gpt-oss-120b is 3.5× cheaper per million tokens (blended). MiniMax M3.1 Flash has the larger context window (1,048,576 vs 131,072 tokens, 8.0×).
MiniMax M3.1 Flash vs gpt-oss-120b
Live catalog fields. Best-in-row is highlighted.
MiniMax M3.1 Flashopen
Minimax · minimax__minimax-m3.1-flash
gpt-oss-120bopen
OpenAI · openai__gpt-oss-120b
Identity
| Field | minimax__minimax-m3.1-flash | openai__gpt-oss-120b |
|---|---|---|
| Provider | Minimax | OpenAI |
| Slug | minimax__minimax-m3.1-flash | openai__gpt-oss-120b |
| Status | live | live |
| Open weights | Yes | Yes |
| License | — | — |
| HuggingFace | MiniMaxAI/MiniMax-M3.1-Flash | openai/gpt-oss-120b |
Quality
| Field | minimax__minimax-m3.1-flash | openai__gpt-oss-120b |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | minimax__minimax-m3.1-flash | openai__gpt-oss-120b |
|---|---|---|
| Input $ / 1M tokens | $0.07 | $0.02 |
| Cached input $ / 1M | $0.01 | $0.02 |
| Output $ / 1M tokens | $0.30 | $0.09 |
Context
| Field | minimax__minimax-m3.1-flash | openai__gpt-oss-120b |
|---|---|---|
| Max context tokens | 1,048,576 | 131,072 |
| Max output tokens | 524,288 | 65,536 |
Modalities
| Field | minimax__minimax-m3.1-flash | openai__gpt-oss-120b |
|---|---|---|
| Input | text, image, video | text |
| Output | text | text |