feat(models): add grok-4.3

[waleedlatif1]

Summary

• add grok-4.3 to the xAI provider with $1.25/$0.20/$2.50 pricing, 1M context window, and low/medium/high reasoning efforts
• mark as recommended xAI model

Type of Change

• New feature

Testing

Tested manually

Checklist

• Code follows project style guidelines
• Self-reviewed my changes
• Tests added/updated and passing
• No new warnings introduced
• I confirm that I have read and agree to the terms outlined in the Contributor License Agreement (CLA)

[vercel]

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

1 Skipped Deployment

Project	Deployment	Actions	Updated (UTC)
docs	Skipped		May 6, 2026 5:28pm

[cursor]

PR Summary

Low Risk
Low risk: change is limited to adding a new static model entry (metadata/pricing/capabilities) with no logic or API behavior changes.

Overview
Adds the grok-4.3 model to the xai provider’s static model list, including pricing, 1M context window, release date, and nativeStructuredOutputs capability.

Marks grok-4.3 as the recommended xAI model (without changing the provider default of grok-4-latest).

^{Reviewed by Cursor Bugbot for commit 3ab7ed1. Configure here.}

[greptile-apps]

Greptile Summary

This PR adds grok-4.3 to the xAI provider in the model registry with correct pricing ($1.25/$0.20/$2.50 per million tokens), a 1M context window, native structured output support, and the recommended flag.

• The model entry is accurate: official xAI documentation confirms the model ID grok-4.3, the pricing, and the April 30, 2026 release date. The nativeStructuredOutputs: true capability is also verified by the xAI API docs.
• Note: the PR description mentions "low/medium/high reasoning efforts," but per xAI's official documentation, grok-4.3 reasons automatically and returns an error if a reasoning.effort parameter is specified — the code correctly omits reasoningEffort from the model's capabilities.
• The provider's defaultModel remains grok-4-latest; this is consistent with other providers (e.g., OpenAI uses gpt-4.1 as default while GPT-5 is recommended), so the split appears intentional.

Confidence Score: 5/5

Safe to merge — the change is a single model entry addition to the registry with verified pricing, context window, and capabilities matching official xAI documentation.

The change adds one model object to the xAI provider array. All values (model ID, pricing, context window, release date, nativeStructuredOutputs) were confirmed against official xAI and third-party documentation. Reasoning effort is correctly omitted since the model does not support the parameter. No logic, schema, or behavioral contracts are affected.

No files require special attention.

Important Files Changed

Filename	Overview
apps/sim/providers/models.ts	Adds grok-4.3 model entry with verified pricing, 1M context window, nativeStructuredOutputs, and recommended flag — all consistent with official xAI documentation.

Flowchart

%%{init: {'theme': 'neutral'}}%%
flowchart TD
    A[xAI Provider] --> B[grok-4.3 NEW]
    A --> C[grok-4-latest]
    A --> D[grok-4-0709]
    A --> E[grok-4.20 family]
    A --> F[grok-3 family]

    B --> B1["$1.25 input / $0.20 cached / $2.50 output"]
    B --> B2[1M context window]
    B --> B3[nativeStructuredOutputs ✓]
    B --> B4[recommended ✓]
    B --> B5[Reasoning: always active, not configurable]

    C --> C1["$3.00 input / $0.75 cached / $15.00 output"]
    C --> C2[256K context window]
    C --> C3[defaultModel]

Loading

_{Reviews (2): Last reviewed commit: "feat(models): add grok-4.3" | Re-trigger Greptile}

[waleedlatif1]

@greptile

[waleedlatif1]

@cursor review

[cursor]

✅ Bugbot reviewed your changes and found no new issues!

Comment @cursor review or bugbot run to trigger another review on this PR

^{Reviewed by Cursor Bugbot for commit 3ab7ed1. Configure here.}