OpenSource
/
ragflow
Seguir 4
Destacar 0
Fork 0
Código Incidencias 0 Peticiones pull 0 Lanzamientos 33 Wiki Actividad
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
951 Commits
7 Ramas
Árbol: e013ac52af
Ramas Etiquetas
${ item.name }
Crear rama ${ searchTerm }
desde 'e013ac52af'
${ noResults }
ragflow/conf/llm_factories.json

llm_factories.json 108KB
Original Blame Histórico

12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076107710781079108010811082108310841085108610871088108910901091109210931094109510961097109810991100110111021103110411051106110711081109111011111112111311141115111611171118111911201121112211231124112511261127112811291130113111321133113411351136113711381139114011411142114311441145114611471148114911501151115211531154115511561157115811591160116111621163116411651166116711681169117011711172117311741175117611771178117911801181118211831184118511861187118811891190119111921193119411951196119711981199120012011202120312041205120612071208120912101211121212131214121512161217121812191220122112221223122412251226122712281229123012311232123312341235123612371238123912401241124212431244124512461247124812491250125112521253125412551256125712581259126012611262126312641265126612671268126912701271127212731274127512761277127812791280128112821283128412851286128712881289129012911292129312941295129612971298129913001301130213031304130513061307130813091310131113121313131413151316131713181319132013211322132313241325132613271328132913301331133213331334133513361337133813391340134113421343134413451346134713481349135013511352135313541355135613571358135913601361136213631364136513661367136813691370137113721373137413751376137713781379138013811382138313841385138613871388138913901391139213931394139513961397139813991400140114021403140414051406140714081409141014111412141314141415141614171418141914201421142214231424142514261427142814291430143114321433143414351436143714381439144014411442144314441445144614471448144914501451145214531454145514561457145814591460146114621463146414651466146714681469147014711472147314741475147614771478147914801481148214831484148514861487148814891490149114921493149414951496149714981499150015011502150315041505150615071508150915101511151215131514151515161517151815191520152115221523152415251526152715281529153015311532153315341535153615371538153915401541154215431544154515461547154815491550155115521553155415551556155715581559156015611562156315641565156615671568156915701571157215731574157515761577157815791580158115821583158415851586158715881589159015911592159315941595159615971598159916001601160216031604160516061607160816091610161116121613161416151616161716181619162016211622162316241625162616271628162916301631163216331634163516361637163816391640164116421643164416451646164716481649165016511652165316541655165616571658165916601661166216631664166516661667166816691670167116721673167416751676167716781679168016811682168316841685168616871688168916901691169216931694169516961697169816991700170117021703170417051706170717081709171017111712171317141715171617171718171917201721172217231724172517261727172817291730173117321733173417351736173717381739174017411742174317441745174617471748174917501751175217531754175517561757175817591760176117621763176417651766176717681769177017711772177317741775177617771778177917801781178217831784178517861787178817891790179117921793179417951796179717981799180018011802180318041805180618071808180918101811181218131814181518161817181818191820182118221823182418251826182718281829183018311832183318341835183618371838183918401841184218431844184518461847184818491850185118521853185418551856185718581859186018611862186318641865186618671868186918701871187218731874187518761877187818791880188118821883188418851886188718881889189018911892189318941895189618971898189919001901190219031904190519061907190819091910191119121913191419151916191719181919192019211922192319241925192619271928192919301931193219331934193519361937193819391940194119421943194419451946194719481949195019511952195319541955195619571958195919601961196219631964196519661967196819691970197119721973197419751976197719781979198019811982198319841985198619871988198919901991199219931994199519961997199819992000200120022003200420052006200720082009201020112012201320142015201620172018201920202021202220232024202520262027202820292030203120322033203420352036203720382039204020412042204320442045204620472048204920502051205220532054205520562057205820592060206120622063206420652066206720682069207020712072207320742075207620772078207920802081208220832084208520862087208820892090209120922093209420952096209720982099210021012102210321042105210621072108210921102111211221132114211521162117211821192120212121222123212421252126212721282129213021312132213321342135213621372138213921402141214221432144214521462147214821492150215121522153215421552156215721582159216021612162216321642165216621672168216921702171217221732174217521762177217821792180218121822183218421852186218721882189219021912192219321942195219621972198219922002201220222032204220522062207220822092210221122122213221422152216221722182219222022212222222322242225222622272228222922302231223222332234223522362237223822392240224122422243224422452246224722482249225022512252225322542255225622572258225922602261226222632264226522662267226822692270227122722273227422752276227722782279228022812282228322842285228622872288228922902291229222932294229522962297229822992300230123022303230423052306230723082309231023112312231323142315231623172318231923202321232223232324232523262327232823292330233123322333233423352336233723382339234023412342234323442345234623472348234923502351235223532354235523562357235823592360236123622363236423652366236723682369237023712372237323742375237623772378237923802381238223832384238523862387238823892390239123922393239423952396239723982399240024012402240324042405240624072408240924102411241224132414241524162417241824192420242124222423242424252426242724282429243024312432243324342435243624372438243924402441244224432444244524462447244824492450245124522453245424552456245724582459246024612462246324642465246624672468246924702471247224732474247524762477247824792480248124822483248424852486248724882489249024912492249324942495249624972498249925002501250225032504250525062507250825092510251125122513251425152516251725182519252025212522252325242525252625272528252925302531253225332534253525362537253825392540254125422543254425452546254725482549255025512552255325542555255625572558255925602561256225632564256525662567256825692570257125722573257425752576257725782579258025812582258325842585258625872588258925902591259225932594259525962597259825992600260126022603260426052606260726082609261026112612261326142615261626172618261926202621262226232624262526262627262826292630263126322633263426352636263726382639264026412642264326442645264626472648264926502651265226532654265526562657265826592660266126622663266426652666266726682669267026712672267326742675267626772678267926802681268226832684268526862687268826892690269126922693269426952696269726982699270027012702270327042705270627072708270927102711271227132714271527162717271827192720272127222723272427252726272727282729273027312732273327342735273627372738273927402741274227432744274527462747274827492750275127522753275427552756275727582759276027612762276327642765276627672768276927702771277227732774277527762777277827792780278127822783278427852786278727882789279027912792279327942795279627972798279928002801280228032804280528062807280828092810281128122813281428152816281728182819282028212822282328242825282628272828282928302831283228332834283528362837283828392840284128422843284428452846284728482849285028512852285328542855285628572858285928602861286228632864286528662867286828692870287128722873287428752876287728782879288028812882288328842885288628872888288928902891289228932894289528962897289828992900290129022903290429052906290729082909291029112912291329142915291629172918291929202921292229232924292529262927292829292930293129322933293429352936293729382939294029412942294329442945294629472948294929502951295229532954295529562957295829592960296129622963296429652966296729682969297029712972297329742975297629772978297929802981298229832984298529862987298829892990299129922993299429952996299729982999300030013002300330043005300630073008300930103011301230133014301530163017301830193020302130223023302430253026302730283029303030313032303330343035303630373038303930403041304230433044304530463047304830493050305130523053305430553056 
  1. {

  2.     "factory_llm_infos": [

  3.         {

  4.             "name": "OpenAI",

  5.             "logo": "",

  6.             "tags": "LLM,TEXT EMBEDDING,SPEECH2TEXT,MODERATION",

  7.             "status": "1",

  8.             "llm": [

  9.                 {

  10.                     "llm_name": "gpt-4o-mini",

  11.                     "tags": "LLM,CHAT,128K",

  12.                     "max_tokens": 128000,

  13.                     "model_type": "chat"

  14.                 },

  15.                 {

  16.                     "llm_name": "gpt-4o",

  17.                     "tags": "LLM,CHAT,128K",

  18.                     "max_tokens": 128000,

  19.                     "model_type": "chat"

  20.                 },

  21.                 {

  22.                     "llm_name": "gpt-3.5-turbo",

  23.                     "tags": "LLM,CHAT,4K",

  24.                     "max_tokens": 4096,

  25.                     "model_type": "chat"

  26.                 },

  27.                 {

  28.                     "llm_name": "gpt-3.5-turbo-16k-0613",

  29.                     "tags": "LLM,CHAT,16k",

  30.                     "max_tokens": 16385,

  31.                     "model_type": "chat"

  32.                 },

  33.                 {

  34.                     "llm_name": "text-embedding-ada-002",

  35.                     "tags": "TEXT EMBEDDING,8K",

  36.                     "max_tokens": 8191,

  37.                     "model_type": "embedding"

  38.                 },

  39.                 {

  40.                     "llm_name": "text-embedding-3-small",

  41.                     "tags": "TEXT EMBEDDING,8K",

  42.                     "max_tokens": 8191,

  43.                     "model_type": "embedding"

  44.                 },

  45.                 {

  46.                     "llm_name": "text-embedding-3-large",

  47.                     "tags": "TEXT EMBEDDING,8K",

  48.                     "max_tokens": 8191,

  49.                     "model_type": "embedding"

  50.                 },

  51.                 {

  52.                     "llm_name": "whisper-1",

  53.                     "tags": "SPEECH2TEXT",

  54.                     "max_tokens": 26214400,

  55.                     "model_type": "speech2text"

  56.                 },

  57.                 {

  58.                     "llm_name": "gpt-4",

  59.                     "tags": "LLM,CHAT,8K",

  60.                     "max_tokens": 8191,

  61.                     "model_type": "chat"

  62.                 },

  63.                 {

  64.                     "llm_name": "gpt-4-turbo",

  65.                     "tags": "LLM,CHAT,8K",

  66.                     "max_tokens": 8191,

  67.                     "model_type": "chat"

  68.                 },

  69.                 {

  70.                     "llm_name": "gpt-4-32k",

  71.                     "tags": "LLM,CHAT,32K",

  72.                     "max_tokens": 32768,

  73.                     "model_type": "chat"

  74.                 },

  75.                 {

  76.                     "llm_name": "gpt-4-vision-preview",

  77.                     "tags": "LLM,CHAT,IMAGE2TEXT",

  78.                     "max_tokens": 765,

  79.                     "model_type": "image2text"

  80.                 }

  81.             ]

  82.         },

  83.         {

  84.             "name": "Tongyi-Qianwen",

  85.             "logo": "",

  86.             "tags": "LLM,TEXT EMBEDDING,SPEECH2TEXT,MODERATION",

  87.             "status": "1",

  88.             "llm": [

  89.                 {

  90.                     "llm_name": "qwen-turbo",

  91.                     "tags": "LLM,CHAT,8K",

  92.                     "max_tokens": 8191,

  93.                     "model_type": "chat"

  94.                 },

  95.                 {

  96.                     "llm_name": "qwen-plus",

  97.                     "tags": "LLM,CHAT,32K",

  98.                     "max_tokens": 32768,

  99.                     "model_type": "chat"

  100.                 },

  101.                 {

  102.                     "llm_name": "text-embedding-v2",

  103.                     "tags": "TEXT EMBEDDING,2K",

  104.                     "max_tokens": 2048,

  105.                     "model_type": "embedding"

  106.                 },

  107.                 {

  108.                     "llm_name": "paraformer-realtime-8k-v1",

  109.                     "tags": "SPEECH2TEXT",

  110.                     "max_tokens": 26214400,

  111.                     "model_type": "speech2text"

  112.                 },

  113.                 {

  114.                     "llm_name": "qwen-vl-max",

  115.                     "tags": "LLM,CHAT,IMAGE2TEXT",

  116.                     "max_tokens": 765,

  117.                     "model_type": "image2text"

  118.                 },

  119.                 {

  120.                     "llm_name": "qwen-vl-plus",

  121.                     "tags": "LLM,CHAT,IMAGE2TEXT",

  122.                     "max_tokens": 765,

  123.                     "model_type": "image2text"

  124.                 }

  125.             ]

  126.         },

  127.         {

  128.             "name": "ZHIPU-AI",

  129.             "logo": "",

  130.             "tags": "LLM,TEXT EMBEDDING,SPEECH2TEXT,MODERATION",

  131.             "status": "1",

  132.             "llm": [

  133.                 {

  134.                     "llm_name": "glm-3-turbo",

  135.                     "tags": "LLM,CHAT,",

  136.                     "max_tokens": 128000,

  137.                     "model_type": "chat"

  138.                 },

  139.                 {

  140.                     "llm_name": "glm-4",

  141.                     "tags": "LLM,CHAT,",

  142.                     "max_tokens": 128000,

  143.                     "model_type": "chat"

  144.                 },

  145.                 {

  146.                     "llm_name": "glm-4v",

  147.                     "tags": "LLM,CHAT,IMAGE2TEXT",

  148.                     "max_tokens": 2000,

  149.                     "model_type": "image2text"

  150.                 },

  151.                 {

  152.                     "llm_name": "embedding-2",

  153.                     "tags": "TEXT EMBEDDING",

  154.                     "max_tokens": 512,

  155.                     "model_type": "embedding"

  156.                 }

  157.             ]

  158.         },

  159.         {

  160.             "name": "Ollama",

  161.             "logo": "",

  162.             "tags": "LLM,TEXT EMBEDDING,SPEECH2TEXT,MODERATION",

  163.             "status": "1",

  164.             "llm": []

  165.         },

  166.         {

  167.             "name": "LocalAI",

  168.             "logo": "",

  169.             "tags": "LLM,TEXT EMBEDDING,SPEECH2TEXT,MODERATION",

  170.             "status": "1",

  171.             "llm": []

  172.         },

  173.         {

  174.             "name": "OpenAI-API-Compatible",

  175.             "logo": "",

  176.             "tags": "LLM,TEXT EMBEDDING,SPEECH2TEXT,MODERATION",

  177.             "status": "1",

  178.             "llm": []

