Synap

OpenAI-compatible inference on open models, served on GPUs Linkrra owns and operates. Zero data retention on self-hosted models.

For agents
Models & live prices (no key): GET https://pool.linkrra.com/v1/models
Chat: POST https://pool.linkrra.com/v1/chat/completions
MCP: https://pool.linkrra.com/mcp · source · registry com.linkrra/synap
x402 (USDC on Base): /.well-known/x402
Self-hosted models
qwen3-coder-30b · gpt-oss-20b · gemma-4-26b-a4b-it

Get an API key →