Qwen/Qwen3-Coder-30B-A3B-Instruct

Built on the Qwen3 architecture, this model utilizes a sparse Mixture-of-Experts design to balance performance with efficiency. With a total of 30.5 billion parameters and 3.3 billion active parameters per forward pass, it is engineered to handle complex programming tasks and repository-scale understanding. The architecture features 128 experts, with 8 activated during each inference step, allowing it to maintain high performance across foundational coding and agentic browser-use tasks while remaining computationally streamlined.

The model underwent comprehensive pretraining and post-training stages to refine its instruction-following capabilities, specifically for technical and agentic environments. It supports a native context length of 262,144 tokens, which can be extended to 1 million tokens using Yarn, making it well-suited for deep analysis of extensive codebases. Designed for seamless integration with modern development tools, it features a specialized function call format that aligns with standard industry practices, providing a robust solution for developers seeking reliable, structured output in automated coding workflows.

SiliconFlowQwen/Qwen3-Coder-30B-A3B-Instructqwen

Open provider page Provider docs

Quick Info

Provider: SiliconFlow
Model key: Qwen/Qwen3-Coder-30B-A3B-Instruct
Release date: Aug 1, 2025
Last updated: Nov 25, 2025
Input modalities
Output modalities
Capabilities

Cost

Input token cost: $0.07
Output token cost: $0.28

Limits

Output tokens: 262,000 tokens
Context window: 262,000 tokens

Transparent token rates

Compare Qwen/Qwen3-Coder-30B-A3B-Instruct pricing

Rates are shown per one million tokens. Combined means one million input plus one million output tokens.

Browse this family

Latest news about Qwen/Qwen3-Coder-30B-A3B-Instruct

SiliconFlow

CoverageBenchmark

The OpenRouter listing for Qwen3-Coder-30B-A3B-Instruct describes it as a 30.5B-parameter Mixture-of-Experts model with 128 experts and 8 active per forward pass, built on the Qwen3 architecture and aimed at advanced code generation, repository-scale understanding, and agentic tool use. It supports a native 256K-token Benchmark figures aggregated by OpenRouter from Artificial Analysis and Design Arena include GPQA Diamond 51.6%, HLE 3.8%, IFBench 32.7%, τ²-Bench Telecom 34.5%, AA-LCR 32.7%, CritPt 0.0%, Terminal-Bench Hard 15.2%, AA-Omniscience Accuracy 16.4%, and AA-Omniscience Non-Hallucination Rate 19.7%, alongside Design Arena E

SiliconFlow

Coverage

The LLM Explorer catalog page for Qwen3 Coder 30B A3B Instruct lists it as an open-source Apache-2.0 language model from Qwen with 30B parameters, a MoE architecture (Qwen3MoeForCausalLM), 256K-token context, instruction-following and code-generation capabilities, and links to the Hugging Face repo at huggingface.co/Qw The page also surfaces community alternatives and sibling Qwen3 30B A3B variants (including YOYO V2/V3 finetunes and a REAP 25B A3B pruning), as well as links to the underlying Arxiv paper 2505.09388 and the model card, framing Qwen3-Coder-30B-A3B-Instruct within the broader Qwen3 MoE family. The listed "Updated 2026-0

SiliconFlow

Official sourceBenchmark

Compare DeepSeek-R1-Distill-Qwen-14B and Qwen3-Coder-30B-A3B-Instruct across performance, cost, capabilities, and real-world use cases. See which model fits your needs.

SiliconFlow

Official sourceBenchmark

Compare Qwen2.5-32B-Instruct and Qwen3-Coder-30B-A3B-Instruct across performance, cost, capabilities, and real-world use cases. See which model fits your needs.

SiliconFlow

Official sourceBenchmark

Compare Qwen3-Coder-30B-A3B-Instruct and Qwen3-VL-30B-A3B-Instruct across performance, cost, capabilities, and real-world use cases. See which model fits your needs.