DeepSeek Model Pricing & Calculator
Open-Weight / Self-Hostable
DeepSeek: DeepSeek V3.1 API Cost Calculator
DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...
Interactive Monthly Spend Estimator
Adjust sliders to calculate your daily and monthly bill for DeepSeek: DeepSeek V3.1.
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-chat-v3.1
Provider
DeepSeek
Weight Availability
Open-Weight (Downloadable GGUF / Safetensors)
Input Price (per 1M tokens)
$0.25
Output Price (per 1M tokens)
$0.95
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
~280.7M tokens/day
Best for Serverless & Dedicated AI GPUs
Deploy on RunPod (From $0.20/hr) โ
Stop Overpaying for High-Volume AI Inference
Running DeepSeek: DeepSeek V3.1 at scale? Deploy pre-configured vLLM or Ollama pods on dedicated H100, A100, or RTX 4090 GPUs by the second.
๐ Deploy & Run Commands (Ollama, vLLM & Cloud GPU Docker)
Recommended TP: 8x GPUCopy and paste to run DeepSeek: DeepSeek V3.1 locally or launch an OpenAI-compatible API server on a Cloud GPU pod:
1. Ollama (Local 4-Bit GGUF)
ollama run deepseek-v3
2. vLLM (OpenAI-Compatible Production API)
vllm serve deepseek-ai/DeepSeek-V3 --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-V3 --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 -
Compare DeepSeek: DeepSeek V3.1 With Other Popular Models
- OpenAI: GPT-5 Cost Calculator ($1.25/1M in)
- Anthropic: Claude Sonnet 4.5 Cost Calculator ($3.00/1M in)
- Google: Gemini 2.5 Pro Cost Calculator ($1.25/1M in)
- DeepSeek: DeepSeek V3 Cost Calculator ($0.2574/1M in)
- Meta: Llama 4 Maverick Cost Calculator ($0.35/1M in)
- Qwen: Qwen3 32B Cost Calculator ($0.08/1M in)
- Mistral Large Cost Calculator ($2.00/1M in)
- SpaceXAI: Grok 4.20 Cost Calculator ($1.25/1M in)