OpenCode Zen adds LL Alpha Free, a limited-time $0 text reasoning model (~262k context)
OpenCode Zen just added LL Alpha Free, an anonymous text model billed at $0 for input, output, and cached reads. It offers about 262k tokens of context and up to ~65k output tokens, with reasoning and tool use. It is free for a limited time with no end date announced yet.
The briefing
OpenCode Zen added a free anonymous model called LL Alpha Free (model id ll-alpha-free). Anyone with a Zen account can call it at no cost.
What you can use
Input, output, and cached reads on LL Alpha Free are all billed at $0. It handles about 262k tokens of context and up to roughly 65k output tokens per response, supports reasoning, tool calls, and structured JSON output. Reasoning effort can be set to low, medium, high, xhigh, or max.
It is a limited-time anonymous preview with no public vendor identity and no announced end date. Requests during the free period may be used to improve the model.
Specs
LL Alpha Free is a text-only reasoning model with open weights and a knowledge cutoff around June 2026. Speed is around 20 tokens per second, so it is better as a trial option than as your only daily driver.
How to use it
- Open OpenCode, sign in to Zen, and switch to LL Alpha Free with
/models, or set the model toopencode/ll-alpha-freein your config. - For API calls, use the Zen endpoint
https://opencode.ai/zen/v1/chat/completionswith modelll-alpha-free.
Docs: OpenCode Zen · models.dev OpenCode list · Zen models API.