token.app › Compare › Qwen3.5 397B A17B vs Mercury 3

Qwen3.5 397B A17B vs Mercury 3

Mercury 3 is 7.8× 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
Qwen3.5 397B A17BMercury 3
ProviderAlibabaInception
Input $/1M$0.500$0.100
Output $/1M$3.60$0.350
Blended $/1M$1.27$0.163
Context window262K1M
Max output236K131K
ReleasedFeb 2026Oct 2026
LicenceOpen weightsProprietary
Choose Qwen3.5 397B A17B if…
  • Open weights — self-hostable
Choose Mercury 3 if…
  • Costs less per token — $0.163 vs $1.27 blended
  • Larger context window (1M)
  • Newer model (released Oct 2026)
FAQ
Which is better, Qwen3.5 397B A17B or Mercury 3?
We do not hold independently-run benchmark scores covering both Qwen3.5 397B A17B and Mercury 3, so we make no quality claim. Their pricing and specifications are compared on this page.
Is Qwen3.5 397B A17B cheaper than Mercury 3?
Mercury 3 is cheaper: $0.163 versus $1.27 per million tokens blended at 3:1 input:output. Input alone: $0.500 vs $0.100. Output alone: $3.60 vs $0.350.
What context windows do Qwen3.5 397B A17B and Mercury 3 have?
Qwen3.5 397B A17B: 262,144 tokens. Mercury 3: 1,000,000 tokens.
Who makes Qwen3.5 397B A17B and Mercury 3?
Qwen3.5 397B A17B is made by Alibaba. Mercury 3 is made by Inception.
Related comparisons