  179.         },

  180.         {

  181.             "name": "Moonshot",

  182.             "logo": "",

  183.             "tags": "LLM,TEXT EMBEDDING",

  184.             "status": "1",

  185.             "llm": [

  186.                 {

  187.                     "llm_name": "moonshot-v1-8k",

  188.                     "tags": "LLM,CHAT,",

  189.                     "max_tokens": 7900,

  190.                     "model_type": "chat"

  191.                 },

  192.                 {

  193.                     "llm_name": "moonshot-v1-32k",

  194.                     "tags": "LLM,CHAT,",

  195.                     "max_tokens": 32768,

  196.                     "model_type": "chat"

  197.                 },

  198.                 {

  199.                     "llm_name": "moonshot-v1-128k",

  200.                     "tags": "LLM,CHAT",

  201.                     "max_tokens": 128000,

  202.                     "model_type": "chat"

  203.                 }

  204.             ]

  205.         },

  206.         {

  207.             "name": "FastEmbed",

  208.             "logo": "",

  209.             "tags": "TEXT EMBEDDING",

  210.             "status": "1",

  211.             "llm": [

  212.                 {

  213.                     "llm_name": "BAAI/bge-small-en-v1.5",

  214.                     "tags": "TEXT EMBEDDING,",

  215.                     "max_tokens": 512,

  216.                     "model_type": "embedding"

  217.                 },

  218.                 {

  219.                     "llm_name": "BAAI/bge-small-zh-v1.5",

  220.                     "tags": "TEXT EMBEDDING,",

  221.                     "max_tokens": 512,

  222.                     "model_type": "embedding"

  223.                 },

  224.                 {

  225.                     "llm_name": "BAAI/bge-base-en-v1.5",

  226.                     "tags": "TEXT EMBEDDING,",

  227.                     "max_tokens": 512,

  228.                     "model_type": "embedding"

  229.                 },

  230.                 {

  231.                     "llm_name": "BAAI/bge-large-en-v1.5",

  232.                     "tags": "TEXT EMBEDDING,",

  233.                     "max_tokens": 512,

  234.                     "model_type": "embedding"

  235.                 },

  236.                 {

  237.                     "llm_name": "sentence-transformers/all-MiniLM-L6-v2",

  238.                     "tags": "TEXT EMBEDDING,",

  239.                     "max_tokens": 512,

  240.                     "model_type": "embedding"

  241.                 },

  242.                 {

  243.                     "llm_name": "nomic-ai/nomic-embed-text-v1.5",

  244.                     "tags": "TEXT EMBEDDING,",

  245.                     "max_tokens": 8192,

  246.                     "model_type": "embedding"

  247.                 },

  248.                 {

  249.                     "llm_name": "jinaai/jina-embeddings-v2-small-en",

  250.                     "tags": "TEXT EMBEDDING,",

  251.                     "max_tokens": 2147483648,

  252.                     "model_type": "embedding"

  253.                 },

  254.                 {

  255.                     "llm_name": "jinaai/jina-embeddings-v2-base-en",

  256.                     "tags": "TEXT EMBEDDING,",

  257.                     "max_tokens": 2147483648,

  258.                     "model_type": "embedding"

  259.                 }

  260.             ]

  261.         },

  262.         {

  263.             "name": "Xinference",

  264.             "logo": "",

  265.             "tags": "LLM,TEXT EMBEDDING,SPEECH2TEXT,MODERATION,TEXT RE-RANK",

  266.             "status": "1",

  267.             "llm": []

  268.         },

  269.         {

  270.             "name": "Youdao",

  271.             "logo": "",

  272.             "tags": "LLM,TEXT EMBEDDING,SPEECH2TEXT,MODERATION",

  273.             "status": "1",

  274.             "llm": [

  275.                 {

  276.                     "llm_name": "maidalun1020/bce-embedding-base_v1",

  277.                     "tags": "TEXT EMBEDDING,",

  278.                     "max_tokens": 512,

  279.                     "model_type": "embedding"

  280.                 },

  281.                 {

  282.                     "llm_name": "maidalun1020/bce-reranker-base_v1",

  283.                     "tags": "RE-RANK, 512",

  284.                     "max_tokens": 512,

  285.                     "model_type": "rerank"

  286.                 }

  287.             ]

  288.         },

  289.         {

  290.             "name": "DeepSeek",

  291.             "logo": "",

  292.             "tags": "LLM",

  293.             "status": "1",

  294.             "llm": [

  295.                 {

  296.                     "llm_name": "deepseek-chat",

  297.                     "tags": "LLM,CHAT,",

  298.                     "max_tokens": 32768,

  299.                     "model_type": "chat"

  300.                 },

  301.                 {

  302.                     "llm_name": "deepseek-coder",

  303.                     "tags": "LLM,CHAT,",

  304.                     "max_tokens": 16385,

  305.                     "model_type": "chat"

  306.                 }

  307.             ]

  308.         },

  309.         {

  310.             "name": "VolcEngine",

  311.             "logo": "",

  312.             "tags": "LLM, TEXT EMBEDDING",

  313.             "status": "1",

  314.             "llm": [

  315.                 {

  316.                     "llm_name": "Skylark2-pro-32k",

  317.                     "tags": "LLM,CHAT,32k",

  318.                     "max_tokens": 32768,

  319.                     "model_type": "chat"

  320.                 },

  321.                 {

  322.                     "llm_name": "Skylark2-pro-4k",

  323.                     "tags": "LLM,CHAT,4k",

  324.                     "max_tokens": 4096,

  325.                     "model_type": "chat"

  326.                 }

  327.             ]

  328.         },

  329.         {

  330.             "name": "BaiChuan",

  331.             "logo": "",

  332.             "tags": "LLM,TEXT EMBEDDING",

  333.             "status": "1",

  334.             "llm": [

  335.                 {

  336.                     "llm_name": "Baichuan2-Turbo",

  337.                     "tags": "LLM,CHAT,32K",

  338.                     "max_tokens": 32768,

  339.                     "model_type": "chat"

  340.                 },

  341.                 {

  342.                     "llm_name": "Baichuan2-Turbo-192k",

  343.                     "tags": "LLM,CHAT,192K",

  344.                     "max_tokens": 196608,

  345.                     "model_type": "chat"

  346.                 },

  347.                 {

  348.                     "llm_name": "Baichuan3-Turbo",

  349.                     "tags": "LLM,CHAT,32K",

  350.                     "max_tokens": 32768,

  351.                     "model_type": "chat"

  352.                 },

  353.                 {

  354.                     "llm_name": "Baichuan3-Turbo-128k",

  355.                     "tags": "LLM,CHAT,128K",

  356.                     "max_tokens": 131072,

  357.                     "model_type": "chat"

  358.                 },

  359.                 {

  360.                     "llm_name": "Baichuan4",

  361.                     "tags": "LLM,CHAT,128K",

  362.                     "max_tokens": 131072,

  363.                     "model_type": "chat"

  364.                 },

  365.                 {

  366.                     "llm_name": "Baichuan-Text-Embedding",

  367.                     "tags": "TEXT EMBEDDING",

  368.                     "max_tokens": 512,

  369.                     "model_type": "embedding"

  370.                 }

  371.             ]

  372.         },

  373.         {

  374.             "name": "Jina",

  375.             "logo": "",

  376.             "tags": "TEXT EMBEDDING, TEXT RE-RANK",

  377.             "status": "1",

  378.             "llm": [

  379.                 {

  380.                     "llm_name": "jina-reranker-v1-base-en",

  381.                     "tags": "RE-RANK,8k",

  382.                     "max_tokens": 8196,

  383.                     "model_type": "rerank"

  384.                 },

  385.                 {

  386.                     "llm_name": "jina-reranker-v1-turbo-en",

  387.                     "tags": "RE-RANK,8k",

  388.                     "max_tokens": 8196,

  389.                     "model_type": "rerank"

  390.                 },

  391.                 {

  392.                     "llm_name": "jina-reranker-v1-tiny-en",

  393.                     "tags": "RE-RANK,8k",

  394.                     "max_tokens": 8196,

  395.                     "model_type": "rerank"

  396.                 },

  397.                 {

  398.                     "llm_name": "jina-colbert-v1-en",

  399.                     "tags": "RE-RANK,8k",

  400.                     "max_tokens": 8196,

  401.                     "model_type": "rerank"

  402.                 },

  403.                 {

  404.                     "llm_name": "jina-embeddings-v2-base-en",

  405.                     "tags": "TEXT EMBEDDING",

  406.                     "max_tokens": 8196,

  407.                     "model_type": "embedding"

  408.                 },

  409.                 {

  410.                     "llm_name": "jina-embeddings-v2-base-de",

  411.                     "tags": "TEXT EMBEDDING",

  412.                     "max_tokens": 8196,

  413.                     "model_type": "embedding"

  414.                 },

  415.                 {

  416.                     "llm_name": "jina-embeddings-v2-base-es",

  417.                     "tags": "TEXT EMBEDDING",

  418.                     "max_tokens": 8196,

  419.                     "model_type": "embedding"

  420.                 },

  421.                 {

  422.                     "llm_name": "jina-embeddings-v2-base-code",

  423.                     "tags": "TEXT EMBEDDING",

  424.                     "max_tokens": 8196,

  425.                     "model_type": "embedding"

  426.                 },

  427.                 {

  428.                     "llm_name": "jina-embeddings-v2-base-zh",

  429.                     "tags": "TEXT EMBEDDING",

  430.                     "max_tokens": 8196,

  431.                     "model_type": "embedding"

  432.                 }

  433.             ]

  434.         },

  435.         {

  436.             "name": "BAAI",

  437.             "logo": "",

  438.             "tags": "TEXT EMBEDDING, TEXT RE-RANK",

  439.             "status": "1",

  440.             "llm": [

  441.                 {

  442.                     "llm_name": "BAAI/bge-large-zh-v1.5",

  443.                     "tags": "TEXT EMBEDDING,",

  444.                     "max_tokens": 1024,

  445.                     "model_type": "embedding"

  446.                 },

  447.                 {

  448.                     "llm_name": "BAAI/bge-reranker-v2-m3",

  449.                     "tags": "RE-RANK,2k",

  450.                     "max_tokens": 2048,

  451.                     "model_type": "rerank"

  452.                 }

  453.             ]

  454.         },

  455.         {

  456.             "name": "MiniMax",

  457.             "logo": "",

  458.             "tags": "LLM,TEXT EMBEDDING",

  459.             "status": "1",

  460.             "llm": [

  461.                 {

  462.                     "llm_name": "abab6.5-chat",

  463.                     "tags": "LLM,CHAT,8k",

  464.                     "max_tokens": 8192,

  465.                     "model_type": "chat"

  466.                 },

  467.                 {

  468.                     "llm_name": "abab6.5s-chat",

  469.                     "tags": "LLM,CHAT,245k",

  470.                     "max_tokens": 245760,

  471.                     "model_type": "chat"

  472.                 },

  473.                 {

  474.                     "llm_name": "abab6.5t-chat",

  475.                     "tags": "LLM,CHAT,8k",

  476.                     "max_tokens": 8192,

  477.                     "model_type": "chat"

  478.                 },

  479.                 {

  480.                     "llm_name": "abab6.5g-chat",

  481.                     "tags": "LLM,CHAT,8k",

  482.                     "max_tokens": 8192,

  483.                     "model_type": "chat"

  484.                 },

  485.                 {

  486.                     "llm_name": "abab5.5s-chat",

  487.                     "tags": "LLM,CHAT,8k",

  488.                     "max_tokens": 8192,

  489.                     "model_type": "chat"

  490.                 }

  491.             ]

  492.         },

  493.         {

  494.             "name": "Mistral",

  495.             "logo": "",

  496.             "tags": "LLM,TEXT EMBEDDING",

  497.             "status": "1",

  498.             "llm": [

  499.                 {

  500.                     "llm_name": "open-mixtral-8x22b",

  501.                     "tags": "LLM,CHAT,64k",

  502.                     "max_tokens": 64000,

  503.                     "model_type": "chat"

  504.                 },

  505.                 {

  506.                     "llm_name": "open-mixtral-8x7b",

  507.                     "tags": "LLM,CHAT,32k",

  508.                     "max_tokens": 32000,

  509.                     "model_type": "chat"

  510.                 },

  511.                 {

  512.                     "llm_name": "open-mistral-7b",

  513.                     "tags": "LLM,CHAT,32k",

  514.                     "max_tokens": 32000,

  515.                     "model_type": "chat"

  516.                 },

  517.                 {

  518.                     "llm_name": "mistral-large-latest",

  519.                     "tags": "LLM,CHAT,32k",

  520.                     "max_tokens": 32000,

  521.                     "model_type": "chat"

  522.                 },

  523.                 {

  524.                     "llm_name": "mistral-small-latest",

  525.                     "tags": "LLM,CHAT,32k",

  526.                     "max_tokens": 32000,

  527.                     "model_type": "chat"

  528.                 },

  529.                 {

  530.                     "llm_name": "mistral-medium-latest",

  531.                     "tags": "LLM,CHAT,32k",

  532.                     "max_tokens": 32000,

  533.                     "model_type": "chat"

  534.                 },

  535.                 {

  536.                     "llm_name": "codestral-latest",

  537.                     "tags": "LLM,CHAT,32k",

  538.                     "max_tokens": 32000,

  539.                     "model_type": "chat"

  540.                 },

  541.                 {

  542.                     "llm_name": "mistral-embed",

  543.                     "tags": "LLM,CHAT,8k",

  544.                     "max_tokens": 8192,

  545.                     "model_type": "embedding"

  546.                 }

  547.             ]

