Categories › AI & Agents › Models, LLM APIs, routing, serving, training & GPUs
Open AI models through one OpenAI-compatible API: chat, live model list, prices and cost estimates.
Remote server: your requests and data go to pool.linkrra.com. Claude Code: claude mcp add --transport http synap https://pool.linkrra.com/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
synap_chat_completion — Send a conversation to a model on Synap, Linkrra's OpenAI-compatible inference API, and get the model's reply. Use this when you need text gsynap_list_models — List the models Synap serves right now, each with its price per million tokens, context window and what it is good at. Use this to choose a synap_get_model — Return the complete catalogue record for one Synap model: pricing, context and output limits, supported parameters, quantisation, data-retensynap_estimate_cost — Work out what a chat completion would cost on Synap from token counts, using the live price list. Use this before synap_chat_completion whenNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.