OFICIAL Vercel Blog

Grok 4.6 now available on AI Gateway

What happened
Based on Vercel Blog · Aug 12, 2026

Vercel’s AI Gateway now supports Grok 4.6 from SpaceXAI, featuring a 500K token context window and multimodal input, with tiered reasoning levels and default high settings.

Grok 4.6 now available on AI Gateway
Vercel Blog — Vercel
Key points
·
The model has a 500K token context window and accepts text and image inputs.
·
Grok 4.6 supports low, medium, high, and xhigh reasoning levels and defaults to high.
·
To use it in a coding agent, run vercel ai-gateway coding-agents setup to connect Claude Code, Codex, OpenCode, or Pi, then select xai/grok-4.6 inside the agent.
·
To try Grok 4.5 with no code, try the model in the model playground.
Key numbers
·
The model is accessible within these agents via the identifier xai/grok-4.

Grok 4.6 from SpaceXAI has been added to Vercel’s AI Gateway, expanding the platform’s model offerings. The release introduces a 500K token context window, enabling processing of substantially larger inputs than prior versions. The model supports both text and image inputs, broadening its applicability across different use cases. Grok 4.6 also includes four reasoning levels—low, medium, high, and xhigh—with high set as the default configuration.

Users can integrate Grok 4.6 into coding agents by running the command vercel ai-gateway coding-agents setup, which supports connections to Claude Code, Codex, OpenCode, or Pi. The model is accessible within these agents via the identifier xai/grok-4.6. For those seeking a no-code option, Grok 4.5 remains available in the AI Gateway model playground for direct testing and evaluation.

AI Gateway serves as a unified interface for model access, providing tools for usage tracking, cost management, and performance optimizations. The service includes features such as custom reporting, Zero Data Retention support, API key budgeting, and routing rules to enhance reliability and control. Pricing aligns with provider rates, with no additional platform fees applied to inference costs, including Bring Your Own Key requests.

The AI Gateway model leaderboard ranks models based on total token volume processed across all traffic, offering visibility into usage trends. Grok 4.6’s inclusion updates the leaderboard, reflecting its growing adoption. The platform continues to expand its model ecosystem while maintaining transparent pricing and operational flexibility for developers.

Original source → Deals on Clipraptor.com →