Reasoning tokens are charged at the output rate regardless of the model's reasoning price

[willsarg]

Session.getUsage hardcodes reasoning tokens at the output rate:

// TODO: update models.dev to have better pricing model, for now:
// charge reasoning tokens at the same rate as output tokens
.add(new Decimal(tokens.reasoning).mul(costInfo?.output ?? 0).div(1_000_000))

Models with a distinct reasoning price aren't costed correctly. Add an optional reasoning field to the cost schemas and use it in getUsage, falling back to the output rate when unset. Backward compatible.

[github-actions]

This issue doesn't fully meet our contributing guidelines.

What needs to be fixed:

• No issue template was used. Please resubmit using one of the three required templates: Bug Report, Feature Request, or Question. Since this appears to be a bug report, please use the Bug Report template and fill in the required fields (Description, reproduction steps, system info, etc.).

Please edit this issue to address the above within 2 hours, or it will be automatically closed.

---

This issue might be a duplicate of existing issues. Please check:

• OpenAI reasoning tokens double-counted in cost calculation #17566: OpenAI reasoning tokens double-counted in cost calculation — also involves incorrect reasoning token cost calculation in getUsage (though that issue is about double-counting rather than wrong per-token rate, they touch the same code path)

If you believe this was flagged incorrectly, please let a maintainer know.

[github-actions]

This issue has been automatically closed because it was not updated to meet our contributing guidelines within the 2-hour window.

Feel free to open a new issue that follows our issue templates.