Coding Index
0114.6
> 28% OF MODELS
Qwen
Qwen3 30B A3B Thinking 2507
Updated: June 2026
Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated...
Specifications
- Context
- 131K
- Input
- $0.08/M
- Output
- $0.4/M
Capabilities
TEXTWEBCODINGTHINKINGWRITING
Similarly Priced Models
| Model | Provider | Context | Input Price | Output Price |
|---|---|---|---|---|
| Qwen3 VL 8B | Qwen | 256K | $0.08/M | $0.5/M |
| Qwen3 32B | Qwen | 131K | $0.08/M | $0.28/M |
| Gemma 3 27B | Google | 131K | $0.08/M | $0.16/M |
| ByteDance Seed: Seed 1.6 Flash | ByteDance | 262K | $0.075/M | $0.3/M |
| gpt-oss-safeguard-20b | OpenAI | 131K | $0.075/M | $0.3/M |
Performance Metrics
Agentic Index
0217.7
> 33% OF MODELS
DATA SOURCE: Artificial Analysis