{"record": {"aliases": [], "artifacts": [{"id": "gh:enterpilot/ai-gateway-reproducible-benchmark", "kind": "repo", "url": "https://github.com/ENTERPILOT/ai-gateway-reproducible-benchmark"}], "categories": ["Language & Knowledge", "Software & AI Compute", "cs.AI"], "description": {"en": "Compares four open-source AI gateway proxies (GoModel, LiteLLM, Portkey, Bifrost) for routing overhead on a fixed AWS c7i.large instance with a mock backend. Measures latency percentiles, throughput, memory, cold start, and image size across streaming and non-streaming workloads."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://github.com/ENTERPILOT/ai-gateway-reproducible-benchmark", "source": "claire_radar", "source_url": "https://github.com/ENTERPILOT/ai-gateway-reproducible-benchmark", "title": "AI gateway reproducible benchmark"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:github:enterpilot/ai-gateway-reproducible-benchmark", "modality": null, "name": "AI gateway reproducible benchmark", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "Medium", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-candidate", "display_eligible": "false", "origin_record_id": "bm_ai-gateway-reproducible-benchmark_99ff14f3", "origin_source": "github", "recognition_confidence": "0.4", "record_sha256": "a762778791eb2335a2793250ac5df09e7d24a72fb2ad18db1fc2ebebc5801b8c", "relation": "unclear", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-08-25T15:38:21.596820Z", "source_url": "https://github.com/ENTERPILOT/ai-gateway-reproducible-benchmark"}, "publisher": null, "released": "2026-08-20", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:github:enterpilot/ai-gateway-reproducible-benchmark", "source_url": "https://github.com/ENTERPILOT/ai-gateway-reproducible-benchmark"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-github-enterpilot-ai-gateway-reproducible-benchmark", "source": "claire_radar", "source_benchmark_id": "github:enterpilot/ai-gateway-reproducible-benchmark", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Software & AI Compute"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/ENTERPILOT/ai-gateway-reproducible-benchmark", "githubScope": "benchmark_repo", "githubStars": 4, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": null, "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"state": "not_applicable"}}, "status": "fresh"}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-25T16:23:14.196185Z", "inputHash": "35ae8ea80e1f3674246c66858c75bb87488503d64361580d4c7e5e47506410d0", "model": "deepseek-v4-flash"}, "curation": {"decisionReason": "No formally declared benchmark name; it is an infrastructure comparison tool with a fixed measurement procedure rather than a scored benchmark.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-25T15:38:21.596820Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-candidate", "demo": false, "description": "Compares four open-source AI gateway proxies (GoModel, LiteLLM, Portkey, Bifrost) for routing overhead on a fixed AWS c7i.large instance with a mock backend. Measures latency percentiles, throughput, memory, cold start, and image size across streaming and non-streaming workloads.", "discoverySources": [{"id": "github:enterpilot/ai-gateway-reproducible-benchmark", "type": "github", "url": "https://github.com/ENTERPILOT/ai-gateway-reproducible-benchmark"}], "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["discovered via github", "benchmark term in abstract", "evaluation protocol evidence", "public artifact URL", "no explicit benchmark release evidence"], "snippet": "ai-gateway-reproducible-benchmark Comparing Bifrost vs LiteLLM vs GoModel vs PortkeyAI."}, "familyId": "bmf_7fb20c44ab0e", "firstSeenAt": "2026-08-23", "heat": null, "id": "bm_ai-gateway-reproducible-benchmark_99ff14f3", "indexedAt": "2026-08-23T06:55:51.988821Z", "industrySectors": ["Software & Cloud"], "links": {"code": "https://github.com/ENTERPILOT/ai-gateway-reproducible-benchmark"}, "metrics": [], "motivation": "ai-gateway-reproducible-benchmark Comparing Bifrost vs LiteLLM vs GoModel vs PortkeyAI.", "name": "AI gateway reproducible benchmark", "oneLine": "Compares four open-source AI gateway proxies (GoModel, LiteLLM, Portkey, Bifrost) for routing overhead on a fixed AWS c7i.large instance with a mock backend. Measures latency percentiles, throughput, memory, cold start, and image size across streaming and non-streaming workloads.", "paperTitle": "ai-gateway-reproducible-benchmark", "primaryDomain": "Software & AI Compute", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://github.com/ENTERPILOT/ai-gateway-reproducible-benchmark", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-23T06:55:51.988821Z"}, "publications": [], "publishers": [{"name": "ENTERPILOT", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://github.com/ENTERPILOT/ai-gateway-reproducible-benchmark"}], "ranking": {"90d": {"confidence": "Low", "coverage": 0.55, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.21483102985913266, "value": 4}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 198, "score": 34}, "method": "attention-ranking-v13", "rank": 198, "score": 34}}, "readiness": "Runnable", "recognitionConfidence": 0.4, "relation": "unclear", "releasedAt": "2026-08-20", "source": {"authors": ["ENTERPILOT"], "categories": [], "id": "github:enterpilot/ai-gateway-reproducible-benchmark", "title": "ai-gateway-reproducible-benchmark", "type": "github", "url": "https://github.com/ENTERPILOT/ai-gateway-reproducible-benchmark"}, "sourceUpdatedAt": "2026-08-21T09:28:29Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Provides reproducible infrastructure for comparing AI gateway proxies in isolation, enabling teams to evaluate gateway overhead without model or network latency. Useful for capacity planning and technology selection decisions."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
