Newer Grok 4.1 models have shipped; this profile remains specific to the original Grok 4
The OnAirToday AI Progress Tracker verified against xAI's published documentation that this profile covers the original Grok 4, despite the release of newer Grok 4.1 models.
OnAirToday
Newsroom
The OnAirToday AI Progress Tracker recorded a verified change to xAI's Grok 4 (version grok-4): Newer Grok 4.1 models have shipped; this profile remains specific to the original Grok 4.
Grok 4 is xAI’s July 2025 reasoning model, with a documented 256,000-token context window and API pricing of $3 per million input tokens and $15 per million output tokens. Newer Grok 4.1 models have shipped; the specifications and historical benchmark results here remain specific to the original Grok 4.
What changed in this review:
- Removed unconfirmed OTIS Mock AIME, Terminal-Bench, and FrontierMath figures.
- Removed the unconfirmed LMArena Text figure; Elo is not a percentage or a 0–100 benchmark score.
- Capability score 55 → 63
Teams building on Grok 4 should confirm limits, pricing and benchmark coverage against the vendor's own documentation before relying on these figures.
The full profile — capabilities, benchmark citations, known flaws and risk guidance — is on the tracker at /ai-models/grok-4.
References:
- https://x.ai/news/grok-4
- https://docs.x.ai/docs/models
- https://aider.chat/docs/leaderboards/#polyglot-leaderboard
- https://x.ai/news/grok-4-1
Generated insight by OnAirToday AI
Distinguishing the original Grok 4 from newer Grok 4.1 models helps readers understand which model a profile describes. Checking xAI's documentation provides a basis for that distinction.
Comments
Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.