Skip to content

Qwen4 Max through Token Harbor

Qwen4 Max now has a Token Harbor route. Add your Token Harbor key and call qwen/qwen4-max with no markup.

Open Qwen4 Max
Qwen4 announcement artwork

Add a Token Harbor key under Dashboard → BYOK to reach qwen/qwen4-max, the preview of Alibaba's Qwen4 family. Token Harbor lists it at $2 per 1M input and $6 per 1M output and bills you directly. AnyRouter charges nothing for a BYOK route.

AI SDK
import { createAnyRouter } from "@anyr/ai-sdk-provider"
import { generateText } from "ai"
const anyrouter = createAnyRouter()
const { text } = await generateText({ model: anyrouter("qwen/qwen4-max"), prompt: "Hello" })
Coding agent
curl -fsSL https://anyr.dev/cli.sh | bash
anyr login
anyr opencode --model "qwen/qwen4-max"

Playbooks: AI SDK, coding agents, BYOK setup.

Bar charts comparing Qwen4-Max with Qwen3.8-Max-0902, Opus 5.5, GPT 6.1 Sol, GPT 6 Astra and Kimi K3.1 on coding, work, research and multimodal benchmarks
Qwen team chart across coding, work and long-horizon tasks; scores are from Alibaba's own evaluations. Source: Alibaba Qwen.
Token usage of Qwen4-Max against Qwen3.8-Max on Work360 and Terminal-Bench 4.0
Qwen team token efficiency chart on Work360 and Terminal-Bench 4.0. Source: Alibaba Qwen.
Qwen4-Max architecture with GDN and QSA layers, four Gated Residual branches and N-gram Embedding
Qwen4 architecture diagram from the launch blog. Source: Alibaba Qwen.

Looking for the full catalog? Browse all models.