R1 Distill Llama 70B
DeepSeek · Open weights · Released Jan 23, 2025 · deepseek/deepseek-r1-distill-llama-70b
8K contextReasoningOpen weights
Available from 1 providerUSD / MTOK · VERIFIED 4 MINUTES AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
| $0.80 | $0.80 | — | 8K | bf16 | 0.76s | 25 tok/s | 100.0% |
TTFT/TPS: median (P50) over trailing 72h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 44 hours ago
About
DeepSeek R1 Distill Llama 70B is a distilled large language model based on Llama-3.3-70B-Instruct, using outputs from DeepSeek R1. The model combines advanced distillation techniques to achieve high performance across...
Specifications
Context window8,192
Max output8,192
Modalities intext
Modalities outtext
LicenseOpen weights
ReleasedJan 23, 2025
Knowledge cutoff2024-07-31
TokenizerLlama3
WeightsHugging Face ↗
Open weights
safetensors
Related
Embed badge
[](https://modelindex.ai/models/deepseek/deepseek-r1-distill-llama-70b)Sources
OpenRouter API4 minutes ago
AGGREGATORHugging Face4 minutes ago
COMMUNITYModelIndex benchmarks44 hours ago
MEASUREDVerified 4 minutes ago · list prices, not negotiated rates.