Skip to content

fix(pricing): add gpt-5.3 codex entries to pricing snapshot#10

Merged
slkiser merged 2 commits intoslkiser:mainfrom
flmalte:fix/gpt-5-3-codex-pricing
Feb 27, 2026
Merged

fix(pricing): add gpt-5.3 codex entries to pricing snapshot#10
slkiser merged 2 commits intoslkiser:mainfrom
flmalte:fix/gpt-5-3-codex-pricing

Conversation

@flmalte
Copy link
Contributor

@flmalte flmalte commented Feb 27, 2026

Summary

  • Add openai/gpt-5.3-codex to src/data/modelsdev-pricing.min.json with standard API token pricing.
  • Do not add pricing for openai/gpt-5.3-codex-spark because API token pricing is not publicly published yet.
  • Keep the change scoped to the bundled pricing snapshot only.

Testing

  • npm test ✅ (19 files, 82 tests passed)

Risk & Rollback

  • Risk: low; this only enables pricing for one additional model that already appears in usage logs.
  • Rollback: revert this PR to restore previous snapshot behavior.

Linked Issues

  • None.

Copilot AI review requested due to automatic review settings February 27, 2026 20:57
Copy link

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

This PR adds two new OpenAI model pricing entries (openai/gpt-5.3-codex and openai/gpt-5.3-codex-spark) to the bundled pricing snapshot so that usage of these models is costed rather than reported as unknown pricing. The gpt-5.3-codex-spark entry is explicitly an estimated fallback using the same rates as gpt-5.3-codex, since its pricing has not been officially published.

Changes:

  • Add gpt-5.3-codex and gpt-5.3-codex-spark entries to the OpenAI section of the pricing snapshot, both using cache_read: 0.175 / input: 1.75 / output: 14 (USD per 1M tokens).

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Comment on lines +396 to +405
"gpt-5.3-codex": {
"cache_read": 0.175,
"input": 1.75,
"output": 14
},
"gpt-5.3-codex-spark": {
"cache_read": 0.175,
"input": 1.75,
"output": 14
},
Copy link

Copilot AI Feb 27, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The two new gpt-5.3-* entries are inserted between gpt-5.2-codex (line 391) and gpt-5.2-pro (line 406), splitting up the gpt-5.2 variant group. Every other version family in the file keeps all its variants contiguous (e.g. gpt-5, gpt-5-chat-latest, gpt-5-codex, gpt-5-mini, gpt-5-nano, gpt-5-pro are consecutive; the same is true for gpt-5.1-* and gpt-5.2-*). The gpt-5.3-* entries should be placed after gpt-5.2-pro so that the gpt-5.2 family remains intact and the version ordering is consistent. Although JSON key order has no effect on runtime lookups, this inconsistency makes the file harder to read and maintain.

Copilot uses AI. Check for mistakes.
@slkiser slkiser merged commit 5ee6fe3 into slkiser:main Feb 27, 2026
3 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants