Loading page
LightweightOpen SourceAlibaba
Qwen 3 Coder 30B
Qwen 3 Coder 30B is Alibaba's lightweight open-source coding model with tool calling support and a 128K token context window.
Context 128K
Tier Lightweight
Tools Supported
License Open Source
Input from
$0.070 / 1M tokens
across 7 providers
API Pricing
Cheapest on Novita AI — 68% below avg| Provider | Input / 1M | Output / 1M | Cached / 1M |
|---|---|---|---|
| $0.070 | $0.270 | - | |
| $0.075 | $0.300 | - | |
| $0.120 | $0.800 | $0.070 | |
| $0.150 | $0.600 | - | |
| $0.232 | $0.930 | - | |
| $0.300 | $1.00 | $0.100 | |
| $0.300 | $1.00 | - | |
| $0.500 | $1.20 | - |
Prices updated daily. Last check: Sep 6, 2026
Qwen 3 Coder 30B pricing by provider
Input, output, and batch rates, plus alternatives, for one provider at a time.
Performance & Benchmarks
Source: Artificial Analysis →Intelligence
14.3 / 100
Coding
36.2 / 100
Output Speed
116 t/s
Latency (TTFT)
910ms
Reasoning & Knowledge
- GPQA Diamond73.7%
- Humanity's Last Exam10.1%
Agentic & Tool Use
- Terminal-Bench Hard18.2%
- Terminal-Bench v2.138.2%
- τ²-bench79.5%
- τ-bench Banking5.4%
Instruction & Long Context
- IFBench35.2%
- Long-Context Reasoning47.0%
Benchmarks measured Sep 2026. Scores are independent evaluations, not vendor-reported.
Model Details
General
- Creator
- Alibaba
- Family
- Qwen
- Tier
- Lightweight
- Context Window
- 128K
- Modalities
- Text
Capabilities
- Tool Calling
- Yes
- Open Source
- Yes
- Subtypes
- Chat Completion, Code Generation
- Aliases
- qwen3-coder-30b-a3b, qwen3-coder-next, qwen3-coder-480b-a35b, qwen3-coder
Strengths & Limitations
Strengths
- Open-source model weights available for local deployment and customization
- Tool calling support enables integration with development environments and APIs
- 128K token context window accommodates large codebases and documentation
- Specialized for code generation and programming tasks
- Output speed of 27.76 tokens per second for responsive interactions
- Lightweight 30B parameter count reduces computational requirements
- Streaming responses support real-time coding assistance applications
Limitations
- Text-only modalities - no support for image or multimodal inputs
- Lightweight tier may have reduced reasoning capabilities compared to frontier coding models
- Time to first token of 1,494ms slower than some competing models
- Narrower focus on coding may limit general-purpose language capabilities
Key Features
•128K token context window
•Tool calling with structured output support
•Streaming response generation
•Code generation and completion
•Chat-based programming assistance
•Open-source model weights
•Text-based input and output
•API integration capabilities
About Qwen 3 Coder 30B
Qwen 3 Coder 30B is a lightweight coding-focused model developed by Alibaba as part of the Qwen family. Positioned as an efficient coding specialist, this 30-billion parameter model is designed for code generation and programming tasks while maintaining faster inference speeds compared to larger models in the family.
The model supports text-based chat completion and code generation with a 128K token context window, allowing it to work with substantial codebases and documentation. It includes tool calling capabilities and provides streaming responses, making it suitable for interactive coding applications. Performance benchmarks show an output speed of 27.76 tokens per second with a time to first token of 1,494 milliseconds.
As an open-source model, Qwen 3 Coder 30B appeals to developers who need coding assistance without the computational overhead of frontier models. Its lightweight tier positioning makes it practical for applications requiring frequent code generation, automated programming tasks, and integration into development workflows where response speed matters.
Common Use Cases
Qwen 3 Coder 30B is well-suited for development teams and individual programmers who need efficient coding assistance without the overhead of larger models. Its 128K context window makes it effective for code review, debugging sessions with large files, and generating code that needs to integrate with existing codebases. The tool calling capabilities enable integration into IDEs, automated testing frameworks, and CI/CD pipelines. Its lightweight nature makes it practical for high-frequency coding tasks like code completion, documentation generation, and automated refactoring where speed matters more than the most advanced reasoning capabilities.
Frequently Asked Questions
How much does Qwen 3 Coder 30B cost per million tokens?
Qwen 3 Coder 30B pricing varies by provider and deployment type (hosted API vs self-hosted). Check the pricing table above for current rates across all available providers.
What is Qwen 3 Coder 30B best used for?
Qwen 3 Coder 30B excels at code generation, programming assistance, and development workflow integration. Its 128K context window and tool calling capabilities make it ideal for code review, debugging, automated testing, and IDE integration where you need efficient coding help without the computational cost of larger models.
Can I run Qwen 3 Coder 30B locally or do I need to use an API?
Since Qwen 3 Coder 30B is open-source, you can download and run the model weights locally if you have sufficient hardware resources. Alternatively, several cloud providers offer hosted API access. Local deployment gives you full control and privacy, while API access provides easier setup and scaling.