Loading...
Loading...
Side-by-side comparison of API pricing, context window, latency, and benchmark performance. Data refreshed daily from provider APIs and ModelStop's own latency probes.
💰DeepSeek-R1-Distill-Llama-8B is 100% cheaper than deepseek-r1-distill-qwen-32b
⚡DeepSeek-R1-Distill-Llama-8B is 372ms faster than deepseek-r1-distill-qwen-32b
Price (lower is better), Speed/Latency (lower is better), Performance (higher is better)
DeepSeek-R1-Distill-Llama-8B is Infinity% cheaper
| Spec | deepseek-r1-distill-qwen-32b | DeepSeek-R1-Distill-Llama-8B |
|---|---|---|
| Provider | deepseek-ai | deepseek-ai |
| Input price / 1M tokens | $0.50 | Free |
| Output price / 1M tokens | $4.88 | — |
| Context window | 80k tokens | — |
| Latency (p50) | 372ms | — |
| Best benchmark score | — | — |
| Open source | No | Yes |
DeepSeek-R1-Distill-Qwen-32B is a model distilled from DeepSeek-R1 based on Qwen2.5. It outperforms OpenAI-o1-mini across various benchmarks, achieving new state-of-the-art results for dense models.
Open-source DeepSeek-R1-Distill-Llama-8B model from deepseek-ai — available for download and self-hosting on Hugging Face.
Want to swap in a different model or estimate monthly costs?
Help my team choose the right model
Not sure which model fits your workload, budget, and latency requirements? Get a tailored recommendation.