Repository navigation
fix(pricing): correct gpt-5.6-sol rates and add the daybreak blue alias - #39
Merged
Merged
Conversation
The gpt-5.6-sol row carried 2.00 in and 10.00 out per million tokens, with cache reads at 0.20 and writes at 2.50. Those are OpenAI's Batch and Flex figures; the Standard tier is 4.00, 20.00, 0.40, and 5.00, so Sol usage was estimated at half its list cost. gpt-daybreak-blue-latest, which OpenAI documents as an approval-gated alias of Sol, had no row and priced at zero. The row now carries the Standard rates, annotated with the promotional window OpenAI publishes so the figures get rechecked when it lapses. CostFromUsage resolves the Daybreak alias onto Sol after normalizing the ID, so the OpenCode provider prefix and context suffix still strip, and a table-driven test pins each rate and the cache arithmetic for both IDs in their bare and prefixed forms. Signed-off-by: Patrick Linnane <patrick@linnane.io>
There was a problem hiding this comment.
🟢 Approval recommended
No unresolved approval-blocking issues were identified.
Pull request overview
Corrects GPT-5.6 Sol Standard pricing and adds Daybreak Blue alias support.
Changes:
- Updates Sol input, output, and cache rates.
- Maps Daybreak Blue to Sol pricing.
- Adds table-driven pricing and cache tests.
File summaries
| File | Description |
|---|---|
pricing.go |
Updates rates and alias handling. |
pricing_test.go |
Tests pricing and cache arithmetic. |
harness.go |
Defines shared model identifiers. |
copilot.go |
Uses the Sol model identifier. |
Review details
- Files reviewed: 4/4 changed files
- Comments generated: 0
- Review effort level: Lite
💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The
gpt-5.6-solpricing row carried $2.00 in and $10.00 out per million tokens, with cache reads at $0.20 and writes at $2.50. Those are OpenAI's Batch and Flex tier figures; the Standard tier is $4.00, $20.00, $0.40, and $5.00, so any consumer estimating Sol cost from tokens reported half the list price.gpt-daybreak-blue-latest, which OpenAI documents as an approval-gated alias of Sol, had no row and priced at zero.The row now carries the Standard rates with a note on the promotional window OpenAI publishes (at least through 2026-11-21) so they get rechecked when it lapses.
CostFromUsagemaps the Daybreak alias onto Sol afternormalizeModelID, so the OpenCode provider prefix and[1m]suffix still strip first, and a table-driven test pins each rate and the cache arithmetic for both IDs. Scrutineer carries the same rates locally in alpha-omega-security/scrutineer#1018 until this ships in a release.Codex was used to implement this; Opus 5 reviewed it.