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...
Quality Score
80/100
composite of price, context, capability
Input Price
$0.70
per 1M tokens
Output Price
$0.80
per 1M tokens
Context Window
131,072
tokens
- Model ID
- deepseek/deepseek-r1-distill-llama-70b
- Vendor
- deepseek
- Tokenizer
- Llama3
- Input Modalities
- text
- Output Modalities
- text
- Max Output
- 16,384 tokens
- Tool Calling
- not supported
- Structured Output
- ✓ supported
- Reasoning Mode
- ✓ supported
- Vision
- text only
- Audio
- no
- Moderated
- no
Similar models
deepseek
DeepSeek: DeepSeek V3.1
$0.15 in / $0.75 out
32,768 ctx
78
deepseek
DeepSeek: DeepSeek V3.2 Speciale
$0.40 in / $1.20 out
163,840 ctx
84
deepseek
DeepSeek: R1
$0.70 in / $2.50 out
64,000 ctx
76
deepseek
DeepSeek: DeepSeek V3
$0.32 in / $0.89 out
163,840 ctx
89
deepseek
DeepSeek: DeepSeek V3 0324
$0.20 in / $0.77 out
163,840 ctx
90
deepseek
DeepSeek: DeepSeek V3.2
$0.25 in / $0.38 out
131,072 ctx
91