Hy4 Flash now available on AI Gateway for 50% off
Vercel made Tencent's Hy4 Flash available on AI Gateway, with an introductory 50% discount on input, cached input, and output tokens through November 29, 2026.
Hy4 Flash is the lower-cost model in the Hy4 family, at roughly a tenth of the price per token. Vercel says it keeps the full Hy4 feature set: reasoning with thinking preserved across turns, tool calling, structured outputs, prompt caching, and image input, plus the same 1M-token context window. You can turn reasoning off for requests that don't need it, which Vercel suggests for high-volume coding, agent, and document work.
Call it with the model name tencent/hy4-flash, for example in the AI SDK's streamText. To use it in Claude Code, Codex, or Cursor, install the latest Vercel CLI, run npx vercel ai-gateway setup, then pick tencent/hy4-flash in the agent. The coding agents guide covers the setup. The command detects the agents you have installed and shows a diff of its changes before writing anything.
AI Gateway passes through provider pricing with no markup and no platform fee on inference, including for bring-your-own-key requests.