Add support for grok-4.20-0309-reasoning model

[Sameerlite]

Relevant issues

Pre-Submission checklist

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

• I have Added testing in the tests/test_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

Delays in PR merge?

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

Screenshots / Proof of Fix

Type

🆕 New Feature
🐛 Bug Fix
🧹 Refactoring
📖 Documentation
🚄 Infrastructure
✅ Test

Changes

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Actions	Updated (UTC)
litellm	Ready	Preview, Comment	Apr 17, 2026 3:21am

[greptile-apps]

Greptile Summary

This PR adds the stable xai/grok-4.20-0309-reasoning model entry to both JSON price files. The pricing values ($2.00/$0.20/$6.00 per M tokens) and the 2 M-token context window match the official xAI documentation. The structure is consistent with the existing xai/grok-4.20-beta-0309-reasoning entry.

• No tests were added. CLAUDE.md explicitly states "Adding at least 1 test is a hard requirement" — even a simple assertion that the model key exists in litellm.model_cost would satisfy this requirement.

Confidence Score: 4/5

Safe to merge after adding the required test — pricing values and capabilities are accurate per official xAI docs.

One P1 finding remains: no test was added despite CLAUDE.md stating it is a hard requirement. The metadata itself is correct (pricing matches xAI docs, context window is accurate, capabilities are consistent with the beta predecessor).

No files have defects; the gap is a missing test file in tests/test_litellm/.

Important Files Changed

Filename	Overview
model_prices_and_context_window.json	Adds xai/grok-4.20-0309-reasoning with correct pricing and context window values; no tests added.
litellm/model_prices_and_context_window_backup.json	Mirror of the root JSON file; identical entry added, consistent with existing backup sync pattern.

Flowchart

%%{init: {'theme': 'neutral'}}%%
flowchart TD
    A["User calls litellm with xai/grok-4.20-0309-reasoning"] --> B["litellm.get_model_info()"]
    B --> C["Loads model_prices_and_context_window.json"]
    C --> D{"Model key found?"}
    D -- Yes --> E["Returns model metadata\n input cost, output cost,\n context window, capabilities"]
    D -- No --> F["KeyError / unknown model"]
    E --> G["Cost tracking and routing\nuse returned metadata"]

Loading

_{Reviews (1): Last reviewed commit: "Add support for grok-4.20-0309-reasoning..." | Re-trigger Greptile}

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!