Tencent Hy4 Flash available on Vercel AI Gateway with introductory 50% discount
Tencent's Hy4 Flash, a lower-cost model in the Hy4 family, is now available on Vercel AI Gateway as tencent/hy4-flash. An introductory 50% discount applies to input, cached input, and output tokens through November 29, 2026.

Why it matters
Hy4 Flash is listed at roughly a tenth of the per-token price of the Hy4 family while keeping reasoning, tool calling, structured outputs, prompt caching, image input, and a 1M-token context window. Reasoning can be disabled per request, which is relevant for high-volume coding, agent, and document workloads. AI Gateway reports no markup and no platform fee on inference, including BYOK requests.
Who should care
Developers building AI agents, coding tools, or document-processing pipelines; online business builders with high-volume LLM usage; teams cost-sensitive about token spend.
What you can do
Set the model name to tencent/hy4-flash in an AI Gateway request, or install the latest Vercel CLI, run setup, and select tencent/hy4-flash in Claude Code, Codex, or Cursor to compare cost and output quality before November 29, 2026.