Qwen3.8 2.4T A95B
- Released
- Aug 12, 2026
- Tracked since
- 2026-08-14
Intelligence index39.9Ranks 45 of 664 models with this metric
Coding index71.9Ranks 40 of 259 models with this metric
Agentic index50.1Ranks 21 of 156 models with this metric
Capability profile
5 axes vs. site averageQwen3.8 2.4T A95B
Site average
Pricing
per 1M tokens- Input
- $2.00
- Output
- $6.00
- Cache read
- $0.250
Performance
- Output throughput
- 40 tokens/sec
- Time to first token
- 2.66s
- First answer token
- 53.11s
- End-to-end response
- 65.73s
History
5Intelligence index
57.7→39.9
Output
Unchanged across 62 days of records
Output throughput
50→40
Cheaper at this level
Models with a comparable intelligence index and a lower output price- Qwen3.8-Flash-Next
AlibabaIntelligence 39.8$0.470−92%
- GLM 5.3 Flash
Z AIIntelligence 41.8$0.500−92%
- MiMo-V2.6-Pro
XiaomiIntelligence 46.3$0.870−86%
- DeepSeek V4.1 Flash (Reasoning, Max Effort)
DeepSeekIntelligence 39.5$1.20−80%
- Step 5 Preview
StepFunIntelligence 43.7$2.70−55%