Go quota accounting does not match Usage History or documented limits

Description

OpenCode Go quota percentages do not appear to match the dollar amounts shown in Usage History. This makes it difficult to understand how much of the shared Go allowance a request consumes.

The OpenCode Go usage limits documentation states:

• 5-hour limit: $12 of usage
• Weekly limit: $30 of usage
• Monthly limit: $60 of usage

The documentation also provides estimated request counts by model, but it does not clearly explain how the model Usage values map to these shared limits.

Evidence

Issue #41146 reports approximately $7.52 of visible qwen3.8-max usage, while the dashboard showed:

• Weekly quota: 100% of the $30 limit
• Monthly quota: 50% of the $60 limit

This is consistent with the visible amount being converted to approximately $30 of quota usage, suggesting an effective multiplier close to 4x.

Issue #41206 reports approximately $11.09 of visible Go usage, while the dashboard showed:

• Weekly usage: 100%
• Monthly usage: 52%

The monthly percentage corresponds to approximately $31.20 of internal quota usage, rather than the visible $11.09.

Issue #40031 reports approximately $3 of visible Grok usage, while the session usage showed 100% of the $12 rolling limit.

These examples suggest that the visible Usage History amount may be multiplied before it is applied to the Go quota.

Main question

Could the team please confirm or correct the following interpretation?

For some models, does OpenCode Go effectively apply a 4x multiplier to the visible Usage History amount? In other words, is the model table effectively normalizing the shared monthly $60 limit to approximately $15 of visible usage for those models?

For example, if the visible Usage History for Grok 4.5 reaches $15, does that mean:

• approximately $15 is deducted from the shared $60 monthly quota, leaving approximately $45 for other models; or
• approximately $60 is deducted from the shared quota because of a 4x model multiplier, leaving no monthly quota for other models?

The same question applies to any other model whose table value is $15.

Please provide a simple worked example or formula showing the relationship between:

1. the dollar amount displayed in Usage History;
2. the model's Usage value in the documentation table; and
3. the amount deducted from the shared 5-hour, weekly, and monthly quotas.

If the 4x interpretation is intentional, the documentation should state this explicitly so users do not assume that $15 of visible usage leaves $45 of the shared $60 allowance. If it is not intentional, these reports may indicate a quota-accounting bug.

Plugins

None.

OpenCode version

OpenCode Go web dashboard/account quota; this concerns server-side accounting.

Steps to reproduce

1. Subscribe to OpenCode Go and use one or more Go models.
2. Open the Usage dashboard and record the dollar amount shown in Usage History.
3. Compare it with the rolling, weekly, and monthly quota percentages.
4. Compare the result with the published limits and model table in the Go documentation.

Screenshot and/or share link

https://opencode.ai/docs/en/go/#usage-limits:~:text=The%20estimates%20are%20also%20based%20on%20the%20following%20prices%20per%201M%20tokens%20and%20the%20monthly%20usage%20included%20with%20each%20model%3A

See the account-level data and screenshots in issue #41206 and issue #41146.

Operating System

Not applicable to server-side quota calculation.

Terminal

Not applicable to server-side quota calculation.

Start with the Go usage-limits documentation and the account data and screenshots referenced in issues #41146 and #41206. Trace how Usage History amounts correspond to the rolling, weekly, and monthly quota percentages; done means the relationship is corrected or clearly documented with a worked formula.