back_office_ops · saas · workflow
Deploying DeepSeek-R1 on AWS: Our Journey Through Performance, Cost, and Reality
The team wanted to evaluate whether self-hosted open-source LLMs could replace paid AI coding assistants, motivated by goals of control, privacy, and long-term cost savings, but faced uncertainty about operational viability at startup scale.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Decide to evaluate self-hosted LLMs
The team decided to explore deploying open-source DeepSeek-R1 models in-house to evaluate their viability as alternatives to paid services like ChatGPT.
Tools used
DeepSeek-R1AWS EC2DockerNVIDIA Container ToolkitOllamaOpenWeb UI
Outcome
Self-hosting was found not cost-effective for startups at small-to-medium scale: a single AWS instance cost around $414/month while comparable SaaS offerings were drastically cheaper, with hidden operational overhead further widening the gap.
What failed first
The 16B model crashed under load even after aggressive quantization and batch-size reductions; performance degraded below usable token speeds with longer context windows; and tuning parameters introduced unpredictable latency and crashes.
Results
Volume$20/user/month
Cost replacedaround $414/month
Grounding & classification
Source type: technical build writeup
21 fields verified against source quotes.
code generationconversational aibuilder submittedfailure mode describedmetric backedtools describedworkflow describedsoftwarecost reductionemployee productivitytechnical build writeupback office ops