# Qwen3-Coder 30B-A3B Instruct

Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the Qwen3 architecture, it supports a native context length of 256K tokens (extendable to 1M with Yarn) and performs strongly in tasks involving function calls, browser use, and structured code completion.

This model is optimized for instruction-following without “thinking mode”, and integrates well with OpenAI-compatible tool-use formats. 

## Model Information

- **Organization**: [Alibaba](/llm.txt)
- **Slug**: qwen3-coder-30b-a3b-instruct
- **Available at Providers**: 26
- **Release Date**: July 31, 2025

## Providers

| Provider | Name | $ Input (per 1M) | $ Output (per 1M) | Free | Link |
|----------|------|-----------------|------------------|------|------|
| [AIHubMix](/llm/aihubmix.txt) | qwen3-coder-30b-a3b-instruct | 0.20 | 0.80 |  | [View](https://aihubmix.com/model/qwen3-coder-30b-a3b-instruct) |
| [Helicone](/llm/helicone.txt) | Qwen3 Coder 30B A3B Instruct | 0.10 | 0.30 |  | [View](https://www.helicone.ai/model/qwen3-coder-30b-a3b-instruct) |
| [Alibaba](/llm/alibaba.txt) | Qwen3-Coder 30B-A3B Instruct | 0.45 | 2.25 |  |  |
| [Alibaba (China)](/llm/alibabacn.txt) | Qwen3-Coder 30B-A3B Instruct | 0.22 | 0.86 |  |  |
| [Novita AI](/llm/novita.txt) | qwen3-coder-30b-a3b-instruct | 0.07 | 0.27 |  |  |
| [SiliconFlow (China)](/llm/siliconflowcn.txt) | Qwen/Qwen3-Coder-30B-A3B-Instruct | 0.07 | 0.28 |  |  |
| [SiliconFlow](/llm/siliconflow.txt) | Qwen3-Coder-30B-A3B-Instruct | 0.07 | 0.28 |  | [View](https://www.siliconflow.com./models/qwen3-coder-30b-a3b-instruct) |
| [OVHcloud AI Endpoints](/llm/ovhcloud.txt) | Qwen3-Coder-30B-A3B-Instruct | 0.07 | 0.26 |  |  |
| [ModelScope](/llm/modelscope.txt) | Qwen3 Coder 30B A3B Instruct | 0.00 | 0.00 | Yes |  |
| [Scaleway](/llm/scaleway.txt) | Qwen3-Coder 30B-A3B Instruct | 0.20 | 0.80 |  |  |
| [Nano-GPT](/llm/nanogpt.txt) | Qwen3 Coder 30B A3B Instruct |  |  |  |  |
| [OpenRouter](/llm/openrouter.txt) | Qwen3 Coder 30B A3B Instruct | 0.07 | 0.27 |  | [View](https://openrouter.ai/qwen/qwen3-coder-30b-a3b-instruct) |
| [ValorGPT](/llm/valorgpt.txt) | Qwen3 Coder 30B A3B Instruct |  |  |  | [View](https://www.valorgpt.com/models/qwen-qwen3-coder-30b-a3b-instruct) |
| [Yupp](/llm/yupp.txt) | Qwen3-Coder-30B-A3B-Instruct (OpenRouter) |  |  |  |  |
| [Yupp](/llm/yupp.txt) | Qwen3-Coder-30B-A3B-Instruct |  |  |  |  |
| [Nebius Token Factory](/llm/nebius.txt) | Qwen3-Coder-30B-A3B-Instruct | 0.10 | 0.30 |  | [View](https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct) |
| [LangDB](/llm/langdb.txt) | qwen3-coder-30b-a3b-instruct |  |  |  | [View](https://langdb.ai/app/models) |
| [Kilo Code](/llm/kilocode.txt) | Qwen: Qwen3 Coder 30B A3B Instruct | 0.07 | 0.27 |  |  |
| [302.AI](/llm/302ai.txt) | qwen3-coder-30b-a3b-instruct | 0.22 | 0.86 |  | [View](https://302ai-en.apifox.cn/207705113e0) |
| [Baidu AI Studio](/llm/baidu.txt) |  |  |  |  | [View](https://aistudio.baidu.com) |
| [302.AI](/llm/302ai.txt) | Qwen/Qwen3-Coder-30B-A3B-Instruct | 0.10 | 0.40 |  | [View](https://302ai-en.apifox.cn/api-252564719) |
| [Together AI](/llm/togetherai.txt) | Qwen3 Coder 30B A3b Instruct | 0.00 | 0.00 |  |  |
| [NetMind](/llm/netmind.txt) | qwen-3-code | 0.04 | 0.17 |  |  |
| [Blackbox AI](/llm/blackboxai.txt) | blackboxai/qwen/qwen3-coder-30b-a3b-instruct |  |  |  |  |
| [WaveSpeed AI](/llm/wavespeed.txt) | qwen3-coder-30b-a3b-instruct | 0.08 | 0.30 |  |  |
| [Writingmate](/llm/writingmate.txt) | Qwen: Qwen3 Coder 30B A3B Instruct |  |  |  | [View](https://writingmate.ai/models/qwen/qwen3-coder-30b-a3b-instruct) |

---

[← Back to all providers](/llm.txt)