AI Provider Portfolio
7 active models in catalogxAI Models
Comprehensive benchmark scores, coding performance, latency metrics, and API pricing for all models developed by xAI.
Available Models & Verified Benchmarks
#1Grok 4.6
ProprietaryxAI Aug 12 2026 post-training refresh of Grok 4.5. Same $2/$6 API price, 500k context, stronger agentic traces.
Elo1,592
SWE-bench69.1%
Out $/1M$6
#2Grok 4
ProprietaryPrevious xAI flagship.
Elo1,488
SWE-bench58.6%
Out $/1M$15
#3Grok 3
ProprietaryPrevious xAI generation before Grok 4. Kept for grok 3 vs grok 4.
Elo1,405
SWE-bench51.4%
Out $/1M$15
Proprietary
Auto-discovered from OpenRouter (x-ai/grok-build-0.1). Preview until a second source matches.
Elo—
SWE-bench—
Out $/1M$2
Proprietary
Auto-discovered from OpenRouter (x-ai/grok-4.3). Preview until a second source matches.
Elo—
SWE-bench—
Out $/1M$2.5
Proprietary
Auto-discovered from OpenRouter (x-ai/grok-4.20-multi-agent). Preview until a second source matches.
Elo—
SWE-bench—
Out $/1M$2.5
Proprietary
Auto-discovered from OpenRouter (x-ai/grok-4.20). Preview until a second source matches.
Elo—
SWE-bench—
Out $/1M$2.5