Last refreshed 2026-11-16. Next refresh: weekly.
Why use Qwen4-Max on Vercel AI Gateway?
Vercel AI Gateway offers Qwen4-Max with pay-as-you-go pricing at $1.50/1M input tokens. Vercel AI Gateway is a unified AI proxy providing a single OpenAI-compatible API endpoint to 275+ models from 25+ providers including Anthropic, OpenAI, Google, Meta, Mistral, DeepSeek, xAI, Alibaba, Amazon, ByteDance, Cohere, MiniMax, MoonshotAI, KwaiPilot, Black Forest Labs, Recraft, Voyage AI, NVIDIA, and more.
Compare Qwen4-Max across 6 providers to find the best fit for your use caseSetup recipe
Python + curlpip install openaiexport AI_GATEWAY_API_KEY=...import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["AI_GATEWAY_API_KEY"],alibaba/qwen4-maxRequest example
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["AI_GATEWAY_API_KEY"],
base_url="https://ai-gateway.vercel.sh/v1"
)
response = client.chat.completions.create(
model="alibaba/qwen4-max",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Gotchas
- Use provider model ID "alibaba/qwen4-max", not the LLMReference slug "qwen4-max".
- creator/model-name e.g. kwaipilot/kat-coder-pro-v2
- The examples expect AI_GATEWAY_API_KEY; rename it only if your application config maps the new variable.
Compare Qwen4-Max Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Alibaba Cloud PAI-EAS | $1.50 | $4.50 |
| OpenRouter | $1.50 | $4.50 |
| Vercel AI Gateway | $1.50 | $4.50 |
| DeepInfra | $1.41 | $4.24 |
| Novita AI | $1.41 | $4.24 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $1.50 |
| Output tokens | $4.50 |
Capabilities
About Qwen4-Max
Qwen4-Max is the first production model in Alibaba's Qwen4 series and the general-availability successor to Qwen4-Max-Preview, with pay-as-you-go API access on Alibaba Cloud Model Studio. The Qwen team describes a new sparse MoE architecture with a 2.4-trillion-parameter backbone, 71B parameters activated per token and an additional 328B N-gram embedding parameters, with native vision. It takes text, image and video input and returns text, with a 1,000,000-token context window, deep thinking at low, high and xhigh effort, parallel tool calling, web search, structured output, and explicit and implicit caching, over OpenAI- and Anthropic-compatible APIs.