Skip to main content
DEDeepSeek/ DeepSeek

R1 Distill Llama 70B

deepseek/deepseek-r1-distill-llama-70b

DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across...

Model information

Released
2025-01-23
Context window
8.2K
Max output
8.2K
Model parameters
71B
Weights
Open

Modalities

Input
Text
Output
Text

Identity

Version
deepseek-r1-distill-llama-70b
Knowledge cutoff
2024-07-31
License
MIT

Resources

Capabilities

Open weightReasoningTemperature

Providers

ProviderProvider model IDProtocolContextMax outputInputOutputCapabilitiesNotesPricingStreaming
OpenRouterdeepseek/deepseek-r1-distill-llama-70bopenai_chat8.2K8.2K
ReasoningTemperature
Hugging Face: deepseek-ai/DeepSeek-R1-Distill-Llama-70B
input $0.8/M · output $0.8/M
Yes
Kilo Gatewaydeepseek/deepseek-r1-distill-llama-70bopenai_chat8.2K8.2K
ReasoningTemperature
-
input $0.8/M · output $0.8/M
Yes
NovitaAIdeepseek/deepseek-r1-distill-llama-70bopenai_chat8.2K8.2K
ReasoningStructuredTemperature
-
input $0.8/M · output $0.8/M
Yes
DeepSeekdeepseek-r1-distill-llama-70bcustom8.2K8.2K
---Yes

FAQ