  548.         },

  549.         {

  550.             "name": "Azure-OpenAI",

  551.             "logo": "",

  552.             "tags": "LLM,TEXT EMBEDDING,SPEECH2TEXT,MODERATION",

  553.             "status": "1",

  554.             "llm": [

  555.                 {

  556.                     "llm_name": "azure-gpt-4o-mini",

  557.                     "tags": "LLM,CHAT,128K",

  558.                     "max_tokens": 128000,

  559.                     "model_type": "image2text"

  560.                 },

  561.                 {

  562.                     "llm_name": "azure-gpt-4o",

  563.                     "tags": "LLM,CHAT,128K",

  564.                     "max_tokens": 128000,

  565.                     "model_type": "chat,image2text"

  566.                 },

  567.                 {

  568.                     "llm_name": "azure-gpt-35-turbo",

  569.                     "tags": "LLM,CHAT,4K",

  570.                     "max_tokens": 4096,

  571.                     "model_type": "chat"

  572.                 },

  573.                 {

  574.                     "llm_name": "azure-gpt-35-turbo-16k",

  575.                     "tags": "LLM,CHAT,16k",

  576.                     "max_tokens": 16385,

  577.                     "model_type": "chat"

  578.                 },

  579.                 {

  580.                     "llm_name": "azure-text-embedding-ada-002",

  581.                     "tags": "TEXT EMBEDDING,8K",

  582.                     "max_tokens": 8191,

  583.                     "model_type": "embedding"

  584.                 },

  585.                 {

  586.                     "llm_name": "azure-text-embedding-3-small",

  587.                     "tags": "TEXT EMBEDDING,8K",

  588.                     "max_tokens": 8191,

  589.                     "model_type": "embedding"

  590.                 },

  591.                 {

  592.                     "llm_name": "azure-text-embedding-3-large",

  593.                     "tags": "TEXT EMBEDDING,8K",

  594.                     "max_tokens": 8191,

  595.                     "model_type": "embedding"

  596.                 },

  597.                 {

  598.                     "llm_name": "azure-whisper-1",

  599.                     "tags": "SPEECH2TEXT",

  600.                     "max_tokens": 26214400,

  601.                     "model_type": "speech2text"

  602.                 },

  603.                 {

  604.                     "llm_name": "azure-gpt-4",

  605.                     "tags": "LLM,CHAT,8K",

  606.                     "max_tokens": 8191,

  607.                     "model_type": "chat"

  608.                 },

  609.                 {

  610.                     "llm_name": "azure-gpt-4-turbo",

  611.                     "tags": "LLM,CHAT,8K",

  612.                     "max_tokens": 8191,

  613.                     "model_type": "chat"

  614.                 },

  615.                 {

  616.                     "llm_name": "azure-gpt-4-32k",

  617.                     "tags": "LLM,CHAT,32K",

  618.                     "max_tokens": 32768,

  619.                     "model_type": "chat"

  620.                 },

  621.                 {

  622.                     "llm_name": "azure-gpt-4-vision-preview",

  623.                     "tags": "LLM,CHAT,IMAGE2TEXT",

  624.                     "max_tokens": 765,

  625.                     "model_type": "image2text"

  626.                 }

  627.             ]

  628.         },

  629.         {

  630.             "name": "Bedrock",

  631.             "logo": "",

  632.             "tags": "LLM,TEXT EMBEDDING",

  633.             "status": "1",

  634.             "llm": [

  635.                 {

  636.                     "llm_name": "ai21.j2-ultra-v1",

  637.                     "tags": "LLM,CHAT,8k",

  638.                     "max_tokens": 8191,

  639.                     "model_type": "chat"

  640.                 },

  641.                 {

  642.                     "llm_name": "ai21.j2-mid-v1",

  643.                     "tags": "LLM,CHAT,8k",

  644.                     "max_tokens": 8191,

  645.                     "model_type": "chat"

  646.                 },

  647.                 {

  648.                     "llm_name": "cohere.command-text-v14",

  649.                     "tags": "LLM,CHAT,4k",

  650.                     "max_tokens": 4096,

  651.                     "model_type": "chat"

  652.                 },

  653.                 {

  654.                     "llm_name": "cohere.command-light-text-v14",

  655.                     "tags": "LLM,CHAT,4k",

  656.                     "max_tokens": 4096,

  657.                     "model_type": "chat"

  658.                 },

  659.                 {

  660.                     "llm_name": "cohere.command-r-v1:0",

  661.                     "tags": "LLM,CHAT,128k",

  662.                     "max_tokens": 131072,

  663.                     "model_type": "chat"

  664.                 },

  665.                 {

  666.                     "llm_name": "cohere.command-r-plus-v1:0",

  667.                     "tags": "LLM,CHAT,128k",

  668.                     "max_tokens": 128000,

  669.                     "model_type": "chat"

  670.                 },

  671.                 {

  672.                     "llm_name": "anthropic.claude-v2",

  673.                     "tags": "LLM,CHAT,100k",

  674.                     "max_tokens": 102400,

  675.                     "model_type": "chat"

  676.                 },

  677.                 {

  678.                     "llm_name": "anthropic.claude-v2:1",

  679.                     "tags": "LLM,CHAT,200k",

  680.                     "max_tokens": 204800,

  681.                     "model_type": "chat"

  682.                 },

  683.                 {

  684.                     "llm_name": "anthropic.claude-3-sonnet-20240229-v1:0",

  685.                     "tags": "LLM,CHAT,200k",

  686.                     "max_tokens": 204800,

  687.                     "model_type": "chat"

  688.                 },

  689.                 {

  690.                     "llm_name": "anthropic.claude-3-5-sonnet-20240620-v1:0",

  691.                     "tags": "LLM,CHAT,200k",

  692.                     "max_tokens": 204800,

  693.                     "model_type": "chat"

  694.                 },

  695.                 {

  696.                     "llm_name": "anthropic.claude-3-haiku-20240307-v1:0",

  697.                     "tags": "LLM,CHAT,200k",

  698.                     "max_tokens": 204800,

  699.                     "model_type": "chat"

  700.                 },

  701.                 {

  702.                     "llm_name": "anthropic.claude-3-opus-20240229-v1:0",

  703.                     "tags": "LLM,CHAT,200k",

  704.                     "max_tokens": 204800,

  705.                     "model_type": "chat"

  706.                 },

  707.                 {

  708.                     "llm_name": "anthropic.claude-instant-v1",

  709.                     "tags": "LLM,CHAT,100k",

  710.                     "max_tokens": 102400,

  711.                     "model_type": "chat"

  712.                 },

  713.                 {

  714.                     "llm_name": "amazon.titan-text-express-v1",

  715.                     "tags": "LLM,CHAT,8k",

  716.                     "max_tokens": 8192,

  717.                     "model_type": "chat"

  718.                 },

  719.                 {

  720.                     "llm_name": "amazon.titan-text-premier-v1:0",

  721.                     "tags": "LLM,CHAT,32k",

  722.                     "max_tokens": 32768,

  723.                     "model_type": "chat"

  724.                 },

  725.                 {

  726.                     "llm_name": "amazon.titan-text-lite-v1",

  727.                     "tags": "LLM,CHAT,4k",

  728.                     "max_tokens": 4096,

  729.                     "model_type": "chat"

  730.                 },

  731.                 {

  732.                     "llm_name": "meta.llama2-13b-chat-v1",

  733.                     "tags": "LLM,CHAT,4k",

  734.                     "max_tokens": 4096,

  735.                     "model_type": "chat"

  736.                 },

  737.                 {

  738.                     "llm_name": "meta.llama2-70b-chat-v1",

  739.                     "tags": "LLM,CHAT,4k",

  740.                     "max_tokens": 4096,

  741.                     "model_type": "chat"

  742.                 },

  743.                 {

  744.                     "llm_name": "meta.llama3-8b-instruct-v1:0",

  745.                     "tags": "LLM,CHAT,8k",

  746.                     "max_tokens": 8192,

  747.                     "model_type": "chat"

  748.                 },

  749.                 {

  750.                     "llm_name": "meta.llama3-70b-instruct-v1:0",

  751.                     "tags": "LLM,CHAT,8k",

  752.                     "max_tokens": 8192,

  753.                     "model_type": "chat"

  754.                 },

  755.                 {

  756.                     "llm_name": "mistral.mistral-7b-instruct-v0:2",

  757.                     "tags": "LLM,CHAT,8k",

  758.                     "max_tokens": 8192,

  759.                     "model_type": "chat"

  760.                 },

  761.                 {

  762.                     "llm_name": "mistral.mixtral-8x7b-instruct-v0:1",

  763.                     "tags": "LLM,CHAT,4k",

  764.                     "max_tokens": 4096,

  765.                     "model_type": "chat"

  766.                 },

  767.                 {

  768.                     "llm_name": "mistral.mistral-large-2402-v1:0",

  769.                     "tags": "LLM,CHAT,8k",

  770.                     "max_tokens": 8192,

  771.                     "model_type": "chat"

  772.                 },

  773.                 {

  774.                     "llm_name": "mistral.mistral-small-2402-v1:0",

  775.                     "tags": "LLM,CHAT,8k",

  776.                     "max_tokens": 8192,

  777.                     "model_type": "chat"

  778.                 },

  779.                 {

  780.                     "llm_name": "amazon.titan-embed-text-v2:0",

  781.                     "tags": "TEXT EMBEDDING",

  782.                     "max_tokens": 8192,

  783.                     "model_type": "embedding"

  784.                 },

  785.                 {

  786.                     "llm_name": "cohere.embed-english-v3",

  787.                     "tags": "TEXT EMBEDDING",

  788.                     "max_tokens": 2048,

  789.                     "model_type": "embedding"

  790.                 },

  791.                 {

  792.                     "llm_name": "cohere.embed-multilingual-v3",

  793.                     "tags": "TEXT EMBEDDING",

  794.                     "max_tokens": 2048,

  795.                     "model_type": "embedding"

  796.                 }

  797.             ]

  798.         },

  799.         {

  800.             "name": "Gemini",

  801.             "logo": "",

  802.             "tags": "LLM,TEXT EMBEDDING,IMAGE2TEXT",

  803.             "status": "1",

  804.             "llm": [

  805.                 {

  806.                     "llm_name": "gemini-1.5-pro-latest",

  807.                     "tags": "LLM,CHAT,1024K",

  808.                     "max_tokens": 1048576,

  809.                     "model_type": "chat"

  810.                 },

  811.                 {

  812.                     "llm_name": "gemini-1.5-flash-latest",

  813.                     "tags": "LLM,CHAT,1024K",

  814.                     "max_tokens": 1048576,

  815.                     "model_type": "chat"

  816.                 },

  817.                 {

  818.                     "llm_name": "gemini-1.0-pro",

  819.                     "tags": "LLM,CHAT,30K",

  820.                     "max_tokens": 30720,

  821.                     "model_type": "chat"

  822.                 },

  823.                 {

  824.                     "llm_name": "gemini-1.0-pro-vision-latest",

  825.                     "tags": "LLM,IMAGE2TEXT,12K",

  826.                     "max_tokens": 12288,

  827.                     "model_type": "image2text"

  828.                 },

  829.                 {

  830.                     "llm_name": "text-embedding-004",

  831.                     "tags": "TEXT EMBEDDING",

  832.                     "max_tokens": 2048,

  833.                     "model_type": "embedding"

  834.                 }

  835.             ]

  836.         },

  837.         {

  838.             "name": "Groq",

  839.             "logo": "",

  840.             "tags": "LLM",

  841.             "status": "1",

  842.             "llm": [

  843.                 {

  844.                     "llm_name": "gemma-7b-it",

  845.                     "tags": "LLM,CHAT,15k",

  846.                     "max_tokens": 8192,

  847.                     "model_type": "chat"

  848.                 },

  849.                 {

  850.                     "llm_name": "gemma2-9b-it",

  851.                     "tags": "LLM,CHAT,15k",

  852.                     "max_tokens": 8192,

  853.                     "model_type": "chat"

  854.                 },

  855.                 {

  856.                     "llm_name": "llama3-70b-8192",

  857.                     "tags": "LLM,CHAT,6k",

  858.                     "max_tokens": 8192,

  859.                     "model_type": "chat"

  860.                 },

  861.                 {

  862.                     "llm_name": "llama3-8b-8192",

  863.                     "tags": "LLM,CHAT,30k",

  864.                     "max_tokens": 8192,

  865.                     "model_type": "chat"

  866.                 },

  867.                 {

  868.                     "llm_name": "mixtral-8x7b-32768",

  869.                     "tags": "LLM,CHAT,5k",

  870.                     "max_tokens": 32768,

  871.                     "model_type": "chat"

  872.                 }

  873.             ]

  874.         },

  875.         {

  876.             "name": "OpenRouter",

  877.             "logo": "",

  878.             "tags": "LLM,IMAGE2TEXT",

  879.             "status": "1",

  880.             "llm": [

  881.                 {

  882.                     "llm_name": "nousresearch/hermes-2-theta-llama-3-8b",

  883.                     "tags": "LLM CHAT 16K",

  884.                     "max_tokens": 16384,

  885.                     "model_type": "chat"

  886.                 },

  887.                 {

  888.                     "llm_name": "alpindale/magnum-72b",

  889.                     "tags": "LLM CHAT 16K",

  890.                     "max_tokens": 16384,

  891.                     "model_type": "chat"

  892.                 },

  893.                 {

  894.                     "llm_name": "google/gemma-2-9b-it",

  895.                     "tags": "LLM CHAT 8K",

  896.                     "max_tokens": 8192,

  897.                     "model_type": "chat"

