xAI Launches Grok 4.6 With Unified Multi-Modal API, Sub-200ms Latency
Jasonio · x · 2026-09-16
At the Compile 26 event, xAI unveiled Grok 4.6, its new frontier model spanning reasoning, code, voice, images, and video, trained on what it calls the world's largest supercluster.
- One unified API for all modalities, model name grok-4.6
- Claimed stats: 1M+ API calls/day, <200ms median latency, 5+ model families
- Works with OpenAI SDK, Vercel AI SDK, and native xAI SDK
- Demo includes agentic coding workflows with parallel task execution
More from Models
- ChatGPT usage seasonality has faded sharply: back-to-school spikes are a thing of the past — menhguin · 2026-09-16
- ChatGPT was the fastest-growing top-10 website in August as students returned to school — menhguin · 2026-09-16
- Qwen 27B on a single RTX 5090 generates 8-scene animation from one prompt — Acceptable-Object390 · 2026-09-16
- Qwen 27B on a single RTX 5090 generates 8-scene animation from one prompt — Acceptable-Object390 · 2026-09-16
- New paper lifts LLM memory retention 28x to 34.9% across 100 sequential tasks — DanielKhashabi · 2026-09-16
- Claude usage bug unexpectedly grants extra quota as user plans ASC CLI release — rudrank · 2026-09-16