Skip to content
LLMs
DeepSeek logo

DeepSeek: R1 Distill Llama 70B

by DeepSeek

DeepSeek: R1 Distill Llama 70B is a large language model from DeepSeek. It costs $0.800 per million input tokens and $0.800 per million output tokens. Its context window is 8K tokens.

ReasoningOpen weights
Input / 1M tokens
$0.800
Output / 1M tokens
$0.800
Cached input / 1M
-

Not supported

Context window
8K

tokens

Who serves it cheapest

1 hosts serve R1 Distill Llama 70B. Same weights, same API - the price difference is pure margin and routing.

Providers serving DeepSeek: R1 Distill Llama 70B, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
NovitaCheapestbf16$0.800$0.8008K-100.0%

About 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...

Specifications

DeepSeek: R1 Distill Llama 70B specifications
Model IDdeepseek/deepseek-r1-distill-llama-70b
ProviderDeepSeek
Context window8K tokens
Max output7K tokens
Input modalitiestext
Output modalitiestext
Knowledge cutoff2024-07-31
Open weightsYes - deepseek-ai/DeepSeek-R1-Distill-Llama-70B
ReleasedJanuary 23, 2025

Cheaper alternatives

Models that cost less than R1 Distill Llama 70B while keeping at least half its context window and every input modality it supports.

Frequently asked

How much does DeepSeek: R1 Distill Llama 70B cost?

$0.800 per million input tokens and $0.800 per million output tokens.

What is the context window of DeepSeek: R1 Distill Llama 70B?

8K tokens, with up to 7K tokens of output per request.

Confirm against the source: DeepSeek official pricing.