Qwen3.8 27B vs Qwen3.5 35B-A3B Base
Qwen3.5 35B-A3B Base is cheaper on output tokens, while Qwen3.8 27B offers a larger context window. Choose Qwen3.8 27B or Qwen3.5 35B-A3B Base based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Qwen3.8 27B | Qwen3.5 35B-A3B Base |
|---|---|---|
| Provider | Qwen | Thinking Machines |
| Input / 1M tokens | $0.04 | $0.54 |
| Output / 1M tokens | $1.35 | $1.34 |
| Context window | 1M | 66K |
| Parameters | — | — |
| Open weights | — | Yes |
| Released | — | Feb 2026 |
| LMArena (Chatbot Arena) Elo score | 1440 | — |
| LMArena WebDev Elo score | 1593 | — |
| LMArena Vision Elo score | 1269 | — |
| Epoch Capabilities Index score | 152 | — |
FAQ
Is Qwen3.8 27B or Qwen3.5 35B-A3B Base cheaper?
Qwen3.5 35B-A3B Base is cheaper on output tokens ($1.34 vs $1.35 per 1M).
Which has the larger context window, Qwen3.8 27B or Qwen3.5 35B-A3B Base?
Qwen3.8 27B has the larger context window (1M tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.