DeepSeek Model Pricing & Calculator Open-Weight / Self-Hostable

DeepSeek: R1 0528 API Cost Calculator

May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...

Interactive Monthly Spend Estimator

Adjust sliders to calculate your daily and monthly bill for DeepSeek: R1 0528.

Estimated Daily API Cost $0.00
Estimated Monthly API Cost (30 days) $0.00
24/7 Dedicated 2x NVIDIA H100 (160GB VRAM) Self-Host Cost $3,873.60/mo

Official Token Pricing & Specs

Model ID deepseek/deepseek-r1-0528
Provider DeepSeek
Weight Availability Open-Weight (Downloadable GGUF / Safetensors)
Input Price (per 1M tokens) $0.571
Output Price (per 1M tokens) $2.286
Max Context Window 163,840 tokens
VRAM Needed (4-Bit Q4 / FP16) 436.2 GB / 1476.2 GB โ†’
API vs. GPU Daily Break-Even ~118.9M tokens/day
Deploy on RunPod (From $0.20/hr) Rent GPUs on Vast.ai (Save up to 70%)
Best for Serverless & Dedicated AI GPUs

Stop Overpaying for High-Volume AI Inference

Running DeepSeek: R1 0528 at scale? Deploy pre-configured vLLM or Ollama pods on dedicated H100, A100, or RTX 4090 GPUs by the second.

Deploy on RunPod (From $0.20/hr) โ†’

๐Ÿš€ Deploy & Run Commands (Ollama, vLLM & Cloud GPU Docker)

Recommended TP: 8x GPU

Copy and paste to run DeepSeek: R1 0528 locally or launch an OpenAI-compatible API server on a Cloud GPU pod:

1. Ollama (Local 4-Bit GGUF)
ollama run deepseek-r1:671b
2. vLLM (OpenAI-Compatible Production API)
vllm serve deepseek-ai/DeepSeek-R1-0528 --max-model-len 32768 --tensor-parallel-size 8 --gpu-memory-utilization 0.92
3. Docker / Cloud GPU Pod (RunPod & Vast.ai)
docker run --gpus all -p 8000:8000 --ipc=host vllm/vllm-openai:latest --model deepseek-ai/DeepSeek-R1-0528 --tensor-parallel-size 8
4. Local GPU Compatibility CLI Check (Detects nvidia-smi / Apple Silicon)
curl -sL https://stigla610.github.io/ai-cost-engine/tokenbench.py | python3 -
Launch vLLM / Ollama Template on RunPod โ†’ Rent Cheap GPUs on Vast.ai โ†’

Compare DeepSeek: R1 0528 With Other Popular Models