  898.                 },

  899.                 {

  900.                     "llm_name": "google/gemma-2-9b-it:free",

  901.                     "tags": "LLM CHAT 8K",

  902.                     "max_tokens": 8192,

  903.                     "model_type": "chat"

  904.                 },

  905.                 {

  906.                     "llm_name": "sao10k/l3-stheno-8b",

  907.                     "tags": "LLM CHAT 32K",

  908.                     "max_tokens": 32000,

  909.                     "model_type": "chat"

  910.                 },

  911.                 {

  912.                     "llm_name": "openrouter/flavor-of-the-week",

  913.                     "tags": "LLM CHAT 32K",

  914.                     "max_tokens": 32000,

  915.                     "model_type": "chat"

  916.                 },

  917.                 {

  918.                     "llm_name": "ai21/jamba-instruct",

  919.                     "tags": "LLM CHAT 250K",

  920.                     "max_tokens": 256000,

  921.                     "model_type": "chat"

  922.                 },

  923.                 {

  924.                     "llm_name": "nvidia/nemotron-4-340b-instruct",

  925.                     "tags": "LLM CHAT 4K",

  926.                     "max_tokens": 4096,

  927.                     "model_type": "chat"

  928.                 },

  929.                 {

  930.                     "llm_name": "anthropic/claude-3.5-sonnet",

  931.                     "tags": "LLM IMAGE2TEXT 195K",

  932.                     "max_tokens": 200000,

  933.                     "model_type": "image2text"

  934.                 },

  935.                 {

  936.                     "llm_name": "anthropic/claude-3.5-sonnet:beta",

  937.                     "tags": "LLM IMAGE2TEXT 195K",

  938.                     "max_tokens": 200000,

  939.                     "model_type": "image2text"

  940.                 },

  941.                 {

  942.                     "llm_name": "sao10k/l3-euryale-70b",

  943.                     "tags": "LLM CHAT 8K",

  944.                     "max_tokens": 8192,

  945.                     "model_type": "chat"

  946.                 },

  947.                 {

  948.                     "llm_name": "microsoft/phi-3-medium-4k-instruct",

  949.                     "tags": "LLM CHAT 4K",

  950.                     "max_tokens": 4000,

  951.                     "model_type": "chat"

  952.                 },

  953.                 {

  954.                     "llm_name": "cognitivecomputations/dolphin-mixtral-8x22b",

  955.                     "tags": "LLM CHAT 64K",

  956.                     "max_tokens": 65536,

  957.                     "model_type": "chat"

  958.                 },

  959.                 {

  960.                     "llm_name": "qwen/qwen-2-72b-instruct",

  961.                     "tags": "LLM CHAT 32K",

  962.                     "max_tokens": 32768,

  963.                     "model_type": "chat"

  964.                 },

  965.                 {

  966.                     "llm_name": "openchat/openchat-8b",

  967.                     "tags": "LLM CHAT 8K",

  968.                     "max_tokens": 8192,

  969.                     "model_type": "chat"

  970.                 },

  971.                 {

  972.                     "llm_name": "mistralai/mistral-7b-instruct",

  973.                     "tags": "LLM CHAT 32K",

  974.                     "max_tokens": 32768,

  975.                     "model_type": "chat"

  976.                 },

  977.                 {

  978.                     "llm_name": "mistralai/mistral-7b-instruct-v0.3",

  979.                     "tags": "LLM CHAT 32K",

  980.                     "max_tokens": 32768,

  981.                     "model_type": "chat"

  982.                 },

  983.                 {

  984.                     "llm_name": "nousresearch/hermes-2-pro-llama-3-8b",

  985.                     "tags": "LLM CHAT 8K",

  986.                     "max_tokens": 8192,

  987.                     "model_type": "chat"

  988.                 },

  989.                 {

  990.                     "llm_name": "microsoft/phi-3-mini-128k-instruct",

  991.                     "tags": "LLM CHAT 125K",

  992.                     "max_tokens": 128000,

  993.                     "model_type": "chat"

  994.                 },

  995.                 {

  996.                     "llm_name": "microsoft/phi-3-mini-128k-instruct:free",

  997.                     "tags": "LLM CHAT 125K",

  998.                     "max_tokens": 128000,

  999.                     "model_type": "chat"

  1000.                 },

  1001.                 {

  1002.                     "llm_name": "microsoft/phi-3-medium-128k-instruct",

  1003.                     "tags": "LLM CHAT 125K",

  1004.                     "max_tokens": 128000,

  1005.                     "model_type": "chat"

  1006.                 },

  1007.                 {

  1008.                     "llm_name": "microsoft/phi-3-medium-128k-instruct:free",

  1009.                     "tags": "LLM CHAT 125K",

  1010.                     "max_tokens": 128000,

  1011.                     "model_type": "chat"

  1012.                 },

  1013.                 {

  1014.                     "llm_name": "neversleep/llama-3-lumimaid-70b",

  1015.                     "tags": "LLM CHAT 8K",

  1016.                     "max_tokens": 8192,

  1017.                     "model_type": "chat"

  1018.                 },

  1019.                 {

  1020.                     "llm_name": "google/gemini-flash-1.5",

  1021.                     "tags": "LLM IMAGE2TEXT 2734K",

  1022.                     "max_tokens": 2800000,

  1023.                     "model_type": "image2text"

  1024.                 },

  1025.                 {

  1026.                     "llm_name": "perplexity/llama-3-sonar-small-32k-chat",

  1027.                     "tags": "LLM CHAT 32K",

  1028.                     "max_tokens": 32768,

  1029.                     "model_type": "chat"

  1030.                 },

  1031.                 {

  1032.                     "llm_name": "perplexity/llama-3-sonar-small-32k-online",

  1033.                     "tags": "LLM CHAT 28K",

  1034.                     "max_tokens": 28000,

  1035.                     "model_type": "chat"

  1036.                 },

  1037.                 {

  1038.                     "llm_name": "perplexity/llama-3-sonar-large-32k-chat",

  1039.                     "tags": "LLM CHAT 32K",

  1040.                     "max_tokens": 32768,

  1041.                     "model_type": "chat"

  1042.                 },

  1043.                 {

  1044.                     "llm_name": "perplexity/llama-3-sonar-large-32k-online",

  1045.                     "tags": "LLM CHAT 28K",

  1046.                     "max_tokens": 28000,

  1047.                     "model_type": "chat"

  1048.                 },

  1049.                 {

  1050.                     "llm_name": "deepseek/deepseek-chat",

  1051.                     "tags": "LLM CHAT 125K",

  1052.                     "max_tokens": 128000,

  1053.                     "model_type": "chat"

  1054.                 },

  1055.                 {

  1056.                     "llm_name": "deepseek/deepseek-coder",

  1057.                     "tags": "LLM CHAT 125K",

  1058.                     "max_tokens": 128000,

  1059.                     "model_type": "chat"

  1060.                 },

  1061.                 {

  1062.                     "llm_name": "openai/gpt-4o",

  1063.                     "tags": "LLM IMAGE2TEXT 125K",

  1064.                     "max_tokens": 128000,

  1065.                     "model_type": "image2text"

  1066.                 },

  1067.                 {

  1068.                     "llm_name": "openai/gpt-4o-2024-05-13",

  1069.                     "tags": "LLM IMAGE2TEXT 125K",

  1070.                     "max_tokens": 128000,

  1071.                     "model_type": "image2text"

  1072.                 },

  1073.                 {

  1074.                     "llm_name": "meta-llama/llama-3-8b",

  1075.                     "tags": "LLM CHAT 8K",

  1076.                     "max_tokens": 8192,

  1077.                     "model_type": "chat"

  1078.                 },

  1079.                 {

  1080.                     "llm_name": "meta-llama/llama-3-70b",

  1081.                     "tags": "LLM CHAT 8K",

  1082.                     "max_tokens": 8192,

  1083.                     "model_type": "chat"

  1084.                 },

  1085.                 {

  1086.                     "llm_name": "meta-llama/llama-guard-2-8b",

  1087.                     "tags": "LLM CHAT 8K",

  1088.                     "max_tokens": 8192,

  1089.                     "model_type": "chat"

  1090.                 },

  1091.                 {

  1092.                     "llm_name": "liuhaotian/llava-yi-34b",

  1093.                     "tags": "LLM IMAGE2TEXT 4K",

  1094.                     "max_tokens": 4096,

  1095.                     "model_type": "image2text"

  1096.                 },

  1097.                 {

  1098.                     "llm_name": "allenai/olmo-7b-instruct",

  1099.                     "tags": "LLM CHAT 2K",

  1100.                     "max_tokens": 2048,

  1101.                     "model_type": "chat"

  1102.                 },

  1103.                 {

  1104.                     "llm_name": "qwen/qwen-110b-chat",

  1105.                     "tags": "LLM CHAT 32K",

  1106.                     "max_tokens": 32768,

  1107.                     "model_type": "chat"

  1108.                 },

  1109.                 {

  1110.                     "llm_name": "qwen/qwen-72b-chat",

  1111.                     "tags": "LLM CHAT 32K",

  1112.                     "max_tokens": 32768,

  1113.                     "model_type": "chat"

  1114.                 },

  1115.                 {

  1116.                     "llm_name": "qwen/qwen-32b-chat",

  1117.                     "tags": "LLM CHAT 32K",

  1118.                     "max_tokens": 32768,

  1119.                     "model_type": "chat"

  1120.                 },

  1121.                 {

  1122.                     "llm_name": "qwen/qwen-14b-chat",

  1123.                     "tags": "LLM CHAT 32K",

  1124.                     "max_tokens": 32768,

  1125.                     "model_type": "chat"

  1126.                 },

  1127.                 {

  1128.                     "llm_name": "qwen/qwen-7b-chat",

  1129.                     "tags": "LLM CHAT 32K",

  1130.                     "max_tokens": 32768,

  1131.                     "model_type": "chat"

  1132.                 },

  1133.                 {

  1134.                     "llm_name": "qwen/qwen-4b-chat",

  1135.                     "tags": "LLM CHAT 32K",

  1136.                     "max_tokens": 32768,

  1137.                     "model_type": "chat"

  1138.                 },

  1139.                 {

  1140.                     "llm_name": "meta-llama/llama-3-8b-instruct:free",

  1141.                     "tags": "LLM CHAT 8K",

  1142.                     "max_tokens": 8192,

  1143.                     "model_type": "chat"

  1144.                 },

  1145.                 {

  1146.                     "llm_name": "neversleep/llama-3-lumimaid-8b",

  1147.                     "tags": "LLM CHAT 24K",

  1148.                     "max_tokens": 24576,

  1149.                     "model_type": "chat"

  1150.                 },

  1151.                 {

  1152.                     "llm_name": "neversleep/llama-3-lumimaid-8b:extended",

  1153.                     "tags": "LLM CHAT 24K",

  1154.                     "max_tokens": 24576,

  1155.                     "model_type": "chat"

  1156.                 },

  1157.                 {

  1158.                     "llm_name": "snowflake/snowflake-arctic-instruct",

  1159.                     "tags": "LLM CHAT 4K",

  1160.                     "max_tokens": 4096,

  1161.                     "model_type": "chat"

  1162.                 },

  1163.                 {

  1164.                     "llm_name": "fireworks/firellava-13b",

  1165.                     "tags": "LLM IMAGE2TEXT 4K",

  1166.                     "max_tokens": 4096,

  1167.                     "model_type": "image2text"

  1168.                 },

  1169.                 {

  1170.                     "llm_name": "lynn/soliloquy-l3",

  1171.                     "tags": "LLM CHAT 24K",

  1172.                     "max_tokens": 24576,

  1173.                     "model_type": "chat"

  1174.                 },

  1175.                 {

  1176.                     "llm_name": "sao10k/fimbulvetr-11b-v2",

  1177.                     "tags": "LLM CHAT 8K",

  1178.                     "max_tokens": 8192,

  1179.                     "model_type": "chat"

  1180.                 },

  1181.                 {

  1182.                     "llm_name": "meta-llama/llama-3-8b-instruct:extended",

  1183.                     "tags": "LLM CHAT 16K",

  1184.                     "max_tokens": 16384,

  1185.                     "model_type": "chat"

  1186.                 },

  1187.                 {

  1188.                     "llm_name": "meta-llama/llama-3-8b-instruct:nitro",

  1189.                     "tags": "LLM CHAT 8K",

  1190.                     "max_tokens": 8192,

  1191.                     "model_type": "chat"

  1192.                 },

  1193.                 {

  1194.                     "llm_name": "meta-llama/llama-3-70b-instruct:nitro",

  1195.                     "tags": "LLM CHAT 8K",

  1196.                     "max_tokens": 8192,

  1197.                     "model_type": "chat"

  1198.                 },

  1199.                 {

  1200.                     "llm_name": "meta-llama/llama-3-8b-instruct",

  1201.                     "tags": "LLM CHAT 8K",

  1202.                     "max_tokens": 8192,

  1203.                     "model_type": "chat"

  1204.                 },

  1205.                 {

  1206.                     "llm_name": "meta-llama/llama-3-70b-instruct",

  1207.                     "tags": "LLM CHAT 8K",

  1208.                     "max_tokens": 8192,

  1209.                     "model_type": "chat"

  1210.                 },

  1211.                 {

  1212.                     "llm_name": "mistralai/mixtral-8x22b-instruct",

  1213.                     "tags": "LLM CHAT 64K",

  1214.                     "max_tokens": 65536,

  1215.                     "model_type": "chat"

  1216.                 },

  1217.                 {

  1218.                     "llm_name": "microsoft/wizardlm-2-8x22b",

  1219.                     "tags": "LLM CHAT 64K",

  1220.                     "max_tokens": 65536,

  1221.                     "model_type": "chat"

