Add OpenAI chat-latest model metadata

[PeterDaveHello]

What

Adds openai/chat-latest model metadata to both model pricing metadata
files.

This replaces the old closed PR #27478 and targets
litellm_internal_staging.

Tests

• .venv/bin/pytest tests/test_litellm/test_openai_chat_latest_model_metadata.py -q
• .venv/bin/black --check tests/test_litellm/test_openai_chat_latest_model_metadata.py
• .venv/bin/python -c "import json; [json.load(open(p)) for p in ['model_prices_and_context_window.json', 'litellm/model_prices_and_context_window_backup.json']]; print('json ok')"
• git diff --check origin/litellm_internal_staging..HEAD

[greptile-apps]

Greptile Summary

This PR adds chat-latest model metadata for the OpenAI provider to both pricing JSON files (model_prices_and_context_window.json and the backup), along with a new test to verify the entry's correctness and cross-file consistency.

• JSON entries: Both files gain an identical "chat-latest" block under litellm_provider: "openai", including token costs, context window sizes, capability flags (supports_web_search, supports_vision, supports_pdf_input, etc.), and flat-rate web-search pricing.
• Tests: test_openai_chat_latest_model_info validates all metadata fields and the provider routing for "chat-latest"; test_openai_chat_latest_backup_matches_main asserts the two JSON files are in sync. Both tests use only local file I/O — no network calls.

Confidence Score: 5/5

This is a pure metadata addition — no logic paths are changed, only JSON pricing data is extended and validated by a new offline test.

The change is confined to two JSON files and one new test file. The new entry follows the established naming and structure conventions used by adjacent OpenAI models (e.g., chatgpt-4o-latest). The test file reads only local files (no network calls), validates every declared field, and explicitly checks that the main and backup JSONs agree. No existing tests are modified.

No files require special attention.

Important Files Changed

Filename	Overview
model_prices_and_context_window.json	Adds "chat-latest" metadata entry for the OpenAI provider; pricing, context window sizes, and capability flags are consistent with OpenAI documentation for this model.
litellm/model_prices_and_context_window_backup.json	Mirror of the main JSON change; the "chat-latest" entry is byte-for-byte identical to the main file, as validated by the new test.
tests/test_litellm/test_openai_chat_latest_model_metadata.py	New test file that validates chat-latest metadata fields and verifies the main/backup JSON files are in sync; reads only local files, no network calls.

_{Reviews (2): Last reviewed commit: "Add OpenAI chat-latest model metadata" | Re-trigger Greptile}

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 1cd9194aef

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!

[PeterDaveHello]

@Sameerlite, @krrish-berri-2, would you please help review?

[PeterDaveHello]

@greptileai review

[github-actions]

This pull request has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs.

[devin-ai-integration]

Superseded by rolling registry audit #37902, which reverified and absorbed the provider-documented metadata changes at field level