Loading page
LightweightAlibaba
Qwen 3 30B
Qwen 3 30B is Alibaba's lightweight text-only model with a 262K token context window, optimized for efficient text processing tasks.
Context 262K
Tier Lightweight
Input from
$0.100 / 1M tokens
across 4 providers
API Pricing
Cheapest on Lyceum — 18% below avg| Provider | Input / 1M | Output / 1M |
|---|---|---|
| $0.100 | $0.300 | |
| $0.120 | $0.500 | |
| $0.120 | $0.500 | |
| $0.150 | $1.50 |
Prices updated daily. Last check: Sep 6, 2026
Qwen 3 30B pricing by provider
Input, output, and batch rates, plus alternatives, for one provider at a time.
Performance & Benchmarks
Source: Artificial Analysis →Intelligence
3.4 / 100
Math
66.3 / 100
Reasoning & Knowledge
- MMLU-Pro77.7%
- GPQA Diamond65.9%
- Humanity's Last Exam6.9%
Coding
- LiveCodeBench51.5%
Math
- AIME 202566.3%
- AIME72.7%
- MATH-50097.5%
Agentic & Tool Use
- Terminal-Bench Hard6.1%
- τ²-bench10.2%
Instruction & Long Context
- IFBench33.1%
- Long-Context Reasoning26.3%
Benchmarks measured Sep 2026. Scores are independent evaluations, not vendor-reported.
Model Details
General
- Creator
- Alibaba
- Family
- Qwen
- Tier
- Lightweight
- Context Window
- 262K
- Modalities
- Text
Capabilities
- Tool Calling
- No
- Open Source
- No
- Aliases
- qwen3-next-80b-a3b-thinking, qwen3-next-80b-a3b-instruct, qwen3-next-80b-a3b, qwen3-30b-a3b-thinking-2507, qwen3-30b-a3b-instruct-2507
Strengths & Limitations
Strengths
- Large 262,144 token context window for processing lengthy documents
- Fast generation speed at 73.23 tokens per second
- Lightweight architecture for efficient resource utilization
- Part of Alibaba's established Qwen model family
- Reasonable time to first token at 1,210 milliseconds
- Text-focused design optimized for language tasks
- Multiple deployment variants available through aliases
Limitations
- No tool calling or function execution capabilities
- Text-only modality without image or audio support
- Proprietary model with no open source availability
- Lightweight tier positioning limits complex reasoning capabilities
- No multimodal input processing
Key Features
•262,144 token context window
•Text input and output processing
•Streaming response generation
•Multiple model variants (instruct and thinking modes)
•Batch processing support
•API-based deployment
•Chinese and multilingual text support
•Document-length context handling
About Qwen 3 30B
Qwen 3 30B is a lightweight model from Alibaba's Qwen family, positioned as an efficient option for text-only processing tasks. As part of the Qwen 3 generation, it represents Alibaba's approach to balancing capability with computational efficiency in the lightweight tier.
The model features a 262,144 token context window and processes text-only inputs. Performance benchmarks show it generates approximately 73 tokens per second with a time to first token of 1,210 milliseconds. The model operates as a proprietary offering without tool calling capabilities, focusing on core text understanding and generation tasks.
Qwen 3 30B serves applications requiring efficient text processing without the computational overhead of larger models. Its extended context window makes it suitable for document analysis and longer conversations while maintaining faster response times compared to flagship-tier models in the Qwen family.
Common Use Cases
Qwen 3 30B is designed for applications requiring efficient text processing with extended context support. Its lightweight architecture makes it suitable for high-volume text classification, content summarization, document analysis, and conversational applications where speed and efficiency are priorities over complex reasoning. The large context window enables processing of lengthy documents, research papers, or extended conversations without context truncation. Organizations needing cost-effective text processing for customer support, content moderation, or document processing workflows can leverage its balance of capability and efficiency.
Frequently Asked Questions
How much does Qwen 3 30B cost per million tokens?
Qwen 3 30B pricing varies by provider and pricing type (standard vs batch). Check the pricing table above for current rates across all providers.
What is Qwen 3 30B best used for?
Qwen 3 30B excels at efficient text processing tasks including document analysis, content summarization, conversational applications, and high-volume text classification. Its 262K context window and fast generation speed make it suitable for applications requiring extended context understanding without the computational cost of larger models.
Does Qwen 3 30B support tool calling or multimodal inputs?
No, Qwen 3 30B is a text-only model without tool calling capabilities or support for images, audio, or other modalities. It focuses specifically on text understanding and generation tasks with optimized performance for these core language processing functions.