gpt-oss-120b is 115.7× cheaper per million tokens (blended). gpt-oss-120b has the larger context window (131,072 vs 128,000 tokens). gpt-oss-120b is open-weights; the other is not.
Command R+ (08-2024) vs gpt-oss-120b
Live catalog fields. Best-in-row is highlighted.
Command R+ (08-2024)
Cohere · cohere__command-r-plus-08-2024
gpt-oss-120bopen
OpenAI · openai__gpt-oss-120b
Identity
| Field | cohere__command-r-plus-08-2024 | openai__gpt-oss-120b |
|---|---|---|
| Provider | Cohere | OpenAI |
| Slug | cohere__command-r-plus-08-2024 | openai__gpt-oss-120b |
| Status | live | live |
| Open weights | No | Yes |
| License | — | — |
| HuggingFace | — | openai/gpt-oss-120b |
Quality
| Field | cohere__command-r-plus-08-2024 | openai__gpt-oss-120b |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | cohere__command-r-plus-08-2024 | openai__gpt-oss-120b |
|---|---|---|
| Input $ / 1M tokens | $2.50 | $0.02 |
| Cached input $ / 1M | — | $0.02 |
| Output $ / 1M tokens | $10.00 | $0.09 |
Context
| Field | cohere__command-r-plus-08-2024 | openai__gpt-oss-120b |
|---|---|---|
| Max context tokens | 128,000 | 131,072 |
| Max output tokens | 4,000 | 65,536 |
Modalities
| Field | cohere__command-r-plus-08-2024 | openai__gpt-oss-120b |
|---|---|---|
| Input | text | text |
| Output | text | text |