  1222.                 },

  1223.                 {

  1224.                     "llm_name": "microsoft/wizardlm-2-7b",

  1225.                     "tags": "LLM CHAT 32K",

  1226.                     "max_tokens": 32000,

  1227.                     "model_type": "chat"

  1228.                 },

  1229.                 {

  1230.                     "llm_name": "undi95/toppy-m-7b:nitro",

  1231.                     "tags": "LLM CHAT 4K",

  1232.                     "max_tokens": 4096,

  1233.                     "model_type": "chat"

  1234.                 },

  1235.                 {

  1236.                     "llm_name": "mistralai/mixtral-8x22b",

  1237.                     "tags": "LLM CHAT 64K",

  1238.                     "max_tokens": 65536,

  1239.                     "model_type": "chat"

  1240.                 },

  1241.                 {

  1242.                     "llm_name": "openai/gpt-4-turbo",

  1243.                     "tags": "LLM IMAGE2TEXT 125K",

  1244.                     "max_tokens": 128000,

  1245.                     "model_type": "image2text"

  1246.                 },

  1247.                 {

  1248.                     "llm_name": "google/gemini-pro-1.5",

  1249.                     "tags": "LLM IMAGE2TEXT 2734K",

  1250.                     "max_tokens": 2800000,

  1251.                     "model_type": "image2text"

  1252.                 },

  1253.                 {

  1254.                     "llm_name": "cohere/command-r-plus",

  1255.                     "tags": "LLM CHAT 125K",

  1256.                     "max_tokens": 128000,

  1257.                     "model_type": "chat"

  1258.                 },

  1259.                 {

  1260.                     "llm_name": "databricks/dbrx-instruct",

  1261.                     "tags": "LLM CHAT 32K",

  1262.                     "max_tokens": 32768,

  1263.                     "model_type": "chat"

  1264.                 },

  1265.                 {

  1266.                     "llm_name": "sophosympatheia/midnight-rose-70b",

  1267.                     "tags": "LLM CHAT 4K",

  1268.                     "max_tokens": 4096,

  1269.                     "model_type": "chat"

  1270.                 },

  1271.                 {

  1272.                     "llm_name": "cohere/command",

  1273.                     "tags": "LLM CHAT 4K",

  1274.                     "max_tokens": 4096,

  1275.                     "model_type": "chat"

  1276.                 },

  1277.                 {

  1278.                     "llm_name": "cohere/command-r",

  1279.                     "tags": "LLM CHAT 125K",

  1280.                     "max_tokens": 128000,

  1281.                     "model_type": "chat"

  1282.                 },

  1283.                 {

  1284.                     "llm_name": "anthropic/claude-3-haiku",

  1285.                     "tags": "LLM IMAGE2TEXT 195K",

  1286.                     "max_tokens": 200000,

  1287.                     "model_type": "image2text"

  1288.                 },

  1289.                 {

  1290.                     "llm_name": "anthropic/claude-3-haiku:beta",

  1291.                     "tags": "LLM IMAGE2TEXT 195K",

  1292.                     "max_tokens": 200000,

  1293.                     "model_type": "image2text"

  1294.                 },

  1295.                 {

  1296.                     "llm_name": "google/gemma-7b-it:nitro",

  1297.                     "tags": "LLM CHAT 8K",

  1298.                     "max_tokens": 8192,

  1299.                     "model_type": "chat"

  1300.                 },

  1301.                 {

  1302.                     "llm_name": "mistralai/mixtral-8x7b-instruct:nitro",

  1303.                     "tags": "LLM CHAT 32K",

  1304.                     "max_tokens": 32768,

  1305.                     "model_type": "chat"

  1306.                 },

  1307.                 {

  1308.                     "llm_name": "mistralai/mistral-7b-instruct:nitro",

  1309.                     "tags": "LLM CHAT 32K",

  1310.                     "max_tokens": 32768,

  1311.                     "model_type": "chat"

  1312.                 },

  1313.                 {

  1314.                     "llm_name": "meta-llama/llama-2-70b-chat:nitro",

  1315.                     "tags": "LLM CHAT 4K",

  1316.                     "max_tokens": 4096,

  1317.                     "model_type": "chat"

  1318.                 },

  1319.                 {

  1320.                     "llm_name": "gryphe/mythomax-l2-13b:nitro",

  1321.                     "tags": "LLM CHAT 4K",

  1322.                     "max_tokens": 4096,

  1323.                     "model_type": "chat"

  1324.                 },

  1325.                 {

  1326.                     "llm_name": "anthropic/claude-3-opus",

  1327.                     "tags": "LLM IMAGE2TEXT 195K",

  1328.                     "max_tokens": 200000,

  1329.                     "model_type": "image2text"

  1330.                 },

  1331.                 {

  1332.                     "llm_name": "anthropic/claude-3-sonnet",

  1333.                     "tags": "LLM IMAGE2TEXT 195K",

  1334.                     "max_tokens": 200000,

  1335.                     "model_type": "image2text"

  1336.                 },

  1337.                 {

  1338.                     "llm_name": "anthropic/claude-3-opus:beta",

  1339.                     "tags": "LLM IMAGE2TEXT 195K",

  1340.                     "max_tokens": 200000,

  1341.                     "model_type": "image2text"

  1342.                 },

  1343.                 {

  1344.                     "llm_name": "anthropic/claude-3-sonnet:beta",

  1345.                     "tags": "LLM IMAGE2TEXT 195K",

  1346.                     "max_tokens": 200000,

  1347.                     "model_type": "image2text"

  1348.                 },

  1349.                 {

  1350.                     "llm_name": "mistralai/mistral-large",

  1351.                     "tags": "LLM CHAT 32K",

  1352.                     "max_tokens": 32000,

  1353.                     "model_type": "chat"

  1354.                 },

  1355.                 {

  1356.                     "llm_name": "google/gemma-7b-it",

  1357.                     "tags": "LLM CHAT 8K",

  1358.                     "max_tokens": 8192,

  1359.                     "model_type": "chat"

  1360.                 },

  1361.                 {

  1362.                     "llm_name": "google/gemma-7b-it:free",

  1363.                     "tags": "LLM CHAT 8K",

  1364.                     "max_tokens": 8192,

  1365.                     "model_type": "chat"

  1366.                 },

  1367.                 {

  1368.                     "llm_name": "nousresearch/nous-hermes-2-mistral-7b-dpo",

  1369.                     "tags": "LLM CHAT 8K",

  1370.                     "max_tokens": 8192,

  1371.                     "model_type": "chat"

  1372.                 },

  1373.                 {

  1374.                     "llm_name": "meta-llama/codellama-70b-instruct",

  1375.                     "tags": "LLM CHAT 2K",

  1376.                     "max_tokens": 2048,

  1377.                     "model_type": "chat"

  1378.                 },

  1379.                 {

  1380.                     "llm_name": "recursal/eagle-7b",

  1381.                     "tags": "LLM CHAT 9K",

  1382.                     "max_tokens": 10000,

  1383.                     "model_type": "chat"

  1384.                 },

  1385.                 {

  1386.                     "llm_name": "openai/gpt-3.5-turbo-0613",

  1387.                     "tags": "LLM CHAT 4K",

  1388.                     "max_tokens": 4095,

  1389.                     "model_type": "chat"

  1390.                 },

  1391.                 {

  1392.                     "llm_name": "openai/gpt-4-turbo-preview",

  1393.                     "tags": "LLM CHAT 125K",

  1394.                     "max_tokens": 128000,

  1395.                     "model_type": "chat"

  1396.                 },

  1397.                 {

  1398.                     "llm_name": "undi95/remm-slerp-l2-13b:extended",

  1399.                     "tags": "LLM CHAT 6K",

  1400.                     "max_tokens": 6144,

  1401.                     "model_type": "chat"

  1402.                 },

  1403.                 {

  1404.                     "llm_name": "nousresearch/nous-hermes-2-mixtral-8x7b-dpo",

  1405.                     "tags": "LLM CHAT 32K",

  1406.                     "max_tokens": 32768,

  1407.                     "model_type": "chat"

  1408.                 },

  1409.                 {

  1410.                     "llm_name": "nousresearch/nous-hermes-2-mixtral-8x7b-sft",

  1411.                     "tags": "LLM CHAT 32K",

  1412.                     "max_tokens": 32768,

  1413.                     "model_type": "chat"

  1414.                 },

  1415.                 {

  1416.                     "llm_name": "mistralai/mistral-tiny",

  1417.                     "tags": "LLM CHAT 32K",

  1418.                     "max_tokens": 32000,

  1419.                     "model_type": "chat"

  1420.                 },

  1421.                 {

  1422.                     "llm_name": "mistralai/mistral-small",

  1423.                     "tags": "LLM CHAT 32K",

  1424.                     "max_tokens": 32000,

  1425.                     "model_type": "chat"

  1426.                 },

  1427.                 {

  1428.                     "llm_name": "mistralai/mistral-medium",

  1429.                     "tags": "LLM CHAT 32K",

  1430.                     "max_tokens": 32000,

  1431.                     "model_type": "chat"

  1432.                 },

  1433.                 {

  1434.                     "llm_name": "austism/chronos-hermes-13b",

  1435.                     "tags": "LLM CHAT 4K",

  1436.                     "max_tokens": 4096,

  1437.                     "model_type": "chat"

  1438.                 },

  1439.                 {

  1440.                     "llm_name": "neversleep/noromaid-mixtral-8x7b-instruct",

  1441.                     "tags": "LLM CHAT 8K",

  1442.                     "max_tokens": 8000,

  1443.                     "model_type": "chat"

  1444.                 },

  1445.                 {

  1446.                     "llm_name": "nousresearch/nous-hermes-yi-34b",

  1447.                     "tags": "LLM CHAT 4K",

  1448.                     "max_tokens": 4096,

  1449.                     "model_type": "chat"

  1450.                 },

  1451.                 {

  1452.                     "llm_name": "mistralai/mistral-7b-instruct-v0.2",

  1453.                     "tags": "LLM CHAT 32K",

  1454.                     "max_tokens": 32768,

  1455.                     "model_type": "chat"

  1456.                 },

  1457.                 {

  1458.                     "llm_name": "cognitivecomputations/dolphin-mixtral-8x7b",

  1459.                     "tags": "LLM CHAT 32K",

  1460.                     "max_tokens": 32768,

  1461.                     "model_type": "chat"

  1462.                 },

  1463.                 {

  1464.                     "llm_name": "google/gemini-pro",

  1465.                     "tags": "LLM CHAT 89K",

  1466.                     "max_tokens": 91728,

  1467.                     "model_type": "chat"

  1468.                 },

  1469.                 {

  1470.                     "llm_name": "google/gemini-pro-vision",

  1471.                     "tags": "LLM IMAGE2TEXT 44K",

  1472.                     "max_tokens": 45875,

  1473.                     "model_type": "image2text"

  1474.                 },

  1475.                 {

  1476.                     "llm_name": "mistralai/mixtral-8x7b",

  1477.                     "tags": "LLM CHAT 32K",

  1478.                     "max_tokens": 32768,

  1479.                     "model_type": "chat"

  1480.                 },

  1481.                 {

  1482.                     "llm_name": "mistralai/mixtral-8x7b-instruct",

  1483.                     "tags": "LLM CHAT 32K",

  1484.                     "max_tokens": 32768,

  1485.                     "model_type": "chat"

  1486.                 },

  1487.                 {

  1488.                     "llm_name": "rwkv/rwkv-5-world-3b",

  1489.                     "tags": "LLM CHAT 9K",

  1490.                     "max_tokens": 10000,

  1491.                     "model_type": "chat"

  1492.                 },

  1493.                 {

  1494.                     "llm_name": "recursal/rwkv-5-3b-ai-town",

  1495.                     "tags": "LLM CHAT 9K",

  1496.                     "max_tokens": 10000,

  1497.                     "model_type": "chat"

  1498.                 },

  1499.                 {

  1500.                     "llm_name": "togethercomputer/stripedhyena-nous-7b",

  1501.                     "tags": "LLM CHAT 32K",

  1502.                     "max_tokens": 32768,

  1503.                     "model_type": "chat"

  1504.                 },

  1505.                 {

  1506.                     "llm_name": "togethercomputer/stripedhyena-hessian-7b",

  1507.                     "tags": "LLM CHAT 32K",

  1508.                     "max_tokens": 32768,

  1509.                     "model_type": "chat"

  1510.                 },

  1511.                 {

  1512.                     "llm_name": "koboldai/psyfighter-13b-2",

  1513.                     "tags": "LLM CHAT 4K",

  1514.                     "max_tokens": 4096,

  1515.                     "model_type": "chat"

  1516.                 },

  1517.                 {

  1518.                     "llm_name": "gryphe/mythomist-7b",

  1519.                     "tags": "LLM CHAT 32K",

  1520.                     "max_tokens": 32768,

  1521.                     "model_type": "chat"

  1522.                 },

  1523.                 {

  1524.                     "llm_name": "openrouter/cinematika-7b",

  1525.                     "tags": "LLM CHAT 8K",

  1526.                     "max_tokens": 8000,

  1527.                     "model_type": "chat"

  1528.                 },

  1529.                 {

  1530.                     "llm_name": "nousresearch/nous-capybara-7b",

  1531.                     "tags": "LLM CHAT 8K",

  1532.                     "max_tokens": 8192,

  1533.                     "model_type": "chat"

  1534.                 },

  1535.                 {

  1536.                     "llm_name": "nousresearch/nous-capybara-7b:free",

  1537.                     "tags": "LLM CHAT 8K",

  1538.                     "max_tokens": 8192,

  1539.                     "model_type": "chat"

