Qwen3.5 397B-A17B vs Inkling
Qwen3.5 397B-A17B is cheaper on output tokens, while Inkling offers a larger context window. Choose Qwen3.5 397B-A17B or Inkling based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Qwen3.5 397B-A17B | Inkling |
|---|---|---|
| Provider | Alibaba | Thinking Machines |
| Input / 1M tokens | $0.60 | $1.00 |
| Output / 1M tokens | $3.60 | $4.05 |
| Context window | 262K | 524K |
| Parameters | 397B | — |
| Open weights | Yes | — |
| Released | Feb 2026 | — |
| LMArena (Chatbot Arena) Elo score | 1438 | 1443 |
| LMArena WebDev Elo score | 1400 | 1415 |
| LMArena Vision Elo score | 1262 | — |
| GPQA Diamond score | 86.4 | 88.3 |
| Epoch Capabilities Index score | 147 | 148 |
FAQ
Is Qwen3.5 397B-A17B or Inkling cheaper?
Qwen3.5 397B-A17B is cheaper on output tokens ($3.60 vs $4.05 per 1M).
Which has the larger context window, Qwen3.5 397B-A17B or Inkling?
Inkling has the larger context window (524K tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.