Models/DeepSeek-R1-Distill-Llama-70B

DeepSeek-R1-Distill-Llama-70BDeprecated · Cloud

Sambanova · Released Jan 2025 · Llama Community License

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...

Context
131K
Max output
131K
Input
$0.70
Output
$1.40
Cached in
-
Latency
-

Capabilities

Core
Streaming
Function calling
JSON mode
Structured outputs
Multimodal
Vision
Image input
Audio
Image generation
Video
Advanced
Reasoning
Tool calling
MCP
Prompt caching
Batch API
Embeddings

Benchmarks

BBH35.8
GPQA2
IFEval43.4
MATH Lvl 530.7
MMLU-Pro41.6
MUSR13.3
Open LLM Average27.8

Details

ProviderSambanova
ReleasedJan 2025
LicenseLlama Community License
InputText
OutputText
Throughput-
Availability100%

Related models