Back to search
30
MCP http

thryx-ai-llm

x402/thryx-ai-llm

LLM inference (Llama 3.1 8B) - prompt in, answer out. Pay-per-call USDC on Base, no API key, no account. [x402: $0.0/call on base-mainnet, category=other]

Uptime
0.0%
12 probes
Response
0ms
last probe
Tools
0
callable
Primary URL
https://thryx-ai-x402.thryx.workers.dev/ask

Similar MCP servers embedding-nearest

Sisyphus LLM API
Pay-per-call LLM inference via x402 USDC on Base. 15 models, 290ms latency, anonymous free tier via LLM7 fallback. OpenAI-compatible /v1/cha
0 tools · http
SYNTHORA Pay-Per-Prompt LLM Inference
Pay-per-prompt LLM inference, multi-provider cascade, no API keys [x402: $0.01/call on base, category=other]
0 tools · http
x402 LLM Proxy
Paid LLM proxy for AI agents, USDC on Base. OpenAI-compatible chat completions endpoint. [x402: $0.001/call on base-mainnet, category=utilit
0 tools · http
thryx-ai-embed
768-dim text embeddings (bge-base) for RAG, semantic search & agent memory. Pay-per-call USDC, no API key. [x402: $0.0/call on base-mainnet,
0 tools · http
com.cheapestinference/mcp
Discover unlimited LLM inference pools, get USDC quotes, subscribe on Base, check key status.
0 tools · streamable-http
Moonmaker API Intelligence
API intelligence and LLM service via x402 payments. AI-powered insights and data analysis. [x402: $0.005/call on base, category=data]
0 tools · http

How to use

Add to your Claude Desktop / Cursor / Cline MCP config:

{
  "mcpServers": {
    "thryx-ai-llm": {
      "url": "https://thryx-ai-x402.thryx.workers.dev/ask",
      "transport": "http"
    }
  }
}