Qwen3 30B A3B is cheaper than GPT-4 at $0/M vs $30/M input tokens.
| Spec | GPT-4 | Qwen3 30B A3B |
|---|---|---|
| Input price | $30/M tokens | Free |
| Output price | $60/M tokens | Free |
| Context window | 8K tokens | 41K tokens |
| Parameters | Not disclosed | 30.5B (3.3B Active MoE) |
| Weights | Closed | Open |
| Free API (OpenRouter) | No | No |
| Released | May 2023 | Apr 2025 |
Not enough votes to call it. On the specs, nothing separates them.
Qwen3 30B A3B wins Image Generation and Web Design.
Per million tokens. Prices and uptime via OpenRouter, checked 8 Sep 2026.
Qwen3 30B A3B uses 43.1x more emoji