modelgrep
Q

Qwen: Qwen3 235B A22B Thinking 2507

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

83rd smartest of 178Cheaper than 82% of paidReasoningToolsJSON
Use via OpenRouter ↗
Intelligence
29.5
83rd of 178
Design Elo
1097
Website
Speed
79
95th fastest
Latency
382ms
first token
Input price
$0.100
55th cheapest
Context
262K
262K max out

How it compares

Smarter than53%
of all ranked models
Faster than68%
of all ranked models
Cheaper than82%
of all ranked models

Overview

Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...

Benchmarks

independent · via OpenRouter
Artificial Analysis52th percentile
Intelligence Index
29.5
Coding Index
23.2
Agentic Index
29.7
GPQA Diamond
79%
Humanity's Last Exam
15%
SciCode
42%
Tau²-Bench (agentic)
53%
Design Arena · Elo2,908 tournaments
Website
1097
codecategories
1085
3D
1080
Game Dev
1027
UI Component
999
Data Viz
991

Providers & pricing (5)

ProviderIn $/MOut $/MUptime
WandBbf16$0.100$0.100100%
Alibaba$0.149$1.5099.1%
DeepInfrafp8$0.230$2.30
AtlasCloudfp8$0.280$2.3099.4%
Novitafp8$0.300$3.00

Specifications

Context window262K
Max output262K
Knowledge cutoffJun 2025
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price$0.100/M
ModeratedNo

Qwen3 235B A22B Thinking 2507 FAQ

How much does Qwen3 235B A22B Thinking 2507 cost?

Qwen3 235B A22B Thinking 2507 costs $0.100 per million input tokens and $0.100 per million output tokens via OpenRouter, making it 55th cheapest of 298 paid models.

How smart is Qwen3 235B A22B Thinking 2507?

Qwen3 235B A22B Thinking 2507 scores 29.5 on the Artificial Analysis Intelligence Index, ranking 83rd of 178 benchmarked models, with a GPQA Diamond score of 79%.

How fast is Qwen3 235B A22B Thinking 2507?

Qwen3 235B A22B Thinking 2507 generates around 79 tokens per second with 382ms time-to-first-token (p50), the 95th fastest tracked model.

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

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

Compare head-to-head