token.app › Compare › Gemma 4 31B vs Beam 1.0 501B A23B
Gemma 4 31B vs Beam 1.0 501B A23B
Gemma 4 31B is 1.8× 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
| Gemma 4 31B | Beam 1.0 501B A23B | |
|---|---|---|
| Provider | Reflection | |
| Input $/1M | $0.200 | $0.250 |
| Output $/1M | $0.400 | $1.00 |
| Blended $/1M | $0.250 | $0.438 |
| Context window | 262K | 1.0M |
| Max output | 16K | 131K |
| Released | Apr 2026 | Oct 2026 |
| Licence | Open weights | Open weights |
Choose Gemma 4 31B if…
- Costs less per token — $0.250 vs $0.438 blended
Choose Beam 1.0 501B A23B if…
- Larger context window (1.0M)
- Newer model (released Oct 2026)
FAQ
Which is better, Gemma 4 31B or Beam 1.0 501B A23B?
We do not hold independently-run benchmark scores covering both Gemma 4 31B and Beam 1.0 501B A23B, so we make no quality claim. Their pricing and specifications are compared on this page.
Is Gemma 4 31B cheaper than Beam 1.0 501B A23B?
Gemma 4 31B is cheaper: $0.250 versus $0.438 per million tokens blended at 3:1 input:output. Input alone: $0.200 vs $0.250. Output alone: $0.400 vs $1.00.
What context windows do Gemma 4 31B and Beam 1.0 501B A23B have?
Gemma 4 31B: 262,144 tokens. Beam 1.0 501B A23B: 1,048,576 tokens.
Who makes Gemma 4 31B and Beam 1.0 501B A23B?
Gemma 4 31B is made by Google. Beam 1.0 501B A23B is made by Reflection.