modelgrep
Q

Qwen: Qwen3 235B A22B Instruct 2507

qwen/qwen3-235b-a22b-2507

95th smartest of 180Cheaper than 85% of paidToolsJSON
Use via OpenRouter ↗
Intelligence
25.0
95th of 180
Design Elo
1103
Website
Speed
82
96th fastest
Latency
291ms
first token
Input price
$0.090
45th cheapest
Context
262K
16K max out

How it compares

Smarter than47%
of all ranked models
Faster than69%
of all ranked models
Cheaper than85%
of all ranked models

Overview

Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...

Benchmarks

independent · via OpenRouter
Artificial Analysis43th percentile
Intelligence Index
25.0
Coding Index
22.1
Agentic Index
22.8
GPQA Diamond
75%
Humanity's Last Exam
11%
SciCode
36%
Tau²-Bench (agentic)
33%
Design Arena · Elo3,206 tournaments
Website
1103
Data Viz
1102
codecategories
1090
3D
1075
UI Component
1023
Game Dev
1021

Providers & pricing (11)

ProviderIn $/MOut $/MUptime
DeepInfrafp8$0.090$0.10099.4%
Novitafp8$0.090$0.58099.9%
WandBbf16$0.100$0.100100%
Parasailfp8$0.140$0.80099.7%
Alibaba$0.149$0.598100%
Together$0.200$0.60093.5%
Friendli$0.200$0.80097.7%
AtlasCloudfp8$0.200$0.880100%
StreamLake$0.210$0.840100%
Google$0.220$0.880100%
Google$0.250$1.00100%

Specifications

Context window262K
Max output16K
Knowledge cutoffJun 2025
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price
ModeratedNo

Qwen3 235B A22B Instruct 2507 FAQ

How much does Qwen3 235B A22B Instruct 2507 cost?

Qwen3 235B A22B Instruct 2507 costs $0.090 per million input tokens and $0.100 per million output tokens via OpenRouter, making it 45th cheapest of 298 paid models.

How smart is Qwen3 235B A22B Instruct 2507?

Qwen3 235B A22B Instruct 2507 scores 25.0 on the Artificial Analysis Intelligence Index, ranking 95th of 180 benchmarked models, with a GPQA Diamond score of 75%.

How fast is Qwen3 235B A22B Instruct 2507?

Qwen3 235B A22B Instruct 2507 generates around 82 tokens per second with 291ms time-to-first-token (p50), the 96th fastest tracked model.

What is Qwen3 235B A22B Instruct 2507's context window?

Qwen3 235B A22B Instruct 2507 supports a 262K-token context window and can output up to 16K tokens. It accepts text input.

Compare head-to-head