nRoute requests across multiple providers. Copy a provider slug to set your preference.\n\n~~$0.07~~\n\n**$0.056**\n\n*/ M tokens*\n\n~~$0.281~~\n\n**$0.2248**\n\n*/ M tokens*\n\n*Read:*\n\n~~0.003~~\n\n**0.0024**/ M tokens\n\n*Write:*\n\n**-**/ M tokens1.05M1.28s108tps\n\n## Uptime\n\n24hours\nDirect request success rate on AI Gateway and per-provider.\n\n## Throughput\n\n24hours\nP50 throughput on live AI Gateway traffic, in tokens per second (TPS).\n\n## Latency\n\n24hours\nP50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds.\n\n## Activity\n\nToken volume and request traffic to this model over time.\n\n## Benchmarks\n\nScores on standardized evaluations. Higher percentages are better — and rank percentile shows\n\nMetrics sourced from[Artificial Analysis](https://artificialanalysis.ai/)\n\n## Apps\n\nPublic apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for. [View All](https://zenmux.ai/analytics/apps)\n\n## Related Models\n\nMore models from [Tencent](https://zenmux.ai/tencent)", "url": "https://wpnews.pro/news/new-model-available-tencent-hy4-flash", "canonical_source": "https://zenmux.ai/tencent/hy4-flash", "published_at": "2026-11-16 07:55:58+00:00", "updated_at": "2026-11-16 08:22:00.794532+00:00", "lang": "en", "topics": ["large-language-models", "generative-ai", "ai-products", "natural-language-processing"], "entities": ["Tencent", "Hy4 Flash", "Artificial Analysis", "AI Gateway"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/new-model-available-tencent-hy4-flash", "markdown": "https://wpnews.pro/news/new-model-available-tencent-hy4-flash.md", "text": "https://wpnews.pro/news/new-model-available-tencent-hy4-flash.txt", "jsonld": "https://wpnews.pro/news/new-model-available-tencent-hy4-flash.jsonld"}}