Tencent Hunyuan Hy4 flash is free on OpenCode Zen for two weeks
Tencent Hunyuan Hy4 flash free for two weeks, near-unlimited usage, ~1M context
OpenCode Zen added a free tier for Tencent Hunyuan Hy4 flash. For two weeks from November 16, input, output, and cache reads cost nothing, with near-unlimited usage. The model supports about one million tokens of context and image input. Switch to Hy4 flash Free in OpenCode to start coding.
- Eligibility
- Any OpenCode account; free chat models must be used through the OpenCode client
- Benefit duration
- Free for two weeks from November 16, 2026, until about November 30
The briefing
OpenCode Zen added a free tier for Tencent Hunyuan Hy4 flash (model ID hy4-flash-free). It is free for two weeks starting November 16, until about November 30, with near-unlimited usage.
What you can use
Anyone with an OpenCode account can pick it. Input, output, and cache reads are billed at $0. It has about one million tokens of context and up to roughly 65K output tokens, takes text and image input, supports tool calls, and lets you set reasoning effort to none or high. The provider follows a zero-retention policy.
Hy4 flash is the fastest and most cost-efficient model in the Hunyuan family, with 224B total parameters and 12B active, a good fit for everyday coding and agent work.
How to use it
- Open OpenCode, sign in, and switch to Hy4 flash Free with
/models, or set the model toopencode/hy4-flash-freein your config. - For the API, use
https://opencode.ai/inference/openai/v1/chat/completionswith modelhy4-flash-free.
More details: OpenCode Zen docs and OpenCode's announcement.
