R1 Distill Llama 70B is 7.8× cheaper per million tokens (blended). Command A has the larger context window (256,000 vs 8,192 tokens, 31.3×).
Command A vs R1 Distill Llama 70B
Live catalog fields. Best-in-row is highlighted.
Command Aopen
Cohere · cohere__command-a
R1 Distill Llama 70Bopen
DeepSeek · deepseek__deepseek-r1-distill-llama-70b
Identity
| Field | cohere__command-a | deepseek__deepseek-r1-distill-llama-70b |
|---|---|---|
| Provider | Cohere | DeepSeek |
| Slug | cohere__command-a | deepseek__deepseek-r1-distill-llama-70b |
| Status | live | live |
| Open weights | Yes | Yes |
| License | — | — |
| HuggingFace | CohereForAI/c4ai-command-a-03-2025 | deepseek-ai/DeepSeek-R1-Distill-Llama-70B |
Quality
| Field | cohere__command-a | deepseek__deepseek-r1-distill-llama-70b |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | cohere__command-a | deepseek__deepseek-r1-distill-llama-70b |
|---|---|---|
| Input $ / 1M tokens | $2.50 | $0.80 |
| Cached input $ / 1M | — | — |
| Output $ / 1M tokens | $10.00 | $0.80 |
Context
| Field | cohere__command-a | deepseek__deepseek-r1-distill-llama-70b |
|---|---|---|
| Max context tokens | 256,000 | 8,192 |
| Max output tokens | 8,192 | 7,372 |
Modalities
| Field | cohere__command-a | deepseek__deepseek-r1-distill-llama-70b |
|---|---|---|
| Input | text | text |
| Output | text | text |