Requesty
Sign in

identity

endpoint
Alibaba Cloud logo

qwen3-maxAlibaba Cloud

in /1M$0.86input tokens
out /1M$3.44output tokens
context262K66K out
trainingnoon your prompts
api
chat
hosting
Singapore
model lab
Alibaba (Qwen)
weights
closed
added
September 2025
model id
alibaba/qwen3-max

capabilities 4/8

visionreasoningtoolscachingweb searchjson schemacomputer useimage gen

2 providers serve qwen3-max. This page is one of them. Compare all endpoints

pricing

no markup
input
$0.86
output
$3.44
cache write
-
cache read
-

worked cost

Estimated cost for three request volumes
volumecost
100K in + 10K out$0.12
1M in + 100K out$1.21
10M in + 1M out$12.05

Requesty charges what the upstream provider charges, with no markup and no per-request fee. Prompt caching and smart routing cut the effective cost further on repeated context. Gateway pricing

provider price, passed throughper 1M tokens

measured

through Sep 12

no measured traffic for this endpoint yet. pricing above is the provider's own

benchmarks

artificial analysis
Benchmark scores, each normalised to 100
evalScore as a share of 100/100
GPQA Diamond86.1
τ²-Bench83.6
Humanity's Last Exam28.0
Terminal-Bench Hard24.2
Intelligence Index21.3
5 evalsmean48.6

Scores from Artificial Analysis and public leaderboards, normalised to 100. Bar colour is the band, not the rank: green 80 and up, blue 55 and up, amber 30 and up. Benchmarks measure narrow skills, so test on your own workload before committing. Released 2026-01-26.

policy

data terms
retention
none
trains on prompts
no
hosted in
Singapore

Terms are the provider's, not Requesty's: routing a request here puts it under them. Alibaba Cloud Privacy Policy

Need every request to stay in one jurisdiction? EU hosting routes only through EU-hosted providers.

quickstart

openai compatible
alibaba/qwen3-max

this id pins the alibaba cloud deployment, with no routing and no failover. the managed id on the canonical page routes across all 2 providers instead

main.py
from openai import OpenAI client = OpenAI(    api_key="YOUR_REQUESTY_API_KEY",    base_url="https://router.requesty.ai/v1",) response = client.chat.completions.create(    model="alibaba/qwen3-max",    messages=[        {"role": "user", "content": "Explain quantum computing in one paragraph."},    ],) print(response.choices[0].message.content)

Change the base url to https://router.requesty.ai/v1, use your Requesty key, set the model to the id above. Existing OpenAI SDK code needs no other edit, and the same key reaches every other model in the catalog. Browse all models

notes

reference

This is the best-performing model in the Qwen series. It is ideal for complex, multi-step tasks.

questions 6

How much does qwen3-max cost?
qwen3-max is priced at $0.86 per million input tokens and $3.44 per million output tokens when accessed via Requesty. Prompt caching is supported, which can cut effective input cost by up to 90% on repeated context. Requesty charges exactly what the upstream provider charges, we don't add markup.
What is the context window of qwen3-max?
qwen3-max has a context window of 262K tokens, with a maximum output of 66K tokens per response. That is roughly 350 words of input you can fit in a single prompt.
How does qwen3-max perform on benchmarks?
qwen3-max scores 86.1% on GPQA Diamond, 83.6% on τ²-Bench, 28.0% on Humanity's Last Exam. The benchmarks pane shows every published result, each normalised to 100.
What can qwen3-max do?
qwen3-max supports vision input, tool calling, prompt caching, structured outputs (JSON schema). You can call it through any OpenAI-compatible client by pointing base_url to Requesty.
How do I use qwen3-max with the OpenAI SDK?
Install the OpenAI SDK, set base_url to "https://router.requesty.ai/v1", set your API key to your Requesty key, and set the model to "alibaba/qwen3-max". The quickstart pane shows Python, JavaScript and cURL snippets.
Can I run qwen3-max through Requesty?
Yes. qwen3-max runs through Requesty's OpenAI-compatible API, served from Alibaba Cloud. You do not host the model yourself: point base_url at Requesty, set the model to "alibaba/qwen3-max", and requests are routed to the upstream provider with automatic failover. The same key gives you 600+ other models too.

more from alibaba cloud 8

Other Alibaba Cloud endpoints
endpointctxin /M
qwen3.8-flash1.0M$0.16
qwen3.8-max1.0M$2.00
qwen3.7-plus1.0M$0.32
qwen3.7-max1.0M$2.50
qwen3.6-plus1M$0.50
qwen3-coder-plus1.0M$1.00
qwen3-coder-flash1.0M$0.30
qwen3-30b-a3b-instruct-2507131K$0.20

call qwen3-max through one endpoint

One key for this endpoint and 600+ other models. No markup on provider prices, automatic failover when a provider degrades, and prompt caching built in. Methodology

qwen3-maxalibaba cloudin $0.86 /1Mout $3.44 /1Mctx 262Khosted Singapore2 providers serve this model