Skip to content

feat(models): add grok-4.6 and make it the xAI flagship - #6624

Merged
waleedlatif1 merged 1 commit into
stagingfrom
feat/grok-4-6-model
Aug 12, 2026
Merged

feat(models): add grok-4.6 and make it the xAI flagship#6624
waleedlatif1 merged 1 commit into
stagingfrom
feat/grok-4-6-model

Conversation

@waleedlatif1

Copy link
Copy Markdown
Collaborator

Summary

  • Add grok-4.6 to the xAI catalog: 500k context, $2.00 in / $0.50 cached / $6.00 out per 1M
  • Promote it to the xAI flagship — recommended: true and defaultModel, both moved off grok-4.5
  • Feature the latest blog post on the index

Verification

Every field was checked against xAI's live API using the staging hosted key, not just the docs:

  • GET /v1/models/grok-4.6context_length: 500000, prompt_text_token_price: 20000, cached_prompt_text_token_price: 5000, completion_text_token_price: 60000 (units are USD cents per 100M tokens, so $2.00 / $0.50 / $6.00 per 1M) — exact match with the entry
  • temperature: 2 accepted, temperature: 2.5 rejected with Temperature must be less than 2{ min: 0, max: 2 } is right
  • max_completion_tokens (the only other param providers/xai/index.ts sends) accepted
  • Tool calling returns a well-formed tool_calls array
  • 400k-token prompt accepted, confirming the long-context path

reasoningEffort is deliberately not set. xAI documents low/medium/high/xhigh for this model, but providers/xai/ never reads the flag, so setting it would be a silent no-op. Worth wiring up separately.

Priced at the <200k tier, matching every existing grok entry. xAI doubles rates at the 200k threshold; Sim's schema holds one price pair, so long prompts under-bill — pre-existing across the whole provider, not new here.

grok-4.6 is hosted and billed automatically, since getHostedModels() already includes all of xai. The staging key pool has access to it today.

Type of Change

  • New feature

Testing

models.test.ts, utils.test.ts, pi-providers.test.ts, and the content/landing suites all pass (256 tests). Lint, type-check, and agent-stream-docs:check clean.

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)

Verified every field against xAI's live API with the staging hosted key:
context_length 500000, $2.00/$0.50/$6.00 per 1M, temperature capped at 2,
tool calling and max_completion_tokens both accepted.

Also feature the latest blog post.
@vercel

vercel Bot commented Aug 12, 2026

Copy link
Copy Markdown

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

1 Skipped Deployment
Project Deployment Actions Updated (UTC)
docs Skipped Skipped Aug 12, 2026 4:31pm

Request Review

@cursor

cursor Bot commented Aug 12, 2026

Copy link
Copy Markdown

PR Summary

Low Risk
Catalog and default-model metadata only; existing workflows pinned to grok-4.5 are unchanged, with minor billing/UI impact for new xAI selections.

Overview
Adds grok-4.6 to the xAI model catalog (500k context, $2.00 / $0.50 cached / $6.00 per 1M tokens) and makes it the xAI default and recommended model, moving those flags off grok-4.5.

models.test.ts now expects grok-4.6 as the xAI default and in getHostedModels(). The secret-provenance blog post is marked featured: true on the index.

Reviewed by Cursor Bugbot for commit 9c6ae59. Configure here.

@greptile-apps

greptile-apps Bot commented Aug 12, 2026

Copy link
Copy Markdown
Contributor

Greptile Summary

The PR registers grok-4.6 as xAI’s recommended default model and promotes the latest security article on the blog index.

  • Adds grok-4.6 pricing, context-window, release, and temperature metadata.
  • Updates xAI default-model and hosted-model tests.
  • Marks the secret-provenance article as featured.

Confidence Score: 5/5

The PR appears safe to merge with no actionable correctness or security issues identified.

The new model is included through the existing data-driven xAI catalog, hosted-model, billing, and provider-resolution paths, while the blog metadata change follows the index’s established featured-post selection behavior.

Important Files Changed

Filename Overview
apps/sim/providers/models.ts Adds grok-4.6 to the xAI catalog and moves the provider’s default and recommendation from grok-4.5.
apps/sim/providers/models.test.ts Updates assertions for the new xAI default and confirms both grok-4.6 and grok-4.5 remain hosted.
apps/sim/content/blog/secret-provenance/index.mdx Promotes the secret-provenance article into the date-ranked featured-post set.

Reviews (1): Last reviewed commit: "feat(models): add grok-4.6 and make it t..." | Re-trigger Greptile

@waleedlatif1
waleedlatif1 merged commit 74212ef into staging Aug 12, 2026
24 checks passed
@waleedlatif1
waleedlatif1 deleted the feat/grok-4-6-model branch August 12, 2026 16:34
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant