gpt-oss-20b is 1.2× cheaper per million tokens (blended). gpt-oss-20b has the larger context window (131,072 vs 128,000 tokens). gpt-oss-20b is open-weights; the other is not.
Command R7B (12-2024) vs gpt-oss-20b
Live catalog fields. Best-in-row is highlighted.
Command R7B (12-2024)
Cohere · cohere__command-r7b-12-2024
gpt-oss-20bopen
OpenAI · openai__gpt-oss-20b
Identity
| Field | cohere__command-r7b-12-2024 | openai__gpt-oss-20b |
|---|---|---|
| Provider | Cohere | OpenAI |
| Slug | cohere__command-r7b-12-2024 | openai__gpt-oss-20b |
| Status | live | live |
| Open weights | No | Yes |
| License | — | — |
| HuggingFace | — | openai/gpt-oss-20b |
Quality
| Field | cohere__command-r7b-12-2024 | openai__gpt-oss-20b |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | cohere__command-r7b-12-2024 | openai__gpt-oss-20b |
|---|---|---|
| Input $ / 1M tokens | $0.04 | $0.03 |
| Cached input $ / 1M | — | $0.03 |
| Output $ / 1M tokens | $0.15 | $0.13 |
Context
| Field | cohere__command-r7b-12-2024 | openai__gpt-oss-20b |
|---|---|---|
| Max context tokens | 128,000 | 131,072 |
| Max output tokens | 4,000 | 117,964 |
Modalities
| Field | cohere__command-r7b-12-2024 | openai__gpt-oss-20b |
|---|---|---|
| Input | text | text |
| Output | text | text |