  1540.                 },

  1541.                 {

  1542.                     "llm_name": "openchat/openchat-7b",

  1543.                     "tags": "LLM CHAT 8K",

  1544.                     "max_tokens": 8192,

  1545.                     "model_type": "chat"

  1546.                 },

  1547.                 {

  1548.                     "llm_name": "openchat/openchat-7b:free",

  1549.                     "tags": "LLM CHAT 8K",

  1550.                     "max_tokens": 8192,

  1551.                     "model_type": "chat"

  1552.                 },

  1553.                 {

  1554.                     "llm_name": "neversleep/noromaid-20b",

  1555.                     "tags": "LLM CHAT 8K",

  1556.                     "max_tokens": 8192,

  1557.                     "model_type": "chat"

  1558.                 },

  1559.                 {

  1560.                     "llm_name": "gryphe/mythomist-7b:free",

  1561.                     "tags": "LLM CHAT 32K",

  1562.                     "max_tokens": 32768,

  1563.                     "model_type": "chat"

  1564.                 },

  1565.                 {

  1566.                     "llm_name": "intel/neural-chat-7b",

  1567.                     "tags": "LLM CHAT 4K",

  1568.                     "max_tokens": 4096,

  1569.                     "model_type": "chat"

  1570.                 },

  1571.                 {

  1572.                     "llm_name": "anthropic/claude-2",

  1573.                     "tags": "LLM CHAT 195K",

  1574.                     "max_tokens": 200000,

  1575.                     "model_type": "chat"

  1576.                 },

  1577.                 {

  1578.                     "llm_name": "anthropic/claude-2.1",

  1579.                     "tags": "LLM CHAT 195K",

  1580.                     "max_tokens": 200000,

  1581.                     "model_type": "chat"

  1582.                 },

  1583.                 {

  1584.                     "llm_name": "anthropic/claude-instant-1.1",

  1585.                     "tags": "LLM CHAT 98K",

  1586.                     "max_tokens": 100000,

  1587.                     "model_type": "chat"

  1588.                 },

  1589.                 {

  1590.                     "llm_name": "anthropic/claude-2:beta",

  1591.                     "tags": "LLM CHAT 195K",

  1592.                     "max_tokens": 200000,

  1593.                     "model_type": "chat"

  1594.                 },

  1595.                 {

  1596.                     "llm_name": "anthropic/claude-2.1:beta",

  1597.                     "tags": "LLM CHAT 195K",

  1598.                     "max_tokens": 200000,

  1599.                     "model_type": "chat"

  1600.                 },

  1601.                 {

  1602.                     "llm_name": "teknium/openhermes-2.5-mistral-7b",

  1603.                     "tags": "LLM CHAT 4K",

  1604.                     "max_tokens": 4096,

  1605.                     "model_type": "chat"

  1606.                 },

  1607.                 {

  1608.                     "llm_name": "nousresearch/nous-capybara-34b",

  1609.                     "tags": "LLM CHAT 195K",

  1610.                     "max_tokens": 200000,

  1611.                     "model_type": "chat"

  1612.                 },

  1613.                 {

  1614.                     "llm_name": "openai/gpt-4-vision-preview",

  1615.                     "tags": "LLM IMAGE2TEXT 125K",

  1616.                     "max_tokens": 128000,

  1617.                     "model_type": "image2text"

  1618.                 },

  1619.                 {

  1620.                     "llm_name": "lizpreciatior/lzlv-70b-fp16-hf",

  1621.                     "tags": "LLM CHAT 4K",

  1622.                     "max_tokens": 4096,

  1623.                     "model_type": "chat"

  1624.                 },

  1625.                 {

  1626.                     "llm_name": "undi95/toppy-m-7b",

  1627.                     "tags": "LLM CHAT 4K",

  1628.                     "max_tokens": 4096,

  1629.                     "model_type": "chat"

  1630.                 },

  1631.                 {

  1632.                     "llm_name": "alpindale/goliath-120b",

  1633.                     "tags": "LLM CHAT 6K",

  1634.                     "max_tokens": 6144,

  1635.                     "model_type": "chat"

  1636.                 },

  1637.                 {

  1638.                     "llm_name": "undi95/toppy-m-7b:free",

  1639.                     "tags": "LLM CHAT 4K",

  1640.                     "max_tokens": 4096,

  1641.                     "model_type": "chat"

  1642.                 },

  1643.                 {

  1644.                     "llm_name": "openrouter/auto",

  1645.                     "tags": "LLM CHAT 195K",

  1646.                     "max_tokens": 200000,

  1647.                     "model_type": "chat"

  1648.                 },

  1649.                 {

  1650.                     "llm_name": "openai/gpt-3.5-turbo-1106",

  1651.                     "tags": "LLM CHAT 16K",

  1652.                     "max_tokens": 16385,

  1653.                     "model_type": "chat"

  1654.                 },

  1655.                 {

  1656.                     "llm_name": "openai/gpt-4-1106-preview",

  1657.                     "tags": "LLM CHAT 125K",

  1658.                     "max_tokens": 128000,

  1659.                     "model_type": "chat"

  1660.                 },

  1661.                 {

  1662.                     "llm_name": "huggingfaceh4/zephyr-7b-beta:free",

  1663.                     "tags": "LLM CHAT 4K",

  1664.                     "max_tokens": 4096,

  1665.                     "model_type": "chat"

  1666.                 },

  1667.                 {

  1668.                     "llm_name": "google/palm-2-chat-bison-32k",

  1669.                     "tags": "LLM CHAT 89K",

  1670.                     "max_tokens": 91750,

  1671.                     "model_type": "chat"

  1672.                 },

  1673.                 {

  1674.                     "llm_name": "google/palm-2-codechat-bison-32k",

  1675.                     "tags": "LLM CHAT 89K",

  1676.                     "max_tokens": 91750,

  1677.                     "model_type": "chat"

  1678.                 },

  1679.                 {

  1680.                     "llm_name": "teknium/openhermes-2-mistral-7b",

  1681.                     "tags": "LLM CHAT 8K",

  1682.                     "max_tokens": 8192,

  1683.                     "model_type": "chat"

  1684.                 },

  1685.                 {

  1686.                     "llm_name": "open-orca/mistral-7b-openorca",

  1687.                     "tags": "LLM CHAT 8K",

  1688.                     "max_tokens": 8192,

  1689.                     "model_type": "chat"

  1690.                 },

  1691.                 {

  1692.                     "llm_name": "gryphe/mythomax-l2-13b:extended",

  1693.                     "tags": "LLM CHAT 8K",

  1694.                     "max_tokens": 8192,

  1695.                     "model_type": "chat"

  1696.                 },

  1697.                 {

  1698.                     "llm_name": "xwin-lm/xwin-lm-70b",

  1699.                     "tags": "LLM CHAT 8K",

  1700.                     "max_tokens": 8192,

  1701.                     "model_type": "chat"

  1702.                 },

  1703.                 {

  1704.                     "llm_name": "openai/gpt-3.5-turbo-instruct",

  1705.                     "tags": "LLM CHAT 4K",

  1706.                     "max_tokens": 4095,

  1707.                     "model_type": "chat"

  1708.                 },

  1709.                 {

  1710.                     "llm_name": "mistralai/mistral-7b-instruct-v0.1",

  1711.                     "tags": "LLM CHAT 4K",

  1712.                     "max_tokens": 4096,

  1713.                     "model_type": "chat"

  1714.                 },

  1715.                 {

  1716.                     "llm_name": "mistralai/mistral-7b-instruct:free",

  1717.                     "tags": "LLM CHAT 32K",

  1718.                     "max_tokens": 32768,

  1719.                     "model_type": "chat"

  1720.                 },

  1721.                 {

  1722.                     "llm_name": "pygmalionai/mythalion-13b",

  1723.                     "tags": "LLM CHAT 8K",

  1724.                     "max_tokens": 8192,

  1725.                     "model_type": "chat"

  1726.                 },

  1727.                 {

  1728.                     "llm_name": "openai/gpt-3.5-turbo-16k",

  1729.                     "tags": "LLM CHAT 16K",

  1730.                     "max_tokens": 16385,

  1731.                     "model_type": "chat"

  1732.                 },

  1733.                 {

  1734.                     "llm_name": "openai/gpt-4-32k",

  1735.                     "tags": "LLM CHAT 32K",

  1736.                     "max_tokens": 32767,

  1737.                     "model_type": "chat"

  1738.                 },

  1739.                 {

  1740.                     "llm_name": "openai/gpt-4-32k-0314",

  1741.                     "tags": "LLM CHAT 32K",

  1742.                     "max_tokens": 32767,

  1743.                     "model_type": "chat"

  1744.                 },

  1745.                 {

  1746.                     "llm_name": "meta-llama/codellama-34b-instruct",

  1747.                     "tags": "LLM CHAT 8K",

  1748.                     "max_tokens": 8192,

  1749.                     "model_type": "chat"

  1750.                 },

  1751.                 {

  1752.                     "llm_name": "phind/phind-codellama-34b",

  1753.                     "tags": "LLM CHAT 4K",

  1754.                     "max_tokens": 4096,

  1755.                     "model_type": "chat"

  1756.                 },

  1757.                 {

  1758.                     "llm_name": "nousresearch/nous-hermes-llama2-13b",

  1759.                     "tags": "LLM CHAT 4K",

  1760.                     "max_tokens": 4096,

  1761.                     "model_type": "chat"

  1762.                 },

  1763.                 {

  1764.                     "llm_name": "mancer/weaver",

  1765.                     "tags": "LLM CHAT 8K",

  1766.                     "max_tokens": 8000,

  1767.                     "model_type": "chat"

  1768.                 },

  1769.                 {

  1770.                     "llm_name": "anthropic/claude-2.0",

  1771.                     "tags": "LLM CHAT 98K",

  1772.                     "max_tokens": 100000,

  1773.                     "model_type": "chat"

  1774.                 },

  1775.                 {

  1776.                     "llm_name": "anthropic/claude-instant-1",

  1777.                     "tags": "LLM CHAT 98K",

  1778.                     "max_tokens": 100000,

  1779.                     "model_type": "chat"

  1780.                 },

  1781.                 {

  1782.                     "llm_name": "anthropic/claude-1",

  1783.                     "tags": "LLM CHAT 98K",

  1784.                     "max_tokens": 100000,

  1785.                     "model_type": "chat"

  1786.                 },

  1787.                 {

  1788.                     "llm_name": "anthropic/claude-1.2",

  1789.                     "tags": "LLM CHAT 98K",

  1790.                     "max_tokens": 100000,

  1791.                     "model_type": "chat"

  1792.                 },

  1793.                 {

  1794.                     "llm_name": "anthropic/claude-instant-1.0",

  1795.                     "tags": "LLM CHAT 98K",

  1796.                     "max_tokens": 100000,

  1797.                     "model_type": "chat"

  1798.                 },

  1799.                 {

  1800.                     "llm_name": "anthropic/claude-2.0:beta",

  1801.                     "tags": "LLM CHAT 98K",

  1802.                     "max_tokens": 100000,

  1803.                     "model_type": "chat"

  1804.                 },

  1805.                 {

  1806.                     "llm_name": "anthropic/claude-instant-1:beta",

  1807.                     "tags": "LLM CHAT 98K",

  1808.                     "max_tokens": 100000,

  1809.                     "model_type": "chat"

  1810.                 },

  1811.                 {

  1812.                     "llm_name": "undi95/remm-slerp-l2-13b",

  1813.                     "tags": "LLM CHAT 4K",

  1814.                     "max_tokens": 4096,

  1815.                     "model_type": "chat"

  1816.                 },

  1817.                 {

  1818.                     "llm_name": "google/palm-2-chat-bison",

  1819.                     "tags": "LLM CHAT 25K",

  1820.                     "max_tokens": 25804,

  1821.                     "model_type": "chat"

  1822.                 },

  1823.                 {

  1824.                     "llm_name": "google/palm-2-codechat-bison",

  1825.                     "tags": "LLM CHAT 19K",

  1826.                     "max_tokens": 20070,

  1827.                     "model_type": "chat"

  1828.                 },

  1829.                 {

  1830.                     "llm_name": "gryphe/mythomax-l2-13b",

  1831.                     "tags": "LLM CHAT 4K",

  1832.                     "max_tokens": 4096,

  1833.                     "model_type": "chat"

  1834.                 },

  1835.                 {

  1836.                     "llm_name": "meta-llama/llama-2-13b-chat",

  1837.                     "tags": "LLM CHAT 4K",

  1838.                     "max_tokens": 4096,

  1839.                     "model_type": "chat"

  1840.                 },

  1841.                 {

  1842.                     "llm_name": "meta-llama/llama-2-70b-chat",

  1843.                     "tags": "LLM CHAT 4K",

  1844.                     "max_tokens": 4096,

  1845.                     "model_type": "chat"

  1846.                 },

  1847.                 {

  1848.                     "llm_name": "openai/gpt-3.5-turbo",

  1849.                     "tags": "LLM CHAT 16K",

  1850.                     "max_tokens": 16385,

  1851.                     "model_type": "chat"

  1852.                 },

  1853.                 {

  1854.                     "llm_name": "openai/gpt-3.5-turbo-0125",

  1855.                     "tags": "LLM CHAT 16K",

  1856.                     "max_tokens": 16385,

  1857.                     "model_type": "chat"

  1858.                 },

  1859.                 {

  1860.                     "llm_name": "openai/gpt-3.5-turbo-0301",

  1861.                     "tags": "LLM CHAT 4K",

  1862.                     "max_tokens": 4095,

  1863.                     "model_type": "chat"

