token.app › Compare › Inkling Small vs Beam 1.0 501B A23B
Inkling Small vs Beam 1.0 501B A23B
Beam 1.0 501B A23B is 1.5× 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
| Inkling Small | Beam 1.0 501B A23B | |
|---|---|---|
| Provider | Thinkingmachines | Reflection |
| Input $/1M | $0.450 | $0.250 |
| Output $/1M | $1.20 | $1.00 |
| Blended $/1M | $0.637 | $0.438 |
| Context window | 524K | 1.0M |
| Max output | 262K | 131K |
| Released | Jul 2026 | Oct 2026 |
| Licence | Open weights | Open weights |
Choose Inkling Small if…
- No clear advantage on the data we hold.
Choose Beam 1.0 501B A23B if…
- Costs less per token — $0.438 vs $0.637 blended
- Larger context window (1.0M)
- Newer model (released Oct 2026)
FAQ
Which is better, Inkling Small or Beam 1.0 501B A23B?
We do not hold independently-run benchmark scores covering both Inkling Small and Beam 1.0 501B A23B, so we make no quality claim. Their pricing and specifications are compared on this page.
Is Inkling Small cheaper than Beam 1.0 501B A23B?
Beam 1.0 501B A23B is cheaper: $0.438 versus $0.637 per million tokens blended at 3:1 input:output. Input alone: $0.450 vs $0.250. Output alone: $1.20 vs $1.00.
What context windows do Inkling Small and Beam 1.0 501B A23B have?
Inkling Small: 524,288 tokens. Beam 1.0 501B A23B: 1,048,576 tokens.
Who makes Inkling Small and Beam 1.0 501B A23B?
Inkling Small is made by Thinkingmachines. Beam 1.0 501B A23B is made by Reflection.