GLM-5.3 Flash Free Arrives on OpenCode

OpenCode’s status page now lists glm-5.3-flash-free under Free inference. That is separate from the standard GLM-5.3 Flash model, which OpenCode’s pricing table lists at $0.15 per million input tokens and $0.50 per million output tokens. Check the exact model name before using it. OpenCode status (opens in a new tab) · OpenCode model pricing (opens in a new tab)

GLM-5.3 Flash is the lighter, lower-cost option beside full GLM-5.3. The free endpoint makes it worth testing for everyday coding, small edits, and agent loops without spending API credits. OpenCode’s status page currently reports increased errors for this free endpoint, so availability may be unreliable.

Budget verdict: Try it for non-critical tasks while it’s free, but keep another model ready. Free access can change, and don’t assume the paid and free endpoints have identical limits or service quality.