# Qwen 3.8 Max 0902 now available on AI Gateway

Source: [Vercel](https://vercel.com/changelog/qwen-3-8-max-0902-now-available-on-ai-gateway)  
Feed7 permalink: https://feed7.dev/p/qwen-3-8-max-0902-now-available-on-ai-gateway-0zxju42  
Published: 2026-09-01T00:00:00.000Z  
Trust: Official Source (official_source)

## Why Included

Vercel’s gateway now exposes a pinned Qwen snapshot aimed at larger coding projects and longer agent runs, with a dated model ID that prevents silent upgrades.

## Source Summary

Vercel AI Gateway now offers **Qwen 3.8 Max 0902** under **alibaba/qwen3.8-max-0902**. Vercel says its gains center on large-project coding, unsupervised long-horizon work, agent runs, and denser visual inputs.

## Practical Implication

Pin the dated identifier when testing it in Cursor, Claude Code, Codex, or another supported agent. That keeps later releases from changing the model behind an established evaluation or workflow.

## Agent-Ready Context

Vercel AI Gateway now offers **Qwen 3.8 Max 0902** under **alibaba/qwen3.8-max-0902**. Vercel says its gains center on large-project coding, unsupervised long-horizon work, agent runs, and denser visual inputs.

Pin the dated identifier when testing it in Cursor, Claude Code, Codex, or another supported agent. That keeps later releases from changing the model behind an established evaluation or workflow.

The changelog provides no benchmark scores, pricing, latency, or direct comparison with other gateway models. Treat the capability claims as candidates for repository-specific evaluation.

## Connected Context

Feed7 judgment across 669 accumulated Signals:

This narrows the earlier Qwen 3.8 Max option to a dated, reproducible route whose behavior can be held stable during evaluation. The claimed focus on large projects, long-horizon agents, and dense visual input expands what should be tested, but missing cost, latency, and comparative results leave no basis for replacing another gateway route.

- [Qwen 3.8 Max now available on Vercel AI Gateway](https://feed7.dev/p/qwen-3-8-max-now-available-on-vercel-ai-gateway-1ikih0e) — The dated 0902 identifier turns the prior general Qwen 3.8 Max endpoint into a version-pinned evaluation target, reducing ambiguity from later model releases.
- [Kimi K3 and Kimi K3 Fast with ZDR and US-based providers now on AI Gateway](https://feed7.dev/p/kimi-k3-and-kimi-k3-fast-on-ai-gateway-0jpdaz6) — Kimi K3 exposes concrete hosting, retention, speed, and price choices that the Qwen announcement omits, showing which operational dimensions must be gathered before a routing comparison is actionable.
- [10x more capacity for Laguna S 2.1 on AI Gateway](https://feed7.dev/p/10x-more-capacity-for-laguna-s-2-1-on-ai-gateway-04s07oo) — Laguna’s capacity change distinguishes operational availability from model capability; Qwen’s capability claims likewise do not establish throughput or production reliability.

## Context Map

- Layer: tools
- Domains: coding
- Topics: coding-agents, model-selection, gateways

## Uncertainty

- The changelog provides no benchmark scores, pricing, latency, or direct comparison with other gateway models. Treat the capability claims as candidates for repository-specific evaluation.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.