R1 Distill Llama 70B is 2.0× cheaper per million tokens (blended). R1 has the larger context window (64,000 vs 8,192 tokens, 7.8×).
R1 vs R1 Distill Llama 70B
Live catalog fields. Best-in-row is highlighted.
R1open
DeepSeek · deepseek__deepseek-r1
R1 Distill Llama 70Bopen
DeepSeek · deepseek__deepseek-r1-distill-llama-70b
Identity
| Field | deepseek__deepseek-r1 | deepseek__deepseek-r1-distill-llama-70b |
|---|---|---|
| Provider | DeepSeek | DeepSeek |
| Slug | deepseek__deepseek-r1 | deepseek__deepseek-r1-distill-llama-70b |
| Status | live | live |
| Open weights | Yes | Yes |
| License | — | — |
| HuggingFace | deepseek-ai/DeepSeek-R1 | deepseek-ai/DeepSeek-R1-Distill-Llama-70B |
Quality
| Field | deepseek__deepseek-r1 | deepseek__deepseek-r1-distill-llama-70b |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | deepseek__deepseek-r1 | deepseek__deepseek-r1-distill-llama-70b |
|---|---|---|
| Input $ / 1M tokens | $0.70 | $0.80 |
| Cached input $ / 1M | — | — |
| Output $ / 1M tokens | $2.50 | $0.80 |
Context
| Field | deepseek__deepseek-r1 | deepseek__deepseek-r1-distill-llama-70b |
|---|---|---|
| Max context tokens | 64,000 | 8,192 |
| Max output tokens | 16,000 | 7,372 |
Modalities
| Field | deepseek__deepseek-r1 | deepseek__deepseek-r1-distill-llama-70b |
|---|---|---|
| Input | text | text |
| Output | text | text |