fix(pricing): add non-zero gpt-5.3-codex entries to model map

[jackcpku]

Relevant issues

• Related: [Bug]: github_copilot pricing missing gpt-5.3-codex and claude-opus-4.6-fast #21148
• Related: feat: add chatgpt 5.3-codex provider model (chatgpt/gpt-5.3-codex) #20552

Pre-Submission checklist

Please complete all items before asking a LiteLLM maintainer to review your PR

• I have Added testing in the tests/litellm/ directory, Adding at least 1 test is a hard requirement - see details
• My PR passes all unit tests on make test-unit
• My PR's scope is as isolated as possible, it only solves 1 specific problem
• I have requested a Greptile review by commenting @greptileai and received a Confidence Score of at least 4/5 before requesting a maintainer review

CI (LiteLLM team)

CI status guideline:

• 50-55 passing tests: main is stable with minor issues.
• 45-49 passing tests: acceptable but needs attention
• <= 40 passing tests: unstable; be careful with your merges and assess the risk.

• Branch creation CI run
  Link:

• CI run for the last commit
  Link:

• Merge / cherry-pick CI run
  Links:

Type

🐛 Bug Fix
✅ Test

Changes

This fixes the $0.00 pricing resolution path for gpt-5.3-codex by adding canonical non-zero entries in the model map.

• Added chatgpt/gpt-5.3-codex metadata entry (responses endpoint + capabilities)
• Added gpt-5.3-codex OpenAI-priced entry with:
  • input_cost_per_token: 1.75e-06
  • output_cost_per_token: 1.4e-05
  • cache_read_input_token_cost: 1.75e-07
  • matching priority pricing fields and capabilities
• Synced litellm/model_prices_and_context_window_backup.json with root map
• Added regression tests in tests/test_litellm/test_gpt_5_3_codex_config.py

Local validation

• python3 ci_cd/check_files_match.py
• /Users/jack/tmp/litellm-work/.venv/bin/pytest tests/test_litellm/test_gpt_5_3_codex_config.py -q
• jq empty model_prices_and_context_window.json
• jq empty litellm/model_prices_and_context_window_backup.json