OpenCode reports that Ox Alpha processed 26T tokens in four days, showing heavy real-world use of the preview but saying nothing by itself about model quality, individual quotas, or availability.
Object: Ox Alpha on OpenCode.
Window: Four days.
Total volume: 26T tokens.
Source type: An aggregate operational observation from the platform, not a public benchmark.
26T is usage/load data, not a count of successful tasks. The post does not disclose user count, task distribution, input/output split, failure rate, latency, model version, or token accounting. It supports only that the entry point saw very high short-term usage; it does not support “widely used, therefore stronger.”
Record the post date, model entry point, and official number.
Do not add the official total to community figures such as 500M/day or 100T/day, which use different scopes.
To evaluate quality, create a fixed task set and save each request's input, output, tool trace, test result, and error.
Replies on the same official post show upstream errors, unavailable endpoints, and account-limit feedback. Aggregate token volume does not reveal the share of failed requests.
Ox Alpha
