modelgrep
Q

Qwen: Qwen3 30B A3B

qwen/qwen3-30b-a3b

141st smartest of 178Cheaper than 78% of paidReasoningToolsJSON
Use via OpenRouter ↗
Intelligence
15.3
141st of 178
Design Elo
1011
Data Viz
Speed
95
72nd fastest
Latency
316ms
first token
Input price
$0.120
67th cheapest
Context
131K
16K max out

How it compares

Smarter than21%
of all ranked models
Faster than76%
of all ranked models
Cheaper than78%
of all ranked models

Overview

Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...

Benchmarks

independent · via OpenRouter
Artificial Analysis22th percentile
Intelligence Index
15.3
Coding Index
11.0
Agentic Index
12.1
GPQA Diamond
62%
Humanity's Last Exam
7%
SciCode
28%
Tau²-Bench (agentic)
26%
Design Arena · Elo1,184 tournaments
Data Viz
1011
UI Component
1003
Website
999
codecategories
994
Game Dev
967

Providers & pricing (3)

ProviderIn $/MOut $/MUptime
DeepInfrafp8$0.120$0.50099.8%
Alibaba$0.130$0.520100%
NextBitfp8$0.140$0.55068.5%

Specifications

Context window131K
Max output16K
Knowledge cutoffMar 2025
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price
ModeratedNo

Qwen3 30B A3B FAQ

How much does Qwen3 30B A3B cost?

Qwen3 30B A3B costs $0.120 per million input tokens and $0.500 per million output tokens via OpenRouter, making it 67th cheapest of 298 paid models.

How smart is Qwen3 30B A3B?

Qwen3 30B A3B scores 15.3 on the Artificial Analysis Intelligence Index, ranking 141st of 178 benchmarked models, with a GPQA Diamond score of 62%.

How fast is Qwen3 30B A3B?

Qwen3 30B A3B generates around 95 tokens per second with 316ms time-to-first-token (p50), the 72nd fastest tracked model.

What is Qwen3 30B A3B's context window?

Qwen3 30B A3B supports a 131K-token context window and can output up to 16K tokens. It accepts text input.

Compare head-to-head