Novita

qwen/qwen3-235b-a22b-instruct-2507

Qwen/Qwen3-235B-A22B-Instruct-2507
Context

256K

Input

text, image

Output

text

Tool calling

Supported

About this model

Qwen3-235B-A22B-Instruct-2507 is Alibaba Cloud's frontier mixture-of-experts model featuring 235B total parameters with 22 specialized experts and 4 active per token. Designed for superhuman reasoning and multilingual mastery, it achieves state-of-the-art performance across technical, creative, and analytical domains with 256K context handling. Optimized for distributed inference across H100 GPU clusters.

Compare Text Models

Input modalities

text

Accepted as model input

image

Accepted as model input

Providers

Available routing options for this model through OneInfer.

Novita
Available

Input tokens

$0.150 / 1M tokens

Output tokens

$0.180 / 1M tokens

Routing

OneInfer optimized

Pricing

Current OneInfer pricing for this model.

UsagePrice
Input tokens$0.150 / 1M tokens
Output tokens$0.180 / 1M tokens

Performance

Published evaluation results associated with this model.

Superhuman Reasoning

MMMU68.3
GPQA57.6
TheoremQA49.7
Gaokao-Integrated92.4

Multilingual Mastery

XTREME-3.089.7
Flores-30085.3
CMMLU-Pro91.8

Technical Proficiency

HumanEval++89.4
MathVista72.6
DS-1000++84.9

API example

Refer Documentation
curl https://api.oneinfer.ai/v1/ula/chat/completions \
  -H "Authorization: Bearer $ONEINFER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Qwen/Qwen3-235B-A22B-Instruct-2507",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'