fix(pricing): adjust gpt-5.6-terra and gpt-5.6-luna prices according to OpenAI's latest article

[lihugang]

feat(pricing): adjust gpt-5.6-terra and gpt-5.6-luna prices according to OpenAI's latest article

Adjust the price of gpt-5.6-terra to 80% of its original rate (2/12), and gpt-5.6-luna to 20% of its original rate (0.2/1.2).

References:
https://openai.com/index/advancing-the-price-performance-frontier-with-gpt-5-6/
https://developers.openai.com/api/docs/pricing

---

Problem this solves:

• The model prices of gpt-5.6-terra and gpt-5.6-luna currently in the repo do not match the official OpenAI prices.

How it solves it:

• Adjusted the metadata in the repo according to [the latest model price of openai](https://developers.openai.com/api/docs/pricing](https://developers.openai.com/api/docs/pricing).

Pre-Submission checklist

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

• I have added meaningful tests
• My PR passes all CI/CD checks (e.g., lint, format, unit tests)
• My PR's scope is as isolated as possible; it only solves 1 specific problem
• I have received a Greptile Confidence Score of at least 4/5 before requesting a maintainer review (Greptile reviews automatically once the PR is opened; only comment @greptileai to re-request a review after pushing changes)

Delays in PR merge?

If you're seeing a delay in your PR being merged, ping the LiteLLM Team on Slack (#pr-review).

Type

🐛 Bug Fix

Changes

Adjust the price of gpt-5.6-terra to 80% of its original rate (2/12), and gpt-5.6-luna to 20% of its original rate (0.2/1.2).

References:
https://openai.com/index/advancing-the-price-performance-frontier-with-gpt-5-6/
https://developers.openai.com/api/docs/pricing

Final Attestation

• The tests check the right things, including the edge cases, and regressions in the respective real-world customer use-cases are not possible after this PR

[CLAassistant]

All committers have signed the CLA.

[greptile-apps]

Greptile Summary

Updates OpenAI GPT-5.6 Terra and Luna pricing consistently across the canonical and backup metadata files

• Revises standard, cached, batch, flex, priority, and long-context token rates
• Updates cost-calculation expectations for the revised OpenAI prices
• Separates OpenAI and Azure test fixtures so Azure retains its existing rates

Confidence Score: 5/5

The PR appears safe to merge

The previously reported synchronization issue is resolved at the current HEAD, and no blocking failure remains

Important Files Changed

Filename	Overview
model_prices_and_context_window.json	Updates the canonical OpenAI GPT-5.6 Terra and Luna pricing fields consistently
litellm/model_prices_and_context_window_backup.json	Keeps the bundled backup synchronized with the canonical pricing metadata
tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py	Updates generic cost-calculation expectations to cover the revised token rates
tests/test_litellm/test_gpt_5_6_model_metadata.py	Separates OpenAI and Azure pricing expectations while preserving provider-specific rates

_{Reviews (4): Last reviewed commit: "fix(pricing): adjust gpt-5.6-terra and g..." | Re-trigger Greptile}

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!

[lihugang]

@greptile-apps

[codspeed-hq]

Merging this PR will not alter performance

✅ 31 untouched benchmarks

---

_{Comparing lihugang:litellm_internal_staging (3212a5f) with litellm_internal_staging (4eecf7a)}

[mubashir1osmani]

merging on staging branch to do a first pass