gpt-oss-20b is 78.1× cheaper per million tokens (blended). Command A has the larger context window (256,000 vs 131,072 tokens, 2.0×).
Command A vs gpt-oss-20b
Live catalog fields. Best-in-row is highlighted.
Command Aopen
Cohere · cohere__command-a
gpt-oss-20bopen
OpenAI · openai__gpt-oss-20b
Identity
| Field | cohere__command-a | openai__gpt-oss-20b |
|---|---|---|
| Provider | Cohere | OpenAI |
| Slug | cohere__command-a | openai__gpt-oss-20b |
| Status | live | live |
| Open weights | Yes | Yes |
| License | — | — |
| HuggingFace | CohereForAI/c4ai-command-a-03-2025 | openai/gpt-oss-20b |
Quality
| Field | cohere__command-a | openai__gpt-oss-20b |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | cohere__command-a | openai__gpt-oss-20b |
|---|---|---|
| Input $ / 1M tokens | $2.50 | $0.03 |
| Cached input $ / 1M | — | $0.03 |
| Output $ / 1M tokens | $10.00 | $0.13 |
Context
| Field | cohere__command-a | openai__gpt-oss-20b |
|---|---|---|
| Max context tokens | 256,000 | 131,072 |
| Max output tokens | 8,192 | 117,964 |
Modalities
| Field | cohere__command-a | openai__gpt-oss-20b |
|---|---|---|
| Input | text | text |
| Output | text | text |