R1 Distill Llama 70B is 11.3× cheaper per million tokens (blended). Claude Sonnet 4 has the larger context window (200,000 vs 8,192 tokens, 24.4×). R1 Distill Llama 70B is open-weights; the other is not.
Claude Sonnet 4 vs R1 Distill Llama 70B
Live catalog fields. Best-in-row is highlighted.
Claude Sonnet 4
Anthropic · anthropic__claude-sonnet-4
R1 Distill Llama 70Bopen
DeepSeek · deepseek__deepseek-r1-distill-llama-70b
Identity
| Field | anthropic__claude-sonnet-4 | deepseek__deepseek-r1-distill-llama-70b |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Slug | anthropic__claude-sonnet-4 | deepseek__deepseek-r1-distill-llama-70b |
| Status | live | live |
| Open weights | No | Yes |
| License | — | — |
| HuggingFace | — | deepseek-ai/DeepSeek-R1-Distill-Llama-70B |
Quality
| Field | anthropic__claude-sonnet-4 | deepseek__deepseek-r1-distill-llama-70b |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | anthropic__claude-sonnet-4 | deepseek__deepseek-r1-distill-llama-70b |
|---|---|---|
| Input $ / 1M tokens | $3.00 | $0.80 |
| Cached input $ / 1M | $0.30 | — |
| Output $ / 1M tokens | $15.00 | $0.80 |
Context
| Field | anthropic__claude-sonnet-4 | deepseek__deepseek-r1-distill-llama-70b |
|---|---|---|
| Max context tokens | 200,000 | 8,192 |
| Max output tokens | 64,000 | 7,372 |
Modalities
| Field | anthropic__claude-sonnet-4 | deepseek__deepseek-r1-distill-llama-70b |
|---|---|---|
| Input | image, text, file | text |
| Output | text | text |