DeepSeek

CommunityMPP LLMLlmStreamOnline

Frontier AI models — DeepSeek-V3 for fast chat and code, DeepSeek-R1 for deep chain-of-thought reasoning. OpenAI-compatible API format. Among the most capable and cost-efficient models available.

Latency1030ms

Channels1h – 1d

Chain—

Quick Start

# Install the MCP server
npm install -g drain-mcp

# MPP LLM: auto-pay per request via Tempo. Call directly:
mpp_chat(
  provider: "https://deepseek.mpp.paywithlocus.com",
  messages: [{ role: "user", content: "..." }]
)

Docs ↗

integration

API↗Websitedeepseek.com↗