token.app › Compare › Mercury 3 vs Beam 1.0 501B A23B
Mercury 3 vs Beam 1.0 501B A23B
Mercury 3 is 2.7× cheaper per token on a blended 3:1 basis. Beam 1.0 501B A23B accepts the larger context window (1.0M).
Head to head
Blended price uses a 3:1 input:output mix
| Mercury 3 | Beam 1.0 501B A23B | |
|---|---|---|
| Provider | Inception | Reflection |
| Input $/1M | $0.100 | $0.250 |
| Output $/1M | $0.350 | $1.00 |
| Blended $/1M | $0.163 | $0.438 |
| Context window | 1M | 1.0M |
| Max output | 131K | 131K |
| Released | Oct 2026 | Oct 2026 |
| Licence | Proprietary | Open weights |
Choose Mercury 3 if…
- Costs less per token — $0.163 vs $0.438 blended
Choose Beam 1.0 501B A23B if…
- Larger context window (1.0M)
- Open weights — self-hostable
- Newer model (released Oct 2026)
FAQ
Which is better, Mercury 3 or Beam 1.0 501B A23B?
We do not hold independently-run benchmark scores covering both Mercury 3 and Beam 1.0 501B A23B, so we make no quality claim. Their pricing and specifications are compared on this page.
Is Mercury 3 cheaper than Beam 1.0 501B A23B?
Mercury 3 is cheaper: $0.163 versus $0.438 per million tokens blended at 3:1 input:output. Input alone: $0.100 vs $0.250. Output alone: $0.350 vs $1.00.
What context windows do Mercury 3 and Beam 1.0 501B A23B have?
Mercury 3: 1,000,000 tokens. Beam 1.0 501B A23B: 1,048,576 tokens.
Who makes Mercury 3 and Beam 1.0 501B A23B?
Mercury 3 is made by Inception. Beam 1.0 501B A23B is made by Reflection.