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

Fieldcohere__command-adeepseek__deepseek-r1-distill-llama-70b
ProviderCohereDeepSeek
Slugcohere__command-adeepseek__deepseek-r1-distill-llama-70b
Statuslivelive
Open weightsYesYes
License
HuggingFaceCohereForAI/c4ai-command-a-03-2025deepseek-ai/DeepSeek-R1-Distill-Llama-70B

Quality

Fieldcohere__command-adeepseek__deepseek-r1-distill-llama-70b
Quality index (0–100)

Cost

Fieldcohere__command-adeepseek__deepseek-r1-distill-llama-70b
Input $ / 1M tokens$2.50$0.80
Cached input $ / 1M
Output $ / 1M tokens$10.00$0.80

Context

Fieldcohere__command-adeepseek__deepseek-r1-distill-llama-70b
Max context tokens256,0008,192
Max output tokens8,1927,372

Modalities

Fieldcohere__command-adeepseek__deepseek-r1-distill-llama-70b
Inputtexttext
Outputtexttext