Alibaba Cloud / Qwen Team model product
Qwen3 30B A3B
3 billion activated parameters.
Updated Aug 17, 2026. Default version: Qwen3 30B A3B
LLMBoard Score28.2Qwen3 30B A3B
Coverage80%8 benchmark families
Context window131.1KTokens
Official input priceN/AOfficial price unavailable
Qwen3 30B A3B Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Qwen3 30B A3B Benchmark Results
Benchmark scores for Qwen3 30B A3B.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkArena Hard | Score91.0% | Rank03 | Participants26 | Percentile92.0% | EvidenceC | Evaluated |
| BenchmarkBFCL | Score69.1% | Rank07 | Participants11 | Percentile40.0% | EvidenceC | Evaluated |
| BenchmarkMulti-IF | Score72.2% | Rank14 | Participants23 | Percentile40.9% | EvidenceC | Evaluated |
| BenchmarkLiveBench | Score74.3% | Rank18 | Participants38 | Percentile54.0% | EvidenceC | Evaluated |
| BenchmarkAIME 2024 | Score80.4% | Rank27 | Participants53 | Percentile50.0% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench | Score62.6% | Rank33 | Participants75 | Percentile56.8% | EvidenceC | Evaluated |
| BenchmarkAIME 2025 | Score70.9% | Rank87 | Participants115 | Percentile24.6% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score65.8% | Rank152 | Participants239 | Percentile36.5% | EvidenceC | Evaluated |
Qwen3 30B A3B Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext | Categoryoverall | Rank145 | Rating / score1384.2 | Votes23,838 | ObservationsN/A | Result date |
| Arenatext style control | Categoryoverall | Rank161 | Rating / score1383.3 | Votes23,838 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank213 | Rating / score1317.0 | Votes26,562 | ObservationsN/A | Result date |
| Arenatext style control | Categoryoverall | Rank225 | Rating / score1327.1 | Votes26,562 | ObservationsN/A | Result date |
Qwen3 30B A3B Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- From $0.08 input, $0.29 output per 1M via Helicone
- Tracked offerings
- 12
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderHelicone | Provider model IDqwen3-30b-a3b | Regionglobal | Input / 1M$0.08 | Output / 1M$0.29 | Context41K | Updated |
| ProviderJiekou.AI | Provider model IDqwen/qwen3-30b-a3b-fp8 | Regionglobal | Input / 1M$0.09 | Output / 1M$0.45 | Context41K | Updated |
| ProviderNovitaAI | Provider model IDqwen/qwen3-30b-a3b-fp8 | Regionglobal | Input / 1M$0.09 | Output / 1M$0.45 | Context41K | Updated |
| ProviderNanoGPT | Provider model IDqwen/qwen3-30b-a3b | Regionglobal | Input / 1M$0.10 | Output / 1M$0.30 | Context41K | Updated |
| ProviderMerge Gateway | Provider model IDqwen/qwen3-30b-a3b | Regionglobal | Input / 1M$0.108 | Output / 1M$1.08 | Context131.1K | Updated |
| Provider302.AI | Provider model IDqwen3-30b-a3b | Regionglobal | Input / 1M$0.11 | Output / 1M$1.08 | Context128K | Updated |
| ProviderDeep Infra | Provider model IDQwen/Qwen3-30B-A3B | Regionglobal | Input / 1M$0.12 | Output / 1M$0.50 | Context41K | Updated |
| ProviderHugging Face | Provider model IDQwen/Qwen3-30B-A3B | Regionglobal | Input / 1M$0.12 | Output / 1M$0.50 | Context41K | Updated |
| ProviderVercel AI Gateway | Provider model IDalibaba/qwen-3-30b | Regionglobal | Input / 1M$0.12 | Output / 1M$0.50 | Context41K | Updated |
| ProviderOpenRouter | Provider model IDqwen/qwen3-30b-a3b | Regionglobal | Input / 1M$0.13 | Output / 1M$0.52 | Context131.1K | Updated |
| ProviderKilo Gateway | Provider model IDqwen/qwen3-30b-a3b | Regionglobal | Input / 1M$0.13 | Output / 1M$0.52 | Context131.1K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Qwen3 30B A3B Runtime Performance
Provider-specific output speed and catalog latency for Qwen3 30B A3B. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderFireworks | Output Speed122.4 tok/s | Catalog Latency0.66 s | Max Input128K | Max Output128K | Updated |
| ProviderNovita | Output Speed88.84 tok/s | Catalog Latency0.73 s | Max Input128K | Max Output128K | Updated |
| ProviderDeepInfra | Output Speed82.57 tok/s | Catalog Latency0.84 s | Max Input128K | Max Output128K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Qwen3 30B A3B Specifications
Technical details for the model's default version.
- Version
- Qwen3 30B A3B
- Released
- Apr 29, 2025
- Knowledge cutoff
- Unknown
- Parameters
- 30.5B
- Context window
- 131.1K
- Max output
- 16.4K
- Inputs
- text
- Outputs
- text
- Open weights
- Yes
- License
- Apache 2.0
Qwen3 30B A3B Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionQwen3 30B A3B | Released | LLMBoard28.2 | Parameters30.5B | Context131.1K | Max output16.4K | Open weightsYes | LicenseApache 2.0 |
Qwen3 30B A3B vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Qwen3 30B A3B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AC
Qwen3 VL 30B A3B
Alibaba Cloud / Qwen Team
AC
Qwen3 VL 8B Thinking
Alibaba Cloud / Qwen Team
AC
Qwen3 32B
Alibaba Cloud / Qwen Team
AC
Qwen3 VL 30B A3B Thinking
Alibaba Cloud / Qwen Team
AC
Qwen2 VL 72B
Alibaba Cloud / Qwen Team
AC
Qwen3.5 4B
Alibaba Cloud / Qwen Team
What is Qwen3 30B A3B?
Key information about Qwen3 30B A3B and its available data.
3 billion activated parameters. Features hybrid thinking/non-thinking modes, support for 119 languages, and enhanced agent capabilities. It aims to outperform previous models like QwQ-32B while using significantly fewer activated parameters.
Data as of 2026-08-17.
FAQ
Common questions about Qwen3 30B A3B.
When was Qwen3 30B A3B released?
Qwen3 30B A3B's default version was released on Apr 29, 2025.
How much does Qwen3 30B A3B cost?
No official standard PAYG price is currently available for Qwen3 30B A3B. The lowest tracked third-party offer starts at $0.08 input and $0.29 output via Helicone.
Who created Qwen3 30B A3B?
Qwen3 30B A3B was created by Alibaba Cloud / Qwen Team.
What is the context window for Qwen3 30B A3B?
The default version has a 131.1K token context window.
Is Qwen3 30B A3B open weight?
Yes. The default version is marked as open weight under Apache 2.0.
How many API providers offer Qwen3 30B A3B?
12 provider offerings are linked to the default version.
What models should I compare Qwen3 30B A3B with?
Nearby ranked alternatives include Kimi k1.5, Gemini 2.0 Flash Thinking, Ministral 3.