# Qwen3 30B A3B

Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique ability to switch seamlessly between a thinking mode for complex reasoning and a non-thinking mode for efficient dialogue ensures versatile, high-quality performance.

Significantly outperforming prior models like QwQ and Qwen2.5, Qwen3 delivers superior mathematics, coding, commonsense reasoning, creative writing, and interactive dialogue capabilities. The Qwen3-30B-A3B variant includes 30.5 billion parameters (3.3 billion activated), 48 layers, 128 experts (8 activated per task), and supports up to 131K token contexts with YaRN, setting a new standard among open-source models.

## Model Information

- **Organization**: [qwen](/llm.txt)
- **Slug**: qwen3-30b-a3b
- **Available at Providers**: 28
- **Release Date**: April 29, 2025

### Benchmark Scores
- AIME 2025: 0.709
- GPQA: 0.658

## Providers

| Provider | Name | $ Input (per 1M) | $ Output (per 1M) | Free | Link |
|----------|------|-----------------|------------------|------|------|
| [AIHubMix](/llm/aihubmix.txt) | Qwen3-30B-A3B | 1.00 | 1.00 |  | [View](https://aihubmix.com/model/Qwen/Qwen3-30B-A3B) |
| [AIHubMix](/llm/aihubmix.txt) | qwen3-30b-a3b | 0.12 | 1.20 |  | [View](https://aihubmix.com/model/qwen3-30b-a3b) |
| [Chutes.ai](/llm/chutes.txt) | Qwen3-30B-A3B | 0.06 | 0.22 |  |  |
| [FastRouter](/llm/fastrouter.txt) | Qwen: Qwen3 30B A3B | 0.08 | 0.29 |  | [View](https://fastrouter.ai/models/Qwen/Qwen3-30B-A3B) |
| [Helicone](/llm/helicone.txt) | Qwen3 30B A3B | 0.08 | 0.29 |  | [View](https://www.helicone.ai/model/qwen3-30b-a3b) |
| [Nano-GPT](/llm/nanogpt.txt) | Qwen3 30B A3B |  |  |  |  |
| [OpenRouter](/llm/openrouter.txt) | Qwen3 30B A3B | 0.08 | 0.28 |  | [View](https://openrouter.ai/qwen/qwen3-30b-a3b-04-28) |
| [ValorGPT](/llm/valorgpt.txt) | Qwen3 30B A3B |  |  |  | [View](https://www.valorgpt.com/models/qwen-qwen3-30b-a3b) |
| [Yupp](/llm/yupp.txt) | Qwen3-30B-A3B (Chutes AI) |  |  |  |  |
| [Yupp](/llm/yupp.txt) | Qwen 3 30B A3B (OpenRouter) |  |  |  |  |
| [DeepInfra](/llm/deepinfra.txt) | Qwen3-30B-A3B | 0.08 | 0.28 |  |  |
| [LangDB](/llm/langdb.txt) | qwen3-30b-a3b |  |  |  | [View](https://langdb.ai/app/models) |
| [302.AI](/llm/302ai.txt) | Qwen3-30B-A3B | 0.11 | 1.08 |  |  |
| [Kilo Code](/llm/kilocode.txt) | Qwen: Qwen3 30B A3B | 0.06 | 0.22 |  |  |
| [GMI Cloud](/llm/gmi.txt) | Qwen3-30B-A3B | 0.08 | 0.25 |  |  |
| [Baidu AI Studio](/llm/baidu.txt) |  |  |  |  | [View](https://aistudio.baidu.com) |
| [Inference](/llm/inference.txt) |  |  |  |  |  |
| [Blackbox AI](/llm/blackboxai.txt) | Qwen: Qwen3 30B A3B | 0.08 | 0.29 |  |  |
| [Arena AI](/llm/arenaai.txt) |  |  |  |  |  |
| [Together AI](/llm/togetherai.txt) | Qwen3 30B A3b | 0.00 | 0.00 |  |  |
| [StreamLake](/llm/streamlake.txt) | Qwen3-30B-A3B | 0.11 | 0.43 |  |  |
| [NetMind](/llm/netmind.txt) | qwen-3-30b | 0.10 | 0.45 |  |  |
| [CometAPI](/llm/cometapi.txt) |  | 0.12 | 0.48 |  |  |
| [Qiniu](/llm/qiniuai.txt) | Qwen3 30B A3B |  |  |  |  |
| [ApiYI](/llm/apiyi.txt) | qwen3-30b-a3b |  |  |  |  |
| [WaveSpeed AI](/llm/wavespeed.txt) | qwen3-30b-a3b | 0.07 | 0.24 |  |  |
| [Writingmate](/llm/writingmate.txt) | Qwen: Qwen3 30B A3B |  |  |  | [View](https://writingmate.ai/models/qwen/qwen3-30b-a3b) |
| [LLM Stats](/llm/llmstats.txt) | Qwen3 30B A3B |  |  |  |  |

---

[← Back to all providers](/llm.txt)