{"id":"https://openalex.org/W7206149273","doi":"https://doi.org/10.48550/arxiv.2609.00710","title":"Prediction-Assisted Pricing and Admission for LLM APIs with Stochastic Token Consumption","display_name":"Prediction-Assisted Pricing and Admission for LLM APIs with Stochastic Token Consumption","publication_year":2026,"publication_date":"2026-09-01","ids":{"openalex":"https://openalex.org/W7206149273","doi":"https://doi.org/10.48550/arxiv.2609.00710"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.00710","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.00710","pdf_url":"https://arxiv.org/pdf/2609.00710","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.00710","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5149235024","display_name":"Patrick Wong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wong, Patrick","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5149235024"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9643999934196472,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9643999934196472,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.026900000870227814,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.003100000089034438,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/shadow-prices","display_name":"shadow prices","score":0.47699999809265137},{"id":"https://openalex.org/keywords/regret-bounds","display_name":"regret bounds","score":0.6460000276565552},{"id":"https://openalex.org/keywords/stochastic-resource-allocation","display_name":"stochastic resource allocation","score":0.5509999990463257}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6733999848365784},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.641700029373169},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.5922999978065491},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5167999863624573},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.5157999992370605},{"id":"https://openalex.org/C2777632111","wikidata":"https://www.wikidata.org/wiki/Q1937518","display_name":"Reservation","level":2,"score":0.515500009059906},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46560001373291016},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.44209998846054077},{"id":"https://openalex.org/C102408133","wikidata":"https://www.wikidata.org/wiki/Q5156350","display_name":"Competitive analysis","level":3,"score":0.42500001192092896},{"id":"https://openalex.org/C163239763","wikidata":"https://www.wikidata.org/wiki/Q5153637","display_name":"Common value auction","level":2,"score":0.42239999771118164},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.41019999980926514},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.397599995136261},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.3709000051021576},{"id":"https://openalex.org/C196921405","wikidata":"https://www.wikidata.org/wiki/Q786431","display_name":"Online algorithm","level":2,"score":0.3698999881744385},{"id":"https://openalex.org/C117797892","wikidata":"https://www.wikidata.org/wiki/Q286363","display_name":"Shadow (psychology)","level":2,"score":0.3675999939441681},{"id":"https://openalex.org/C2777548347","wikidata":"https://www.wikidata.org/wiki/Q5456937","display_name":"Flagging","level":2,"score":0.3580000102519989},{"id":"https://openalex.org/C178635117","wikidata":"https://www.wikidata.org/wiki/Q747499","display_name":"RADIUS","level":2,"score":0.35190001130104065},{"id":"https://openalex.org/C73602740","wikidata":"https://www.wikidata.org/wiki/Q7795822","display_name":"Thompson sampling","level":3,"score":0.35040000081062317},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C139748260","wikidata":"https://www.wikidata.org/wiki/Q3308839","display_name":"Shadow price","level":2,"score":0.3407999873161316},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C75949130","wikidata":"https://www.wikidata.org/wiki/Q848010","display_name":"Database transaction","level":2,"score":0.33239999413490295},{"id":"https://openalex.org/C30772137","wikidata":"https://www.wikidata.org/wiki/Q5164762","display_name":"Consumption (sociology)","level":2,"score":0.3310999870300293},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.3273000121116638},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.32690000534057617},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3231000006198883},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.32019999623298645},{"id":"https://openalex.org/C89246107","wikidata":"https://www.wikidata.org/wiki/Q1398821","display_name":"Rule of thumb","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C65155139","wikidata":"https://www.wikidata.org/wiki/Q5380912","display_name":"Envelope (radar)","level":3,"score":0.30379998683929443},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2678000032901764},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2615000009536743},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.250900000333786},{"id":"https://openalex.org/C20533482","wikidata":"https://www.wikidata.org/wiki/Q3174091","display_name":"Overconsumption","level":3,"score":0.25060001015663147}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.00710","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.00710","pdf_url":"https://arxiv.org/pdf/2609.00710","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.00710","doi":"https://doi.org/10.48550/arxiv.2609.00710","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.00710","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.00710","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.00710","pdf_url":"https://arxiv.org/pdf/2609.00710","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7206149273.pdf","grobid_xml":"https://content.openalex.org/works/W7206149273.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7223314771","https://openalex.org/W7214969603","https://openalex.org/W4392088194","https://openalex.org/W4416237307","https://openalex.org/W7171806390","https://openalex.org/W4416679450","https://openalex.org/W7220973746","https://openalex.org/W4283802315","https://openalex.org/W7152673404","https://openalex.org/W7172209740"],"abstract_inverted_index":{"An":[0,119],"LLM":[1],"application":[2],"often":[3],"sells":[4],"or":[5,13,18,107],"internally":[6],"allocates":[7],"several":[8],"service":[9],"products:":[10],"a":[11,16,36,43,104,123,156,164,184,190,197],"small":[12],"premium":[14],"model,":[15],"short":[17],"long":[19],"token":[20,44],"cap,":[21],"and":[22,50,56,63,67,87,113,154,212,241],"possibly":[23],"multiple":[24],"posted":[25],"prices.":[26,230],"The":[27,101,161,179],"operational":[28,228],"decision":[29],"is":[30,181,194],"not":[31],"merely":[32],"which":[33,137],"model":[34,76],"answers":[35],"prompt.":[37],"A":[38],"price":[39],"changes":[40,46],"purchase":[41],"probability,":[42],"cap":[45],"both":[47],"user":[48],"value":[49],"the":[51,139,173,201,205,232],"tail":[52],"of":[53,204],"resource":[54,91,114,151],"consumption,":[55],"accepted":[57],"requests":[58],"compete":[59],"for":[60,128],"shared":[61],"compute":[62],"premium-model":[64],"capacity.":[65],"Demand":[66],"output":[68],"length":[69],"are":[70,116,177],"initially":[71],"uncertain,":[72],"while":[73,169],"an":[74,98,144,237],"offline":[75,120,140],"may":[77],"provide":[78],"useful":[79],"but":[80],"imperfect":[81],"predictions.":[82],"We":[83,132],"formulate":[84],"sequential":[85],"pricing":[86],"admission":[88],"with":[89,143],"stochastic":[90],"consumption.":[92],"Each":[93],"arriving":[94],"request":[95],"belongs":[96],"to":[97],"observable":[99],"segment.":[100],"platform":[102,174],"chooses":[103],"product--price":[105],"pair":[106],"makes":[108],"no":[109],"offer;":[110],"purchase,":[111],"revenue,":[112],"use":[115],"then":[117],"random.":[118],"predictor":[121],"supplies":[122],"uniform,":[124],"validated":[125],"error":[126],"radius":[127,214],"every":[129,249],"segment--product":[130],"cell.":[131],"propose":[133],"Prediction-Clipped":[134],"UCB":[135],"(PCUCB),":[136],"intersects":[138],"prediction":[141,213],"interval":[142],"online":[145,170],"confidence":[146,186],"interval,":[147],"evaluates":[148],"products":[149],"using":[150],"shadow":[152,229],"prices,":[153],"reserves":[155],"sample-path":[157],"envelope":[158],"before":[159],"commitment.":[160],"prior":[162],"gives":[163],"fast":[165],"start":[166],"when":[167,175],"accurate,":[168],"learning":[171,242],"protects":[172],"predictions":[176],"coarse.":[178],"analysis":[180],"modular.":[182],"On":[183],"simultaneous":[185],"event,":[187],"regret":[188],"against":[189],"buffered":[191],"fluid":[192],"benchmark":[193],"bounded":[195],"by":[196],"pacing":[198],"term":[199],"plus":[200],"cumulative":[202],"diameter":[203],"intersected":[206],"intervals.":[207],"For":[208],"$J$":[209],"segment-product":[210],"cells":[211],"$\\varepsilon$,":[215],"this":[216],"yields":[217],"\\[":[218],"\\widetilde":[219],"O\\left(":[220],"\\sqrt{T}+(1+\\bar\u039b)":[221],"\\min\\{T\\varepsilon,\\sqrt{JT}\\}":[222],"\\right),":[223],"\\]":[224],"where":[225],"$\\bar\u039b$":[226],"bounds":[227],"Thus":[231],"algorithm":[233],"smoothly":[234],"interpolates":[235],"between":[236],"almost":[238],"full-information":[239],"regime":[240],"from":[243],"scratch.":[244],"Hard":[245],"feasibility":[246],"holds":[247],"on":[248],"sample":[250],"path":[251],"through":[252],"reservation":[253],"envelopes.":[254]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-03T00:00:00"}