Categories › AI & Agents › Models, LLM APIs, routing, serving, training & GPUs
LLM API discovery: access conditions, dated costs, sampled checks and keyless configs. Read-only.
Remote server: your requests and data go to freetoken.link. Claude Code: claude mcp add --transport http freetoken-llm-api-discovery https://freetoken.link/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
search_models — Filter the published catalog (substring search, not a benchmark or guarantee of free access). Returns exact provider/model slugs for subsequget_provider_guide — Read official application links, payment/identity conditions and existing application steps for a published provider. No signup or key generlist_price_references — List dated price reference IDs and billing scenarios for estimate_cost. This is a limited reference set, not complete market coverage or livestimate_cost — Estimate USD cost for ONE listed priceId and its exact billing scenario. inputMillion/outputMillion are millions of tokens, not individual tget_route_status — Read existing sampled checks for public catalog routes. No new checks run. Missing/stale evidence must not be interpreted as uptime or an ouexport_keyless_config — Render a keyless config for 1–5 exact catalog providerSlug/modelSlug pairs. Only environment variable references are returned. No keys, promNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.