Qwen3.8 2.4T A95B is cheaper than Kimi K3 at $2/M vs $3/M input tokens.
| Spec | Kimi K3 | Qwen3.8 2.4T A95B |
|---|---|---|
| Input price | $3/M tokens | $2/M tokens |
| Output price | $15/M tokens | $6/M tokens |
| Context window | 1.0M tokens | 1.0M tokens |
| Weights | Open | Open |
| Free API (OpenRouter) | No | No |
| Released | Jul 2026 | Aug 2026 |
Not enough votes to call it. On the specs, nothing separates them.
Qwen3.8 2.4T A95B takes Image Generation.
Reviewing agent-written code?See a Brief PR report
Qwen3.8 2.4T A95B is cheaper on both: 1.5× input, 2.5× output.
Per million tokens. Prices and uptime via OpenRouter, checked 13 Sep 2026.
Kimi K3 uses 77.9x more emoji