Qwen3 30B A3B
by Alibaba
Prices last updated November 22, 2026
Qwen3 30B A3B, an open-weight Alibaba model available via OpenRouter.
Price Comparison
Compare pricing across 8 providers serving Qwen3 30B A3B
| Provider | Input $/1M | Output $/1M | Context | Speed | TTFT | Status |
|---|---|---|---|---|---|---|
Cloudflare Workers AI | $0.051 ● | $0.335 | — | — | — | Live |
| SY Synap by Linkrra | $0.081 | $0.244 | — | — | — | Live |
Nebius | $0.100 | $0.300 | 262k | — | — | Live |
Infron | $0.100 | $0.300 | 262k | — | — | Live |
OpenRouter | $0.120 | $0.500 | 41k | — | — | Live |
DeepInfra | $0.120 | $0.500 | 41k | — | — | Live |
Infron | $0.120 | $0.480 | 41k | — | — | Live |
Alibaba Cloud | $0.200 | $0.800 | — | — | — | Live |
Benchmarks
Independent results for Qwen3 30B A3B, as each source publishes them. Where a source tested several versions (effort levels, thinking modes, dated snapshots), the best one is shown and named under "As tested". Scores from different sources use different scales and aren't comparable with each other.
| Benchmark | Score | Rank | As tested |
|---|---|---|---|
| Overall | |||
Epoch Capabilities IndexEpoch AI One score combining a model's results across many benchmarks, on a common scale. | 138.3±2.5 | #133 of 258 | Qwen3-30B-A3B-Thinking (Jul 2025) |
| Reasoning | |||
GPQA DiamondEpoch AI Graduate-level multiple-choice questions in biology, physics and chemistry, written to be hard to look up. | 70.1%±5.6 | #122 of 232 | qwen3-30b-a3b-thinking-2507 Aug 2026 |
| Math | |||
OTIS Mock AIMEEpoch AI Competition maths problems from the OTIS mock AIME exams (2024-2025). | 70.3%±11.8 | #113 of 215 | qwen3-30b-a3b-thinking-2507 Aug 2026 |
| Coding | |||
Text Arena: CodingLMArena Text Arena votes on coding prompts only. | 1,438±9 4,604 votes | #180 of 421 | Qwen3-30B-A3B-Instruct (2507) Nov 2026 |
| Chat | |||
Text ArenaLMArena Human votes on chat answers across all kinds of prompts (style-controlled). | 1,382±5 23,267 votes | #198 of 426 | Qwen3-30B-A3B-Instruct (2507) Nov 2026 |
Epoch AI: Epoch runs each benchmark itself on the models it evaluates, with the same harness for every model. The Epoch Capabilities Index combines many benchmarks into one score. Data: Epoch AI, 'Capabilities & benchmarking', epoch.ai/benchmarks (CC BY 4.0).
LMArena: People compare two anonymous models side by side and vote for the better answer; ratings come from those votes (Bradley-Terry, style-controlled for text and vision). Data: LMArena (arena.ai) leaderboard dataset (CC BY 4.0).
Rank is among all models the source ranks, including ones we don't list.