gpt-oss-20b is 7.8× cheaper per million tokens (blended). Beam 1.0 501B A23B has the larger context window (1,048,576 vs 131,072 tokens, 8.0×).
gpt-oss-20b vs Beam 1.0 501B A23B
Live catalog fields. Best-in-row is highlighted.
gpt-oss-20bopen
OpenAI · openai__gpt-oss-20b
Beam 1.0 501B A23Bopen
Reflection · reflection__beam-1.0-501b-a23b
Identity
| Field | openai__gpt-oss-20b | reflection__beam-1.0-501b-a23b |
|---|---|---|
| Provider | OpenAI | Reflection |
| Slug | openai__gpt-oss-20b | reflection__beam-1.0-501b-a23b |
| Status | live | live |
| Open weights | Yes | Yes |
| License | — | — |
| HuggingFace | openai/gpt-oss-20b | reflection/Beam-1.0-501B-A23B |
Quality
| Field | openai__gpt-oss-20b | reflection__beam-1.0-501b-a23b |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | openai__gpt-oss-20b | reflection__beam-1.0-501b-a23b |
|---|---|---|
| Input $ / 1M tokens | $0.03 | $0.25 |
| Cached input $ / 1M | $0.03 | $0.05 |
| Output $ / 1M tokens | $0.13 | $1.00 |
Context
| Field | openai__gpt-oss-20b | reflection__beam-1.0-501b-a23b |
|---|---|---|
| Max context tokens | 131,072 | 1,048,576 |
| Max output tokens | 117,964 | 131,072 |
Modalities
| Field | openai__gpt-oss-20b | reflection__beam-1.0-501b-a23b |
|---|---|---|
| Input | text | text |
| Output | text | text |