token.app › Compare › gpt-oss-120b vs Beam 1.0 501B A23B
gpt-oss-120b vs Beam 1.0 501B A23B
gpt-oss-120b is 1.7× 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
| gpt-oss-120b | Beam 1.0 501B A23B | |
|---|---|---|
| Provider | OpenAI | Reflection |
| Input $/1M | $0.150 | $0.250 |
| Output $/1M | $0.600 | $1.00 |
| Blended $/1M | $0.262 | $0.438 |
| Context window | 131K | 1.0M |
| Max output | 66K | 131K |
| Released | Aug 2025 | Oct 2026 |
| Licence | Open weights | Open weights |
Choose gpt-oss-120b if…
- Costs less per token — $0.262 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, gpt-oss-120b or Beam 1.0 501B A23B?
We do not hold independently-run benchmark scores covering both gpt-oss-120b and Beam 1.0 501B A23B, so we make no quality claim. Their pricing and specifications are compared on this page.
Is gpt-oss-120b cheaper than Beam 1.0 501B A23B?
gpt-oss-120b is cheaper: $0.262 versus $0.438 per million tokens blended at 3:1 input:output. Input alone: $0.150 vs $0.250. Output alone: $0.600 vs $1.00.
What context windows do gpt-oss-120b and Beam 1.0 501B A23B have?
gpt-oss-120b: 131,072 tokens. Beam 1.0 501B A23B: 1,048,576 tokens.
Who makes gpt-oss-120b and Beam 1.0 501B A23B?
gpt-oss-120b is made by OpenAI. Beam 1.0 501B A23B is made by Reflection.