token.app › Compare › Qwen3 Coder 30B A3B Instruct vs Mercury 3

Qwen3 Coder 30B A3B Instruct vs Mercury 3

Qwen3 Coder 30B A3B Instruct is 1.3× 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 Coder 30B A3B InstructMercury 3
ProviderAlibabaInception
Input $/1M$0.070$0.100
Output $/1M$0.280$0.350
Blended $/1M$0.123$0.163
Context window262K1M
Max output236K131K
ReleasedJul 2025Oct 2026
LicenceOpen weightsProprietary
Choose Qwen3 Coder 30B A3B Instruct if…
  • Costs less per token — $0.123 vs $0.163 blended
  • Open weights — self-hostable
Choose Mercury 3 if…
  • Larger context window (1M)
  • Newer model (released Oct 2026)
FAQ
Which is better, Qwen3 Coder 30B A3B Instruct or Mercury 3?
We do not hold independently-run benchmark scores covering both Qwen3 Coder 30B A3B Instruct and Mercury 3, so we make no quality claim. Their pricing and specifications are compared on this page.
Is Qwen3 Coder 30B A3B Instruct cheaper than Mercury 3?
Qwen3 Coder 30B A3B Instruct is cheaper: $0.123 versus $0.163 per million tokens blended at 3:1 input:output. Input alone: $0.070 vs $0.100. Output alone: $0.280 vs $0.350.
What context windows do Qwen3 Coder 30B A3B Instruct and Mercury 3 have?
Qwen3 Coder 30B A3B Instruct: 262,144 tokens. Mercury 3: 1,000,000 tokens.
Who makes Qwen3 Coder 30B A3B Instruct and Mercury 3?
Qwen3 Coder 30B A3B Instruct is made by Alibaba. Mercury 3 is made by Inception.
Related comparisons
Qwen3 Coder 30B A3B Instruct full details Mercury 3 full details Qwen3 Coder 30B A3B Instruct vs Flint (free) Qwen3 Coder 30B A3B Instruct vs MiniMax M3.1 Flash (free) Qwen3 Coder 30B A3B Instruct vs DeepSeek V4.1 Flash 1017 Qwen3 Coder 30B A3B Instruct vs Glimpse Qwen3 Coder 30B A3B Instruct vs Xing4.0 29B A4B (free) Qwen3 Coder 30B A3B Instruct vs Beam 1.0 501B A23B