Updated daily at 05:00 UTC
Reasoning-only
DeepSeek-R1-Distill
Small Qwen and Llama models fine-tuned on DeepSeek-R1 reasoning traces.
By DeepSeek.
Versions
7 versions
| Model | Maker | Kind | Released | Context | Input $/1M | Output $/1M |
|---|---|---|---|---|---|---|
| DeepSeek-R1-0528-Qwen3-8BDeepSeek-R1-Distill · Open weights | DeepSeek | Reasoning-only | 29 May 2025 | 131.1K | — | — |
| DeepSeek-R1-Distill-Llama-70BDeepSeek-R1-Distill · Legacy · Open weights | DeepSeek | Reasoning-only | 20 Jan 2025 | 131.1K | — | — |
| DeepSeek-R1-Distill-Llama-8BDeepSeek-R1-Distill · Legacy · Open weights | DeepSeek | Reasoning-only | 20 Jan 2025 | 131.1K | — | — |
| DeepSeek-R1-Distill-Qwen-1.5BDeepSeek-R1-Distill · Legacy · Open weights | DeepSeek | Reasoning-only | 20 Jan 2025 | 131.1K | — | — |
| DeepSeek-R1-Distill-Qwen-14BDeepSeek-R1-Distill · Legacy · Open weights | DeepSeek | Reasoning-only | 20 Jan 2025 | 131.1K | — | — |
| DeepSeek-R1-Distill-Qwen-32BDeepSeek-R1-Distill · Legacy · Open weights | DeepSeek | Reasoning-only | 20 Jan 2025 | 131.1K | — | — |
| DeepSeek-R1-Distill-Qwen-7BDeepSeek-R1-Distill · Legacy · Open weights | DeepSeek | Reasoning-only | 20 Jan 2025 | 131.1K | — | — |
- DeepSeek-R1-0528-Qwen3-8BDeepSeek · 29 May 2025 · 131.1K context—in / 1M
- DeepSeek-R1-Distill-Llama-70BDeepSeek · 20 Jan 2025 · 131.1K context—in / 1M
- DeepSeek-R1-Distill-Llama-8BDeepSeek · 20 Jan 2025 · 131.1K context—in / 1M
- DeepSeek-R1-Distill-Qwen-1.5BDeepSeek · 20 Jan 2025 · 131.1K context—in / 1M
- DeepSeek-R1-Distill-Qwen-14BDeepSeek · 20 Jan 2025 · 131.1K context—in / 1M
- DeepSeek-R1-Distill-Qwen-32BDeepSeek · 20 Jan 2025 · 131.1K context—in / 1M
- DeepSeek-R1-Distill-Qwen-7BDeepSeek · 20 Jan 2025 · 131.1K context—in / 1M