{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZA4S2CLGRBD5XNIYFC2IZ6FXMV","short_pith_number":"pith:ZA4S2CLG","schema_version":"1.0","canonical_sha256":"c8392d09668847dbb51828b48cf8b7657c6500d1906b41c8fb5d78faf21ad36d","source":{"kind":"arxiv","id":"2606.11690","version":1},"attestation_state":"computed","paper":{"title":"Beyond Per-Token Pricing: A Concurrency-Aware Methodology for LLM Infrastructure Cost Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.PF"],"primary_cat":"cs.DC","authors_text":"Chitral Patil","submitted_at":"2026-06-10T06:07:24Z","abstract_excerpt":"Every public LLM cost calculator we surveyed treats GPU utilization as a fixed input -- entered by the user, baked in as a preset, or silently assumed at 100% -- never measured against the operator's actual load. We show that this assumption is the dominant source of error: on identical H100 hardware, effective cost spans \\$0.21 to \\$15.25 per million output tokens, an underutilization penalty of 2.5-24x across low-to-moderate enterprise loads (1-10 rps) and up to 36.3x near idle -- driven by one operator-controlled variable, offered request rate lambda, which sets in-flight concurrency via Li"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.11690","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2026-06-10T06:07:24Z","cross_cats_sorted":["cs.PF"],"title_canon_sha256":"b669def0d9009aa52dc31c7d6426c13b28aa6941dda45a04de03d9898f6c4eb1","abstract_canon_sha256":"8caeee1bdbdf15aa7892ea6498bb13781fc64b4e772461e6e303492412aa4802"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:10:02.935237Z","signature_b64":"8VinzEXhbEAezPTw4ef3gJoKRBHaetvZcfW3UHPzdvod3EuorLWQJ8gCYwalXDNI+s1Diebp0qV577Nznvj8BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8392d09668847dbb51828b48cf8b7657c6500d1906b41c8fb5d78faf21ad36d","last_reissued_at":"2026-06-11T01:10:02.934669Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:10:02.934669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Per-Token Pricing: A Concurrency-Aware Methodology for LLM Infrastructure Cost Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.PF"],"primary_cat":"cs.DC","authors_text":"Chitral Patil","submitted_at":"2026-06-10T06:07:24Z","abstract_excerpt":"Every public LLM cost calculator we surveyed treats GPU utilization as a fixed input -- entered by the user, baked in as a preset, or silently assumed at 100% -- never measured against the operator's actual load. We show that this assumption is the dominant source of error: on identical H100 hardware, effective cost spans \\$0.21 to \\$15.25 per million output tokens, an underutilization penalty of 2.5-24x across low-to-moderate enterprise loads (1-10 rps) and up to 36.3x near idle -- driven by one operator-controlled variable, offered request rate lambda, which sets in-flight concurrency via Li"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11690","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.11690/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.11690","created_at":"2026-06-11T01:10:02.934775+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.11690v1","created_at":"2026-06-11T01:10:02.934775+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11690","created_at":"2026-06-11T01:10:02.934775+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZA4S2CLGRBD5","created_at":"2026-06-11T01:10:02.934775+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZA4S2CLGRBD5XNIY","created_at":"2026-06-11T01:10:02.934775+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZA4S2CLG","created_at":"2026-06-11T01:10:02.934775+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZA4S2CLGRBD5XNIYFC2IZ6FXMV","json":"https://pith.science/pith/ZA4S2CLGRBD5XNIYFC2IZ6FXMV.json","graph_json":"https://pith.science/api/pith-number/ZA4S2CLGRBD5XNIYFC2IZ6FXMV/graph.json","events_json":"https://pith.science/api/pith-number/ZA4S2CLGRBD5XNIYFC2IZ6FXMV/events.json","paper":"https://pith.science/paper/ZA4S2CLG"},"agent_actions":{"view_html":"https://pith.science/pith/ZA4S2CLGRBD5XNIYFC2IZ6FXMV","download_json":"https://pith.science/pith/ZA4S2CLGRBD5XNIYFC2IZ6FXMV.json","view_paper":"https://pith.science/paper/ZA4S2CLG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.11690&json=true","fetch_graph":"https://pith.science/api/pith-number/ZA4S2CLGRBD5XNIYFC2IZ6FXMV/graph.json","fetch_events":"https://pith.science/api/pith-number/ZA4S2CLGRBD5XNIYFC2IZ6FXMV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZA4S2CLGRBD5XNIYFC2IZ6FXMV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZA4S2CLGRBD5XNIYFC2IZ6FXMV/action/storage_attestation","attest_author":"https://pith.science/pith/ZA4S2CLGRBD5XNIYFC2IZ6FXMV/action/author_attestation","sign_citation":"https://pith.science/pith/ZA4S2CLGRBD5XNIYFC2IZ6FXMV/action/citation_signature","submit_replication":"https://pith.science/pith/ZA4S2CLGRBD5XNIYFC2IZ6FXMV/action/replication_record"}},"created_at":"2026-06-11T01:10:02.934775+00:00","updated_at":"2026-06-11T01:10:02.934775+00:00"}