Skip to content

Cost to run

DeepSeek LLM 67B

deepseek/deepseek-llm-67b

Family
DeepSeek LLM
Context
4,096 tokens

DeepSeek LLM 67B can be run self-hosted (rent a GPU + run vLLM/TGI) or through a serverless API (pay per token). Live pricing comparisons:

Need to benchmark this model against another? Try the calculator or see where it ranks on the InferenceScore leaderboard.