  1864.                 },

  1865.                 {

  1866.                     "llm_name": "openai/gpt-4",

  1867.                     "tags": "LLM CHAT 8K",

  1868.                     "max_tokens": 8191,

  1869.                     "model_type": "chat"

  1870.                 },

  1871.                 {

  1872.                     "llm_name": "openai/gpt-4-0314",

  1873.                     "tags": "LLM CHAT 8K",

  1874.                     "max_tokens": 8191,

  1875.                     "model_type": "chat"

  1876.                 },

  1877.                 {

  1878.                     "llm_name": "01-ai/yi-large",

  1879.                     "tags": "LLM CHAT 32K",

  1880.                     "max_tokens": 32768,

  1881.                     "model_type": "chat"

  1882.                 },

  1883.                 {

  1884.                     "llm_name": "01-ai/yi-34b-200k",

  1885.                     "tags": "LLM CHAT 195K",

  1886.                     "max_tokens": 200000,

  1887.                     "model_type": "chat"

  1888.                 },

  1889.                 {

  1890.                     "llm_name": "01-ai/yi-34b-chat",

  1891.                     "tags": "LLM CHAT 4K",

  1892.                     "max_tokens": 4096,

  1893.                     "model_type": "chat"

  1894.                 },

  1895.                 {

  1896.                     "llm_name": "01-ai/yi-34b",

  1897.                     "tags": "LLM CHAT 4K",

  1898.                     "max_tokens": 4096,

  1899.                     "model_type": "chat"

  1900.                 },

  1901.                 {

  1902.                     "llm_name": "01-ai/yi-6b",

  1903.                     "tags": "LLM CHAT 4K",

  1904.                     "max_tokens": 4096,

  1905.                     "model_type": "chat"

  1906.                 }

  1907.             ]

  1908.         },

  1909.         {

  1910.             "name": "StepFun",

  1911.             "logo": "",

  1912.             "tags": "LLM",

  1913.             "status": "1",

  1914.             "llm": [

  1915.                 {

  1916.                     "llm_name": "step-1-8k",

  1917.                     "tags": "LLM,CHAT,8k",

  1918.                     "max_tokens": 8192,

  1919.                     "model_type": "chat"

  1920.                 },

  1921.                 {

  1922.                     "llm_name": "step-1-32k",

  1923.                     "tags": "LLM,CHAT,32k",

  1924.                     "max_tokens": 32768,

  1925.                     "model_type": "chat"

  1926.                 },

  1927.                 {

  1928.                     "llm_name": "step-1-128k",

  1929.                     "tags": "LLM,CHAT,128k",

  1930.                     "max_tokens": 131072,

  1931.                     "model_type": "chat"

  1932.                 },

  1933.                 {

  1934.                     "llm_name": "step-1-256k",

  1935.                     "tags": "LLM,CHAT,256k",

  1936.                     "max_tokens": 262144,

  1937.                     "model_type": "chat"

  1938.                 },

  1939.                 {

  1940.                     "llm_name": "step-1v-8k",

  1941.                     "tags": "LLM,CHAT,IMAGE2TEXT",

  1942.                     "max_tokens": 8192,

  1943.                     "model_type": "image2text"

  1944.                 }

  1945.             ]

  1946.         },

  1947.         {

  1948.             "name": "NVIDIA",

  1949.             "logo": "",

  1950.             "tags": "LLM,TEXT EMBEDDING, TEXT RE-RANK",

  1951.             "status": "1",

  1952.             "llm": [

  1953.                 {

  1954.                     "llm_name": "nvidia/nemotron-4-340b-reward",

  1955.                     "tags": "LLM,CHAT,4K",

  1956.                     "max_tokens": 4096,

  1957.                     "model_type": "chat"

  1958.                 },

  1959.                 {

  1960.                     "llm_name": "aisingapore/sea-lion-7b-instruct",

  1961.                     "tags": "LLM,CHAT,4K",

  1962.                     "max_tokens": 4096,

  1963.                     "model_type": "chat"

  1964.                 },

  1965.                 {

  1966.                     "llm_name": "databricks/dbrx-instruct",

  1967.                     "tags": "LLM,CHAT,16K",

  1968.                     "max_tokens": 16384,

  1969.                     "model_type": "chat"

  1970.                 },

  1971.                 {

  1972.                     "llm_name": "google/gemma-7b",

  1973.                     "tags": "LLM,CHAT,32K",

  1974.                     "max_tokens": 32768,

  1975.                     "model_type": "chat"

  1976.                 },

  1977.                 {

  1978.                     "llm_name": "google/gemma-2b",

  1979.                     "tags": "LLM,CHAT,16K",

  1980.                     "max_tokens": 16384,

  1981.                     "model_type": "chat"

  1982.                 },

  1983.                 {

  1984.                     "llm_name": "google/gemma-2-9b-it",

  1985.                     "tags": "LLM,CHAT,8K",

  1986.                     "max_tokens": 8192,

  1987.                     "model_type": "chat"

  1988.                 },

  1989.                 {

  1990.                     "llm_name": "google/gemma-2-27b-it",

  1991.                     "tags": "LLM,CHAT,8K",

  1992.                     "max_tokens": 8192,

  1993.                     "model_type": "chat"

  1994.                 },

  1995.                 {

  1996.                     "llm_name": "google/recurrentgemma-2b",

  1997.                     "tags": "LLM,CHAT,4K",

  1998.                     "max_tokens": 4096,

  1999.                     "model_type": "chat"

  2000.                 },

  2001.                 {

  2002.                     "llm_name": "mediatek/breeze-7b-instruct",

  2003.                     "tags": "LLM,CHAT,8K",

  2004.                     "max_tokens": 8192,

  2005.                     "model_type": "chat"

  2006.                 },

  2007.                 {

  2008.                     "llm_name": "meta/llama2-70b",

  2009.                     "tags": "LLM,CHAT,4K",

  2010.                     "max_tokens": 4096,

  2011.                     "model_type": "chat"

  2012.                 },

  2013.                 {

  2014.                     "llm_name": "meta/llama3-8b",

  2015.                     "tags": "LLM,CHAT,8K",

  2016.                     "max_tokens": 8192,

  2017.                     "model_type": "chat"

  2018.                 },

  2019.                 {

  2020.                     "llm_name": "meta/llama3-70b",

  2021.                     "tags": "LLM,CHAT,8K",

  2022.                     "max_tokens": 8192,

  2023.                     "model_type": "chat"

  2024.                 },

  2025.                 {

  2026.                     "llm_name": "microsoft/phi-3-medium-128k-instruct",

  2027.                     "tags": "LLM,CHAT,128K",

  2028.                     "max_tokens": 131072,

  2029.                     "model_type": "chat"

  2030.                 },

  2031.                 {

  2032.                     "llm_name": "microsoft/phi-3-medium-4k-instruct",

  2033.                     "tags": "LLM,CHAT,4K",

  2034.                     "max_tokens": 4096,

  2035.                     "model_type": "chat"

  2036.                 },

  2037.                 {

  2038.                     "llm_name": "microsoftphi-3-mini-128k-instruct",

  2039.                     "tags": "LLM,CHAT,128K",

  2040.                     "max_tokens": 131072,

  2041.                     "model_type": "chat"

  2042.                 },

  2043.                 {

  2044.                     "llm_name": "microsoft/phi-3-mini-4k-instruct",

  2045.                     "tags": "LLM,CHAT,4K",

  2046.                     "max_tokens": 4096,

  2047.                     "model_type": "chat"

  2048.                 },

  2049.                 {

  2050.                     "llm_name": "microsoft/phi-3-small-128k-instruct",

  2051.                     "tags": "LLM,CHAT,128K",

  2052.                     "max_tokens": 131072,

  2053.                     "model_type": "chat"

  2054.                 },

  2055.                 {

  2056.                     "llm_name": "microsoft/phi-3-small-8k-instruct",

  2057.                     "tags": "LLM,CHAT,8K",

  2058.                     "max_tokens": 8192,

  2059.                     "model_type": "chat"

  2060.                 },

  2061.                 {

  2062.                     "llm_name": "mistralai/mistral-7b-instruct",

  2063.                     "tags": "LLM,CHAT,4K",

  2064.                     "max_tokens": 4096,

  2065.                     "model_type": "chat"

  2066.                 },

  2067.                 {

  2068.                     "llm_name": "mistralai/mistral-7b-instruct-v0.3",

  2069.                     "tags": "LLM,CHAT,4K",

  2070.                     "max_tokens": 4096,

  2071.                     "model_type": "chat"

  2072.                 },

  2073.                 {

  2074.                     "llm_name": "mistralai/mixtral-8x7b-instruct",

  2075.                     "tags": "LLM,CHAT,32K",

  2076.                     "max_tokens": 32768,

  2077.                     "model_type": "chat"

  2078.                 },

  2079.                 {

  2080.                     "llm_name": "mistralai/mixtral-8x22b-instruct",

  2081.                     "tags": "LLM,CHAT,64K",

  2082.                     "max_tokens": 65536,

  2083.                     "model_type": "chat"

  2084.                 },

  2085.                 {

  2086.                     "llm_name": "mistralai/mistral-large",

  2087.                     "tags": "LLM,CHAT,32K",

  2088.                     "max_tokens": 32768,

  2089.                     "model_type": "chat"

  2090.                 },

  2091.                 {

  2092.                     "llm_name": "nv-mistralai/mistral-nemo-12b-instruct",

  2093.                     "tags": "LLM,CHAT,128K",

  2094.                     "max_tokens": 131072,

  2095.                     "model_type": "chat"

  2096.                 },

  2097.                 {

  2098.                     "llm_name": "nvidia/llama3-chatqa-1.5-70b",

  2099.                     "tags": "LLM,CHAT,4K",

  2100.                     "max_tokens": 4096,

  2101.                     "model_type": "chat"

  2102.                 },

  2103.                 {

  2104.                     "llm_name": "nvidia/llama3-chatqa-1.5-8b",

  2105.                     "tags": "LLM,CHAT,4K",

  2106.                     "max_tokens": 4096,

  2107.                     "model_type": "chat"

  2108.                 },

  2109.                 {

  2110.                     "llm_name": "nvidia/nemotron-4-340b-instruct",

  2111.                     "tags": "LLM,CHAT,4K",

  2112.                     "max_tokens": 4096,

  2113.                     "model_type": "chat"

  2114.                 },

  2115.                 {

  2116.                     "llm_name": "seallms/seallm-7b-v2.5",

  2117.                     "tags": "LLM,CHAT,4K",

  2118.                     "max_tokens": 4096,

  2119.                     "model_type": "chat"

  2120.                 },

  2121.                 {

  2122.                     "llm_name": "snowflake/arctic",

  2123.                     "tags": "LLM,CHAT,4K",

  2124.                     "max_tokens": 4096,

  2125.                     "model_type": "chat"

  2126.                 },

  2127.                 {

  2128.                     "llm_name": "upstage/solar-10.7b-instruct",

  2129.                     "tags": "LLM,CHAT,4K",

  2130.                     "max_tokens": 4096,

  2131.                     "model_type": "chat"

  2132.                 },

  2133.                 {

  2134.                     "llm_name": "baai/bge-m3",

  2135.                     "tags": "TEXT EMBEDDING,8K",

  2136.                     "max_tokens": 8192,

  2137.                     "model_type": "embedding"

  2138.                 },

  2139.                 {

  2140.                     "llm_name": "nvidia/embed-qa-4",

  2141.                     "tags": "TEXT EMBEDDING,512",

  2142.                     "max_tokens": 512,

  2143.                     "model_type": "embedding"

  2144.                 },

  2145.                 {

  2146.                     "llm_name": "nvidia/nv-embed-v1",

  2147.                     "tags": "TEXT EMBEDDING,32K",

  2148.                     "max_tokens": 32768,

  2149.                     "model_type": "embedding"

  2150.                 },

  2151.                 {

  2152.                     "llm_name": "nvidia/nv-embedqa-e5-v5",

  2153.                     "tags": "TEXT EMBEDDING,512",

  2154.                     "max_tokens": 512,

  2155.                     "model_type": "embedding"

  2156.                 },

  2157.                 {

  2158.                     "llm_name": "nvidia/nv-embedqa-mistral-7b-v2",

  2159.                     "tags": "TEXT EMBEDDING,512",

  2160.                     "max_tokens": 512,

  2161.                     "model_type": "embedding"

  2162.                 },

  2163.                 {

  2164.                     "llm_name": "nvidia/nv-rerankqa-mistral-4b-v3",

  2165.                     "tags": "RE-RANK,512",

  2166.                     "max_tokens": 512,

  2167.                     "model_type": "rerank"

  2168.                 },

  2169.                 {

  2170.                     "llm_name": "nvidia/rerank-qa-mistral-4b",

  2171.                     "tags": "RE-RANK,512",

  2172.                     "max_tokens": 512,

  2173.                     "model_type": "rerank"

  2174.                 },

  2175.                 {

  2176.                     "llm_name": "snowflake/arctic-embed-l",

  2177.                     "tags": "TEXT EMBEDDING,512",

  2178.                     "max_tokens": 512,

  2179.                     "model_type": "embedding"

  2180.                 },

  2181.                 {

  2182.                     "llm_name": "adept/fuyu-8b",

  2183.                     "tags": "LLM,IMAGE2TEXT,4K",

  2184.                     "max_tokens": 4096,

  2185.                     "model_type": "image2text"

  2186.                 },

  2187.                 {

  2188.                     "llm_name": "google/deplot",

  2189.                     "tags": "LLM,IMAGE2TEXT,4K",

  2190.                     "max_tokens": 4096,

  2191.                     "model_type": "image2text"

