All Models

DeepSeek R1 Distill Llama 8B

deepseek-thinkingReasoningTool Calling

DeepSeek reasoning model for multi-step analysis, math, coding, and tools

Providers1
ReleasedJan 1, 2025
Input Modalitiestext
Output Modalitiestext
Tarsk Usecoding

Benchmarks

6.5
Intelligence Index
41.3
Math Index

Available Providers (1)

ProviderModel IDInput CostOutput CostContextMax OutputDocs
Alibaba (China)deepseek-r1-distill-llama-8b$0/MTok$0/MTok32.8K16.4K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output