ToolsAugust 2, 2026via Vercel Blog

Qwen 3.8 Max now available on Vercel AI Gateway

Why it matters

Qwen's latest multimodal model is now accessible through Vercel's gateway layer, lowering friction for practitioners to test and integrate it alongside Claude, OpenAI, and other providers. Governance and cost control move into the integration stack.

Key signals

  • Qwen 3.8 Max: 2.4T parameters, 1M token context window
  • Text, vision-language, and multimodal capable in one model
  • Vercel AI Gateway: unified API for routing, usage tracking, failover, retry logic, no platform fee on inference
  • Support for Bring Your Own Key (BYOK) billing
  • Integration with coding agents (Claude Code, Codex, OpenCode, Pi)
  • No provider markup; reflects Alibaba pricing directly
  • Qwen 3.8 Max: 2.4 trillion parameters, 1M token context window
  • Text-only and vision-language in one model
  • Available on Vercel AI Gateway with no platform fee on inference
  • Supports BYOK (Bring Your Own Key) requests
  • Integrates with coding agents (Claude Code, Codex, OpenCode, Pi)
  • Targeted use cases: software engineering, office productivity, visual work (screenshot-to-page, video captioning, image QA)
  • AI Gateway provides unified API, usage tracking, cost control, failover/retry logic, custom reporting

The hook

Qwen 3.8 Max joins Vercel AI Gateway—another frontier model gets the unified API treatment for routing, cost tracking, and failover.

is now available on AI Gateway.Qwen 3.8 Max Qwen 3.8 Max handles text-only and vision-language work in one model, with 2.4 trillion parameters and a context window of up to 1 million tokens. The model is suited for software engineering and office productivity, along with visual work like turning scr

The week's key stories, every Friday.

ONE BRIEFING · EVERY FRIDAY · FREE

Free. Unsubscribe anytime.