AlibabaQwen3 Omni 30B A3B Instruct
- Released
- Sep 22, 2025
- Tracked since
- 2026-07-23
Intelligence index6Ranks 561 of 664 models with this metric
Coding index—Not tested
Agentic index—Not tested
Capability profile
5 axes vs. site averageQwen3 Omni 30B A3B Instruct
Site average
Some dimensions have no data yet — marked on the chart
Pricing
per 1M tokens- Input
- $0.250
- Output
- $0.970
Performance
- Output throughput
- 96 tokens/sec
- Time to first token
- 1.84s
- First answer token
- 1.84s
- End-to-end response
- 7.07s
History
2Intelligence index
5.1→6
Output
Unchanged across 62 days of records
Output throughput
93→96
Cheaper at this level
Models with a comparable intelligence index and a lower output price- Llama 3.1 Instruct 8B
MetaIntelligence 6.9$0.050−95% - Mistral Small 3
MistralIntelligence 6.7$0.080−92% - Gemma 4 E4B (Reasoning)
GoogleIntelligence 8.9$0.100−90% - Gemma 4 E4B (Non-reasoning)GoogleIntelligence 7.5$0.100−90%
- Granite 4.1 8B
IBMIntelligence 6.6$0.100−90%