Artificial Intelligence1 min read

Hy4 Flash now available on AI Gateway for 50% off

By · Published by Everything Blog

In short

The new offering provides the full suite of Hy4 features, including tool calling, structured outputs, prompt caching, and an option to disable reasoning for high-throughput tasks like document analysis. Teams can deploy the model via the unified AI Gateway API or test it directly inside the interactive playground. Access is supported across development tools like Cursor and Codex with no platform markups on inference fees.

Key points

  • Teams can toggle off the reasoning feature to optimize high-volume coding, agent, and doc…: Teams can toggle off the reasoning feature to optimize high-volume coding, agent, and document workloads.
  • The AI Gateway provides unified usage metrics, cost tracking, retries, and failovers with…: The AI Gateway provides unified usage metrics, cost tracking, retries, and failovers with Zero Data Retention support.
  • Inference is delivered at direct provider rates without added platform fees, even for Bri…: Inference is delivered at direct provider rates without added platform fees, even for Bring Your Own Key setups.

Sources checked by our analysis pipeline: 1

Hy4 Flash from Tencent is now available on AI Gateway with an introductory 50% discount on input, cached input, and output tokens through November 29, 2026.

Hy4 Flash is the new lower-cost model in the Hy4 family. It keeps the full Hy4 feature set at roughly a tenth of the price per token: reasoning with preserved thinking across turns, tool calling, structured outputs, prompt caching, and image input, with the same 1M-token context window. Reasoning can be turned off for requests that don't need it, which suits high-volume coding, agent, and document workloads.

Use tencent/hy4-flash

as the model name:

import { streamText } from 'ai';

const result = streamText({ model: 'tencent/hy4-flash', prompt: 'Summarize the tradeoffs of server-side rendering in three sentences.',});

for await (const text of result.textStream) { process.stdout.write(text);}

To use it in Claude Code, Codex, Cursor, and more, install the latest Vercel CLI and run setup:

npx vercel ai-gateway setup

Then select tencent/hy4-flash

in the agent. See the coding agents guide for details.

Try Hy4 Flash in the model playground.

AI Gateway provides a unified API for calling models,…

Artificial Intelligence