modelhub.help

Qwen 2.5 Max

Alibaba Cloud

33K context · — params · —

alibaba/qwen2-5-max

Alibaba's closed-weight Qwen 2.5 Max flagship — MoE architecture trained for top-tier reasoning and coding performance. Competes with GPT-4o / Claude Sonnet on Chinese + English benchmarks.

Official Path Verified AWS Bedrock Azure AI Alibaba Cloud Intl (ap-southeast-1, us-east-1) Intl card
Cheapest blended: ¥2.8 / 1M tokens on Alibaba Cloud DashScopeGet custom quote

Reachability & verification

Live reachability

Probing…

Target (Alibaba Cloud DashScope): https://dashscope.aliyun.com

Overseas reference latency (est.)

Singapore 90 ms London 160 ms

Live reachability probe

Measured in real time from the ModelHub gateway egress to this model's API endpoint. Green means reachable right now. Overseas reference latencies are estimates; the live probe is the proof of current reachability.

Official Path Verified by ModelHub

Pricing across providers

1

Prices are shown in each provider's billing currency — ¥ (CNY) for Chinese providers, $ (USD) for overseas gateways.

ProviderInput /1MOutput /1MBlendedCtxp50 latencyAPIVerified
Alibaba Cloud DashScopeqwen-max-2025-01-25¥1.6¥6.4¥2.833K OAI139d ago

Works with

CursorClineAiderContinueOpenCodeOpen WebUI

Any OpenAI-compatible client works — point the base URL at the provider endpoint.

Capabilities

chatreasoningcodemath

Languages: en, zh

Technical specs

Context

33K

Max output

8K

Parameters

Release

Training cutoff

License

Similar models

Frequently asked questions

How much does Qwen 2.5 Max cost?

The cheapest tracked blended price is ¥2.8 per 1M tokens on Alibaba Cloud DashScope. See the pricing matrix above for input/output splits per provider.

Can I use Qwen 2.5 Max from outside China?

Availability depends on the hosting provider. Use our Path Planner on the Alibaba Cloud DashScope page to map a verified official-vs-brokered access path, including payment and KYC constraints.

Is Qwen 2.5 Max open source?

No — Qwen 2.5 Max is a proprietary hosted model, available only through APIs.

Is Qwen 2.5 Max OpenAI-compatible?

Yes — at least one tracked provider exposes an OpenAI-compatible endpoint, so Cursor, Cline, Aider and similar clients work with just a base-URL change.

What is the maximum context window?

Qwen 2.5 Max supports up to 33K tokens of context with a maximum output of 8K tokens.

Need verified access to Qwen 2.5 Max?

We broker vetted intros to Alibaba Cloud DashScope — payment, KYC and endpoint verification handled.

Request a brokerage intro