qwen3-30b-a3b
Model ID
- Context
- 131.07K
- 8K max output
- Input price
- $0.11
- per 1M tokens · Alibaba Cloud Model Studio
- Output price
- $0.43
- per 1M tokens
- Epoch Capabilities Index
- 136.2
- #94 of 105 listed
- LMArena Text
- 1,327
- #134 of 149 listed
Where to run it
3 offerings · prices as listed| Meter | Tier | Price |
|---|---|---|
Alibaba Cloud Model Studio (opens in a new tab) qwen3-30b-a3b | ||
| Input | Standard | $0.11 / 1M tokens |
| Output | Standard | $0.43 / 1M tokens |
| Reasoning off | $0.43 / 1M tokens | |
| Reasoning on | $1.08 / 1M tokens | |
Alibaba Cloud Model Studio (opens in a new tab) qwen3-30b-a3b | ||
| Input | Standard | $0.20 / 1M tokens |
| Output | Standard | $0.80 / 1M tokens |
| Reasoning off | $0.80 / 1M tokens | |
| Reasoning on | $2.40 / 1M tokens | |
Alibaba Cloud Model Studio (opens in a new tab) qwen3-30b-a3b | ||
| Input | Standard | ¥0.75 / 1M tokens |
| Output | Reasoning off | ¥3.00 / 1M tokens |
| Reasoning on | ¥7.50 / 1M tokens | |
Changes
All changes →- Context window 256K → 131.07K
- Max output 8.19K → 16.38K
Cited scores
From third-party leaderboards, not measured by us- Epoch Capabilities Index 136.2
#94 of 105 listed models · CI 130.3–138.7
- LMArena Text 1,327
#134 of 149 listed models · CI 1,322–1,331 · 26,037 votes
- Epoch AI · GPQA Diamond 61.7%
#93 of 128 listed models · ±2.97
Also listed: reasoning off 50.4%
- LMArena Text · Chinese 1,360
#126 of 149 listed models · CI 1,344–1,375 · 1,560 votes
- LMArena Text · Coding 1,385
#131 of 149 listed models · CI 1,376–1,394 · 4,485 votes
- Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Oct 3, 2026
- LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Oct 2, 2026
- changes we made