Qwen3 Coder 30B

ServerlessDedicated
Hugging Face IDQwen/Qwen3-Coder-30B-A3B-InstructView on Hugging Face ↗

Qwen3 Coder 30B is Alibaba's open coding model for agentic coding, browser use and repository-scale work. It's a 30.5B-parameter mixture of experts with 3.3B active per token and 262,144 tokens of native context, up to 1M with YaRN.

Ways to run Qwen3 Coder 30B

Dedicated endpoint

Get a quote →

Your own GPUs, tuned for your traffic. We profile your workload, tune the deployment and put throughput and latency in your contract.

Serverless

API docs →

Pay per token on shared GPUs, with no capacity to plan or reserve.

Inside your network

Security →

Run a dedicated endpoint inside your own network, including air-gapped environments.

Pricing

Dedicated endpoint
Per GPU-hour
We size the GPUs to your traffic.
Serverless
$0.0125 / $0.05
Per 1M tokens (input/output)

Use it with the agents we set up for you

Point any open-source agent at your endpoint, or pick from our catalog and we set it up as part of your contract.

Cline CodingOpenCode CodingAider Coding
GPT Researcher ResearchRAGFlow DocumentsNanobrowser Browser

Qwen3 Coder 30B FAQ

How much does Qwen3 Coder 30B cost on Saturn Cloud?

Serverless costs $0.0125 per 1M input tokens and $0.05 per 1M output tokens. A dedicated endpoint is priced per GPU-hour for the GPUs it runs on, and we size the GPUs to your traffic.

What is Qwen3 Coder 30B's context length?

262,144 tokens natively, up to 1M with YaRN.

Does Qwen3 Coder 30B support tool calling?

Yes, through Qwen’s function call format and the standard tools parameter.

Which coding agents work with Qwen3 Coder 30B?

Qwen names Qwen Code and Cline. Cline is also in our agent catalog, and we can set it up as part of your contract.

What sampling settings does Qwen recommend?

Temperature 0.7, top_p 0.8, top_k 20 and repetition_penalty 1.05, with up to 65,536 output tokens.