Vercel adds Tencent’s Hy4 Flash to AI Gateway with 50% discount

Vercel has added Tencent’s Hy4 Flash to AI Gateway, offering a 50% introductory discount on input, cached input and output tokens through November 29, 2026. The lower-cost model keeps the Hy4 family’s main capabilities, including reasoning, tool calling and image input.
- Tencent’s Hy4 Flash is now available on Vercel AI Gateway.
- Input, cached input and output tokens are 50% off through November 29, 2026.
- The model retains Hy4 features and a 1M-token context window.
- Developers can use the model name tencent/hy4-flash.
- AI Gateway has no markup or platform fee on inference, according to Vercel.
A lower-cost model in the Hy4 family
Hy4 Flash is positioned as the lower-cost model in Tencent’s Hy4 family. According to Vercel, it provides the full Hy4 feature set at roughly a tenth of the price per token, while retaining a 1M-token context window.
The model supports reasoning with preserved thinking across turns, tool calling, structured outputs, prompt caching and image input. Developers can also turn reasoning off for requests that do not need it. Vercel says that option suits high-volume coding, agent and document workloads.
How developers can use Hy4 Flash
Applications using AI Gateway can call the model with the name tencent/hy4-flash. Vercel’s example uses the AI SDK’s streamText function to send a prompt and stream the response text.
For coding agents, Vercel says Hy4 Flash can be used with Claude Code, Codex, Cursor and more. Developers must install the latest Vercel CLI and run npx vercel ai-gateway setup, then select tencent/hy4-flash in the agent. Vercel also directs users to its coding agents guide and model playground.
The introductory discount applies through November 29, 2026, and covers input, cached input and output tokens. Vercel’s announcement is dated November 16, 2026.
What AI Gateway provides
AI Gateway gives developers a unified API for calling models, tracking usage and cost, and configuring retries, failover and performance optimizations for higher-than-provider uptime. Vercel says the service includes custom reporting, Zero Data Retention support, budgets for API keys and routing rules.
Vercel says AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including requests made with Bring Your Own Key. That pricing approach, combined with Hy4 Flash’s lower-cost positioning and the temporary discount, gives teams a way to test the model through an existing gateway while retaining access to the gateway’s usage controls and routing features.
Vercel: Hy4 Flash now available on AI Gateway for 50% off


