token.app › Compare › Command A vs Mercury 3
Command A vs Mercury 3
Mercury 3 is 27× 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
| Command A | Mercury 3 | |
|---|---|---|
| Provider | Cohere | Inception |
| Input $/1M | $2.50 | $0.100 |
| Output $/1M | $10.00 | $0.350 |
| Blended $/1M | $4.38 | $0.163 |
| Context window | 256K | 1M |
| Max output | 8K | 131K |
| Released | Mar 2025 | Oct 2026 |
| Licence | Open weights | Proprietary |
Choose Command A if…
- Open weights — self-hostable
Choose Mercury 3 if…
- Costs less per token — $0.163 vs $4.38 blended
- Larger context window (1M)
- Newer model (released Oct 2026)
FAQ
Which is better, Command A or Mercury 3?
We do not hold independently-run benchmark scores covering both Command A and Mercury 3, so we make no quality claim. Their pricing and specifications are compared on this page.
Is Command A cheaper than Mercury 3?
Mercury 3 is cheaper: $0.163 versus $4.38 per million tokens blended at 3:1 input:output. Input alone: $2.50 vs $0.100. Output alone: $10.00 vs $0.350.
What context windows do Command A and Mercury 3 have?
Command A: 256,000 tokens. Mercury 3: 1,000,000 tokens.
Who makes Command A and Mercury 3?
Command A is made by Cohere. Mercury 3 is made by Inception.