Qwen3.6 35B A3B is cheaper than Llama 3.1 405B at $0.1612/M vs $2.7/M input tokens.
| Spec | Llama 3.1 405B | Qwen3.6 35B A3B |
|---|---|---|
| Input price | $2.7/M tokens | $0.1612/M tokens |
| Output price | $3.1/M tokens | $0.9653/M tokens |
| Context window | 128K tokens | 262K tokens |
| Weights | Open | Open |
| Free API (OpenRouter) | No | No |
| Released | Jul 2024 | Apr 2026 |
Not enough votes to call it. On the specs, nothing separates them.
Qwen3.6 35B A3B costs 3.2x less per token.
Reviewing agent-written code?See a Brief PR report
Qwen3.6 35B A3B is cheaper on both: 17× input, 3.2× output.
No hosts listed on OpenRouter.
Per million tokens. Prices and uptime via OpenRouter, checked 16 Sep 2026.
Qwen3.6 35B A3B uses 491.6x more bold