Model specification · Qwen

Qwen3 30B A3B Thinking 2507

qwen/qwen3-30b-a3b-thinking-2507

Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated...

SpecificationsReported values
Context window
82K
Maximum output
33K
Architecture
text->text
Tokenizer
Qwen3
Knowledge cutoff
2025-06-30
Moderated
No
Input modalities
text
Output modalities
text
Full pricingUSD where reported
PriceStandard
Input$0.200 / M
Output$2.40 / M
Benchmark indexesReported indexes
Intelligence
9.8
Coding
12.1
Agentic
0.9
Design Arena Elo
941
Example workload costsStandard pricing only
WorkloadInput / outputCache shareEstimated cost
Quick check10K / 1K × 10%$0.00440
Long analysis100K / 4K × 150%$0.030
Workday20K / 2K × 1,00030%$8.80
More from QwenAll Qwen models
ModelContextInput / MOutput / MIntel.
Qwen3.8 Max (0902)1M$2.00$6.0045.4
Qwen3.8 2.4T A95B1.0M$2.00$6.0040
Qwen3.8 27B1M$0.214$2.5533.9
Qwen3.7 Max1M$1.48$4.4229.9
Qwen3.7 Plus1M$0.320$1.2825.8
Qwen3.6 27B262K$0.300$2.0021.9
Qwen3.5 397B A17B262K$0.550$3.5019.1
Qwen3.6 35B A3B262K$0.100$0.90018.8
Qwen3.5-122B-A10B262K$0.260$2.0816.2
Qwen3 235B A22B Thinking 2507131K$0.230$2.3012.7
Qwen3 Coder Next262K$0.120$0.80010.1
Qwen3 32B131K$0.080$0.2807.2