token.app › Compare › o4 Mini vs Mercury 3
o4 Mini vs Mercury 3
Mercury 3 is 12× 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
| o4 Mini | Mercury 3 | |
|---|---|---|
| Provider | OpenAI | Inception |
| Input $/1M | $1.10 | $0.100 |
| Output $/1M | $4.40 | $0.350 |
| Blended $/1M | $1.93 | $0.163 |
| Context window | 200K | 1M |
| Max output | 100K | 131K |
| Released | Apr 2025 | Oct 2026 |
| Licence | Proprietary | Proprietary |
Choose o4 Mini if…
- No clear advantage on the data we hold.
Choose Mercury 3 if…
- Costs less per token — $0.163 vs $1.93 blended
- Larger context window (1M)
- Newer model (released Oct 2026)
FAQ
Which is better, o4 Mini or Mercury 3?
We do not hold independently-run benchmark scores covering both o4 Mini and Mercury 3, so we make no quality claim. Their pricing and specifications are compared on this page.
Is o4 Mini cheaper than Mercury 3?
Mercury 3 is cheaper: $0.163 versus $1.93 per million tokens blended at 3:1 input:output. Input alone: $1.10 vs $0.100. Output alone: $4.40 vs $0.350.
What context windows do o4 Mini and Mercury 3 have?
o4 Mini: 200,000 tokens. Mercury 3: 1,000,000 tokens.
Who makes o4 Mini and Mercury 3?
o4 Mini is made by OpenAI. Mercury 3 is made by Inception.