DeepSeek V3.2 · 10 hours on H100

DeepSeek V3.2 · 10 hours on H100 - a prepaid inference-hour pack for deepseek-ai/DeepSeek-V3.2, billed at Hugging Face's published Inference Endpoints rate of $4.50 per hour on H100 80GB.

What you get

• 10 hour(s) of dedicated H100 80GB inference.
• The model loaded from the Hub: deepseek-ai/DeepSeek-V3.2.
• No shipping: the endpoint key is issued once the order completes.

Quick start

curl -X POST "$ENDPOINT_URL/v1/chat/completions" \
  -H "Authorization: Bearer $HF_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"model": "deepseek-ai/DeepSeek-V3.2", "messages": [{"role": "user", "content": "Hello"}]}'