gpt-oss-20b is 8.1× cheaper per million tokens (blended). MiniMax-01 has the larger context window (1,000,192 vs 131,072 tokens, 7.6×).
MiniMax-01 vs gpt-oss-20b
Live catalog fields. Best-in-row is highlighted.
MiniMax-01open
Minimax · minimax__minimax-01
gpt-oss-20bopen
OpenAI · openai__gpt-oss-20b
Identity
| Field | minimax__minimax-01 | openai__gpt-oss-20b |
|---|---|---|
| Provider | Minimax | OpenAI |
| Slug | minimax__minimax-01 | openai__gpt-oss-20b |
| Status | live | live |
| Open weights | Yes | Yes |
| License | — | — |
| HuggingFace | MiniMaxAI/MiniMax-Text-01 | openai/gpt-oss-20b |
Quality
| Field | minimax__minimax-01 | openai__gpt-oss-20b |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | minimax__minimax-01 | openai__gpt-oss-20b |
|---|---|---|
| Input $ / 1M tokens | $0.20 | $0.03 |
| Cached input $ / 1M | — | $0.03 |
| Output $ / 1M tokens | $1.10 | $0.13 |
Context
| Field | minimax__minimax-01 | openai__gpt-oss-20b |
|---|---|---|
| Max context tokens | 1,000,192 | 131,072 |
| Max output tokens | 900,172 | 117,964 |
Modalities
| Field | minimax__minimax-01 | openai__gpt-oss-20b |
|---|---|---|
| Input | text, image | text |
| Output | text | text |