{
 "schema_version": 1,
 "generated": "2026-10-20",
 "repo": "eliasbiondo/antirion",
 "name": "antirion",
 "owner": "eliasbiondo",
 "slug": "eliasbiondo-antirion",
 "github": "https://github.com/eliasbiondo/antirion",
 "what": "Antirion is an open-source AI gateway written in Rust, shipped as one binary with a built-in web console, that routes, secures, budgets and observes LLM calls across many model providers.",
 "why": "",
 "language": "Rust",
 "requirements": [
  "Docker installed on the machine that will run the gateway",
  "An API key from OpenAI or Anthropic",
  "A web browser to open the console at http://localhost:8081/ui/"
 ],
 "audience_note": "Built for developers and platform teams who run apps that call several LLM providers and want one endpoint, spend limits and request visibility.",
 "risk": "none",
 "section": "earlier",
 "weekly_rank": null,
 "category": "Software and DevOps",
 "url": "https://dedupedai.com/use-cases/eliasbiondo-antirion/",
 "use_case_count": 5,
 "use_cases": [
  {
   "id": "eliasbiondo-antirion--route-all-llm-calls-through-one-endpoint",
   "title": "Send every app's LLM calls through one endpoint",
   "best": true,
   "url": "https://dedupedai.com/use-cases/eliasbiondo-antirion/route-all-llm-calls-through-one-endpoint/",
   "json": "https://dedupedai.com/use-cases/u/eliasbiondo-antirion/route-all-llm-calls-through-one-endpoint.json"
  },
  {
   "id": "eliasbiondo-antirion--cap-team-spend-with-budgets-and-alerts",
   "title": "Cap LLM spend per team, project or key",
   "best": false,
   "url": "https://dedupedai.com/use-cases/eliasbiondo-antirion/cap-team-spend-with-budgets-and-alerts/",
   "json": "https://dedupedai.com/use-cases/u/eliasbiondo-antirion/cap-team-spend-with-budgets-and-alerts.json"
  },
  {
   "id": "eliasbiondo-antirion--trace-why-an-llm-call-failed-or-cost-too-much",
   "title": "Find out why an LLM call failed or cost too much",
   "best": false,
   "url": "https://dedupedai.com/use-cases/eliasbiondo-antirion/trace-why-an-llm-call-failed-or-cost-too-much/",
   "json": "https://dedupedai.com/use-cases/u/eliasbiondo-antirion/trace-why-an-llm-call-failed-or-cost-too-much.json"
  },
  {
   "id": "eliasbiondo-antirion--block-pii-and-prompt-injection-at-the-gateway",
   "title": "Screen prompts for PII and prompt injection",
   "best": false,
   "url": "https://dedupedai.com/use-cases/eliasbiondo-antirion/block-pii-and-prompt-injection-at-the-gateway/",
   "json": "https://dedupedai.com/use-cases/u/eliasbiondo-antirion/block-pii-and-prompt-injection-at-the-gateway.json"
  },
  {
   "id": "eliasbiondo-antirion--reproduce-gateway-benchmark-on-own-aws",
   "title": "Rerun the gateway benchmark on your own AWS account",
   "best": false,
   "url": "https://dedupedai.com/use-cases/eliasbiondo-antirion/reproduce-gateway-benchmark-on-own-aws/",
   "json": "https://dedupedai.com/use-cases/u/eliasbiondo-antirion/reproduce-gateway-benchmark-on-own-aws.json"
  }
 ],
 "disclaimer": "Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk."
}