Qwen Plus 0728 (thinking) vs Qwen3 Coder 30B A3B Instruct
How do these models stack up? Below is an expert side-by-side comparison of specifications, context window capacity, live pricing per million tokens, and standardized benchmark scores for Qwen Plus 0728 (thinking) and Qwen3 Coder 30B A3B Instruct.
Qwen Plus 0728 (thinking)
Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.
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...
Technical Specifications
| Specification | Qwen Plus 0728 (thinking) | Qwen3 Coder 30B A3B Instruct |
|---|---|---|
| Provider | Alibaba | Alibaba |
| Context Window | 1,000,000 tokens | 160,000 tokens |
| Agent Suitability | N/A | N/A |
| Time to First Token (TTFT) | N/A | N/A |
| Deployment Model | self hostable | self hostable |
| Production Stability | beta | stable |
| API Available | Yes | Yes |
| Released Date | 2025-09-08 | 2025-07-31 |
API Pricing Comparison
Input Price per Million Tokens
Qwen Plus 0728 (thinking)
$0.26
Qwen3 Coder 30B A3B Instruct
$0.07
Output Price per Million Tokens
Qwen Plus 0728 (thinking)
$0.78
Qwen3 Coder 30B A3B Instruct
$0.27
Want to test both models live?
Run side-by-side prompt prompts in our dynamic Sandbox. Check execution speeds, latency metrics, and compute actual costs in real-time.
Benchmark Performance Metrics
Scores show the raw performance percentages verified across key evaluation suites. Higher bars indicate superior accuracy and capability in that domain.
Qwen Plus 0728 (thinking) Quirks & Gotchas
No developer gotchas reported.
Qwen3 Coder 30B A3B Instruct Quirks & Gotchas
No developer gotchas reported.