Qwen 3 235B A22B Instruct

by Alibaba

Qwen 3 235B A22B instruct on Nebius (EU)

ToolsStructured output
Context window
262K
Max output
66K
Input price
$0.20 /1M
Output price
$0.60 /1M

Benchmarks

Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.

Global rank#193 of 505 LLMs
TierEfficient
Output speed68 tok/s
First token1.18s
Intelligence Index25.0
Coding Index22.1
Math Index71.7
MMLU-Pro
83%
GPQA Diamond
75%
Humanity's Last Exam
11%
LiveCodeBench
52%
SciCode
36%
AIME 2025
72%
IFBench
46%
Long-context reasoning
31%
Terminal-Bench Hard
15%
τ²-Bench Telecom
33%

Available routes

The same Qwen 3 235B A22B Instruct runs on 1 route through the Opper gateway. Each route has its own data-handling posture.

ProviderRegionZero data retentionTrainingLoggingContractInputOutput
NebiusEUOpt-inNo
Per privacy policy: only as long as necessary; specific window not published.
PAYG$0.20$0.60

Human review: Abuse-flagged only

Other models from Alibaba

Start building with 300+ models

One API key. Every major provider. Up and running in minutes.

Get startedView Documentation
Qwen 3 235B A22B Instruct by Alibaba — pricing, benchmarks, hosting routes | Opper AI