token.app › Compare › Qwen3 VL 30B A3B Thinking vs Mercury 3

Qwen3 VL 30B A3B Thinking vs Mercury 3

Mercury 3 is 2.9× 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 VL 30B A3B ThinkingMercury 3
ProviderAlibabaInception
Input $/1M$0.290$0.100
Output $/1M$1.00$0.350
Blended $/1M$0.467$0.163
Context window262K1M
Max output236K131K
ReleasedOct 2025Oct 2026
LicenceOpen weightsProprietary
Choose Qwen3 VL 30B A3B Thinking if…
  • Open weights — self-hostable
Choose Mercury 3 if…
  • Costs less per token — $0.163 vs $0.467 blended
  • Larger context window (1M)
  • Newer model (released Oct 2026)
FAQ
Which is better, Qwen3 VL 30B A3B Thinking or Mercury 3?
We do not hold independently-run benchmark scores covering both Qwen3 VL 30B A3B Thinking and Mercury 3, so we make no quality claim. Their pricing and specifications are compared on this page.
Is Qwen3 VL 30B A3B Thinking cheaper than Mercury 3?
Mercury 3 is cheaper: $0.163 versus $0.467 per million tokens blended at 3:1 input:output. Input alone: $0.290 vs $0.100. Output alone: $1.00 vs $0.350.
What context windows do Qwen3 VL 30B A3B Thinking and Mercury 3 have?
Qwen3 VL 30B A3B Thinking: 262,144 tokens. Mercury 3: 1,000,000 tokens.
Who makes Qwen3 VL 30B A3B Thinking and Mercury 3?
Qwen3 VL 30B A3B Thinking is made by Alibaba. Mercury 3 is made by Inception.
Related comparisons
Qwen3 VL 30B A3B Thinking full details Mercury 3 full details Qwen3 VL 30B A3B Thinking vs Flint (free) Qwen3 VL 30B A3B Thinking vs MiniMax M3.1 Flash (free) Qwen3 VL 30B A3B Thinking vs DeepSeek V4.1 Flash 1017 Qwen3 VL 30B A3B Thinking vs Glimpse Qwen3 VL 30B A3B Thinking vs Xing4.0 29B A4B (free) Qwen3 VL 30B A3B Thinking vs Beam 1.0 501B A23B