token.app › Compare › Qwen3.6 35B A3B vs Mercury 3
Qwen3.6 35B A3B vs Mercury 3
Mercury 3 is 1.9× cheaper per token on a blended 3:1 basis. Mercury 3 accepts the larger context window (1M).
Head to head
Blended price uses a 3:1 input:output mix
| Qwen3.6 35B A3B | Mercury 3 | |
|---|---|---|
| Provider | Alibaba | Inception |
| Input $/1M | $0.100 | $0.100 |
| Output $/1M | $0.950 | $0.350 |
| Blended $/1M | $0.313 | $0.163 |
| Context window | 262K | 1M |
| Max output | 236K | 131K |
| Released | Apr 2026 | Oct 2026 |
| Licence | Open weights | Proprietary |
Choose Qwen3.6 35B A3B if…
- Open weights — self-hostable
Choose Mercury 3 if…
- Costs less per token — $0.163 vs $0.313 blended
- Larger context window (1M)
- Newer model (released Oct 2026)
FAQ
Which is better, Qwen3.6 35B A3B or Mercury 3?
We do not hold independently-run benchmark scores covering both Qwen3.6 35B A3B and Mercury 3, so we make no quality claim. Their pricing and specifications are compared on this page.
Is Qwen3.6 35B A3B cheaper than Mercury 3?
Mercury 3 is cheaper: $0.163 versus $0.313 per million tokens blended at 3:1 input:output. Input alone: $0.100 vs $0.100. Output alone: $0.950 vs $0.350.
What context windows do Qwen3.6 35B A3B and Mercury 3 have?
Qwen3.6 35B A3B: 262,144 tokens. Mercury 3: 1,000,000 tokens.
Who makes Qwen3.6 35B A3B and Mercury 3?
Qwen3.6 35B A3B is made by Alibaba. Mercury 3 is made by Inception.