Deep Infra

deepseek-r1

DeepSeek-R1 achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks

qwen2.5-coder-32b-instruct

The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing

meta-llama-3.1-70b-instruct

deepseek-r1-distill-llama-70b

deepseek-r1-distill-qwen-32b