  2192.                 },

  2193.                 {

  2194.                     "llm_name": "google/paligemma",

  2195.                     "tags": "LLM,IMAGE2TEXT,4K",

  2196.                     "max_tokens": 4096,

  2197.                     "model_type": "image2text"

  2198.                 },

  2199.                 {

  2200.                     "llm_name": "Iiuhaotian/Ilava-v1.6-34b",

  2201.                     "tags": "LLM,IMAGE2TEXT,4K",

  2202.                     "max_tokens": 4096,

  2203.                     "model_type": "image2text"

  2204.                 },

  2205.                 {

  2206.                     "llm_name": "Iiuhaotian/Ilava-v1.6-mistral-7b",

  2207.                     "tags": "LLM,IMAGE2TEXT,4K",

  2208.                     "max_tokens": 4096,

  2209.                     "model_type": "image2text"

  2210.                 },

  2211.                 {

  2212.                     "llm_name": "microsoft/kosmos-2",

  2213.                     "tags": "LLM,IMAGE2TEXT,4K",

  2214.                     "max_tokens": 4096,

  2215.                     "model_type": "image2text"

  2216.                 },

  2217.                 {

  2218.                     "llm_name": "microsoft/phi-3-vision-128k-instruct",

  2219.                     "tags": "LLM,IMAGE2TEXT,128K",

  2220.                     "max_tokens": 131072,

  2221.                     "model_type": "image2text"

  2222.                 },

  2223.                 {

  2224.                     "llm_name": "nvidia/neva-22b",

  2225.                     "tags": "LLM,IMAGE2TEXT,4K",

  2226.                     "max_tokens": 4096,

  2227.                     "model_type": "image2text"

  2228.                 }

  2229.             ]

  2230.         },

  2231.         {

  2232.             "name": "LM-Studio",

  2233.             "logo": "",

  2234.             "tags": "LLM,TEXT EMBEDDING,IMAGE2TEXT",

  2235.             "status": "1",

  2236.             "llm": []

  2237.         },

  2238.         {

  2239.             "name": "cohere",

  2240.             "logo": "",

  2241.             "tags": "LLM,TEXT EMBEDDING, TEXT RE-RANK",

  2242.             "status": "1",

  2243.             "llm": [

  2244.                 {

  2245.                     "llm_name": "command-r-plus",

  2246.                     "tags": "LLM,CHAT,128k",

  2247.                     "max_tokens": 131072,

  2248.                     "model_type": "chat"

  2249.                 },

  2250.                 {

  2251.                     "llm_name": "command-r",

  2252.                     "tags": "LLM,CHAT,128k",

  2253.                     "max_tokens": 131072,

  2254.                     "model_type": "chat"

  2255.                 },

  2256.                 {

  2257.                     "llm_name": "command",

  2258.                     "tags": "LLM,CHAT,4k",

  2259.                     "max_tokens": 4096,

  2260.                     "model_type": "chat"

  2261.                 },

  2262.                 {

  2263.                     "llm_name": "command-nightly",

  2264.                     "tags": "LLM,CHAT,128k",

  2265.                     "max_tokens": 131072,

  2266.                     "model_type": "chat"

  2267.                 },

  2268.                 {

  2269.                     "llm_name": "command-light",

  2270.                     "tags": "LLM,CHAT,4k",

  2271.                     "max_tokens": 4096,

  2272.                     "model_type": "chat"

  2273.                 },

  2274.                 {

  2275.                     "llm_name": "command-light-nightly",

  2276.                     "tags": "LLM,CHAT,4k",

  2277.                     "max_tokens": 4096,

  2278.                     "model_type": "chat"

  2279.                 },

  2280.                 {

  2281.                     "llm_name": "embed-english-v3.0",

  2282.                     "tags": "TEXT EMBEDDING",

  2283.                     "max_tokens": 512,

  2284.                     "model_type": "embedding"

  2285.                 },

  2286.                 {

  2287.                     "llm_name": "embed-english-light-v3.0",

  2288.                     "tags": "TEXT EMBEDDING",

  2289.                     "max_tokens": 512,

  2290.                     "model_type": "embedding"

  2291.                 },

  2292.                 {

  2293.                     "llm_name": "embed-multilingual-v3.0",

  2294.                     "tags": "TEXT EMBEDDING",

  2295.                     "max_tokens": 512,

  2296.                     "model_type": "embedding"

  2297.                 },

  2298.                 {

  2299.                     "llm_name": "embed-multilingual-light-v3.0",

  2300.                     "tags": "TEXT EMBEDDING",

  2301.                     "max_tokens": 512,

  2302.                     "model_type": "embedding"

  2303.                 },

  2304.                 {

  2305.                     "llm_name": "embed-english-v2.0",

  2306.                     "tags": "TEXT EMBEDDING",

  2307.                     "max_tokens": 512,

  2308.                     "model_type": "embedding"

  2309.                 },

  2310.                 {

  2311.                     "llm_name": "embed-english-light-v2.0",

  2312.                     "tags": "TEXT EMBEDDING",

  2313.                     "max_tokens": 512,

  2314.                     "model_type": "embedding"

  2315.                 },

  2316.                 {

  2317.                     "llm_name": "embed-multilingual-v2.0",

  2318.                     "tags": "TEXT EMBEDDING",

  2319.                     "max_tokens": 256,

  2320.                     "model_type": "embedding"

  2321.                 },

  2322.                 {

  2323.                     "llm_name": "rerank-english-v3.0",

  2324.                     "tags": "RE-RANK,4k",

  2325.                     "max_tokens": 4096,

  2326.                     "model_type": "rerank"

  2327.                 },

  2328.                 {

  2329.                     "llm_name": "rerank-multilingual-v3.0",

  2330.                     "tags": "RE-RANK,4k",

  2331.                     "max_tokens": 4096,

  2332.                     "model_type": "rerank"

  2333.                 },

  2334.                 {

  2335.                     "llm_name": "rerank-english-v2.0",

  2336.                     "tags": "RE-RANK,512",

  2337.                     "max_tokens": 8196,

  2338.                     "model_type": "rerank"

  2339.                 },

  2340.                 {

  2341.                     "llm_name": "rerank-multilingual-v2.0",

  2342.                     "tags": "RE-RANK,512",

  2343.                     "max_tokens": 512,

  2344.                     "model_type": "rerank"

  2345.                 }

  2346.             ]

  2347.         },

  2348.         {

  2349.             "name": "Lepton",

  2350.             "logo": "",

  2351.             "tags": "LLM",

  2352.             "status": "1",

  2353.             "llm": [

  2354.                 {

  2355.                     "llm_name": "dolphin-mixtral-8x7b",

  2356.                     "tags": "LLM,CHAT,32k",

  2357.                     "max_tokens": 32768,

  2358.                     "model_type": "chat"

  2359.                 },

  2360.                 {

  2361.                     "llm_name": "gemma-7b",

  2362.                     "tags": "LLM,CHAT,8k",

  2363.                     "max_tokens": 8192,

  2364.                     "model_type": "chat"

  2365.                 },

  2366.                 {

  2367.                     "llm_name": "llama3-1-8b",

  2368.                     "tags": "LLM,CHAT,4k",

  2369.                     "max_tokens": 4096,

  2370.                     "model_type": "chat"

  2371.                 },

  2372.                 {

  2373.                     "llm_name": "llama3-8b",

  2374.                     "tags": "LLM,CHAT,8K",

  2375.                     "max_tokens": 8192,

  2376.                     "model_type": "chat"

  2377.                 },

  2378.                 {

  2379.                     "llm_name": "llama2-13b",

  2380.                     "tags": "LLM,CHAT,4K",

  2381.                     "max_tokens": 4096,

  2382.                     "model_type": "chat"

  2383.                 },

  2384.                 {

  2385.                     "llm_name": "llama3-1-70b",

  2386.                     "tags": "LLM,CHAT,8k",

  2387.                     "max_tokens": 8192,

  2388.                     "model_type": "chat"

  2389.                 },

  2390.                 {

  2391.                     "llm_name": "llama3-70b",

  2392.                     "tags": "LLM,CHAT,8k",

  2393.                     "max_tokens": 8192,

  2394.                     "model_type": "chat"

  2395.                 },

  2396.                 {

  2397.                     "llm_name": "llama3-1-405b",

  2398.                     "tags": "LLM,CHAT,8k",

  2399.                     "max_tokens": 8192,

  2400.                     "model_type": "chat"

  2401.                 },

  2402.                 {

  2403.                     "llm_name": "mistral-7b",

  2404.                     "tags": "LLM,CHAT,8K",

  2405.                     "max_tokens": 8192,

  2406.                     "model_type": "chat"

  2407.                 },

  2408.                 {

  2409.                     "llm_name": "mistral-8x7b",

  2410.                     "tags": "LLM,CHAT,8K",

  2411.                     "max_tokens": 8192,

  2412.                     "model_type": "chat"

  2413.                 },

  2414.                 {

  2415.                     "llm_name": "nous-hermes-llama2",

  2416.                     "tags": "LLM,CHAT,4k",

  2417.                     "max_tokens": 4096,

  2418.                     "model_type": "chat"

  2419.                 },

  2420.                 {

  2421.                     "llm_name": "openchat-3-5",

  2422.                     "tags": "LLM,CHAT,4k",

  2423.                     "max_tokens": 4096,

  2424.                     "model_type": "chat"

  2425.                 },

  2426.                 {

  2427.                     "llm_name": "toppy-m-7b",

  2428.                     "tags": "LLM,CHAT,4k",

  2429.                     "max_tokens": 4096,

  2430.                     "model_type": "chat"

  2431.                 },

  2432.                 {

  2433.                     "llm_name": "wizardlm-2-7b",

  2434.                     "tags": "LLM,CHAT,32k",

  2435.                     "max_tokens": 32768,

  2436.                     "model_type": "chat"

  2437.                 },

  2438.                 {

  2439.                     "llm_name": "wizardlm-2-8x22b",

  2440.                     "tags": "LLM,CHAT,64K",

  2441.                     "max_tokens": 65536,

  2442.                     "model_type": "chat"

  2443.                 }

  2444.             ]

  2445.         },

  2446.         {

  2447.             "name": "TogetherAI",

  2448.             "logo": "",

  2449.             "tags": "LLM,TEXT EMBEDDING,IMAGE2TEXT",

  2450.             "status": "1",

  2451.             "llm": []

  2452.         },

  2453.         {

  2454.             "name": "PerfXCloud",

  2455.             "logo": "",

  2456.             "tags": "LLM,TEXT EMBEDDING",

  2457.             "status": "1",

  2458.             "llm": [

  2459.                 {

  2460.                     "llm_name": "deepseek-v2-chat",

  2461.                     "tags": "LLM,CHAT,4k",

  2462.                     "max_tokens": 4096,

  2463.                     "model_type": "chat"

  2464.                 },

  2465.                 {

  2466.                     "llm_name": "llama3.1:405b",

  2467.                     "tags": "LLM,CHAT,128k",

  2468.                     "max_tokens": 131072,

  2469.                     "model_type": "chat"

  2470.                 },

  2471.                 {

  2472.                     "llm_name": "Qwen2-72B-Instruct",

  2473.                     "tags": "LLM,CHAT,128k",

  2474.                     "max_tokens": 131072,

  2475.                     "model_type": "chat"

  2476.                 },

  2477.                 {

  2478.                     "llm_name": "Qwen2-72B-Instruct-GPTQ-Int4",

  2479.                     "tags": "LLM,CHAT,2k",

  2480.                     "max_tokens": 2048,

  2481.                     "model_type": "chat"

  2482.                 },

  2483.                 {

  2484.                     "llm_name": "Qwen2-72B-Instruct-awq-int4",

  2485.                     "tags": "LLM,CHAT,32k",

  2486.                     "max_tokens": 32768,

  2487.                     "model_type": "chat"

  2488.                 },

  2489.                 {

  2490.                     "llm_name": "Llama3-Chinese_v2",

  2491.                     "tags": "LLM,CHAT,8k",

  2492.                     "max_tokens": 8192,

  2493.                     "model_type": "chat"

  2494.                 },

  2495.                 {

  2496.                     "llm_name": "Yi-1_5-9B-Chat-16K",

  2497.                     "tags": "LLM,CHAT,16k",

  2498.                     "max_tokens": 16384,

  2499.                     "model_type": "chat"

  2500.                 },

  2501.                 {

  2502.                     "llm_name": "Qwen1.5-72B-Chat-GPTQ-Int4",

  2503.                     "tags": "LLM,CHAT,2k",

  2504.                     "max_tokens": 2048,

  2505.                     "model_type": "chat"

  2506.                 },

  2507.                 {

  2508.                     "llm_name": "Meta-Llama-3.1-8B-Instruct",

  2509.                     "tags": "LLM,CHAT,4k",

  2510.                     "max_tokens": 4096,

  2511.                     "model_type": "chat"

  2512.                 },

  2513.                 {

  2514.                     "llm_name": "Qwen2-7B-Instruct",

  2515.                     "tags": "LLM,CHAT,32k",

  2516.                     "max_tokens": 32768,

  2517.                     "model_type": "chat"

  2518.                 },

  2519.                 {

  2520.                     "llm_name": "deepseek-v2-lite-chat",

  2521.                     "tags": "LLM,CHAT,2k",

  2522.                     "max_tokens": 2048,

  2523.                     "model_type": "chat"

  2524.                 },

  2525.                 {

  2526.                     "llm_name": "Qwen2-7B",

  2527.                     "tags": "LLM,CHAT,128k",

  2528.                     "max_tokens": 131072,

  2529.                     "model_type": "chat"

  2530.                 },

  2531.                 {

  2532.                     "llm_name": "chatglm3-6b",

  2533.                     "tags": "LLM,CHAT,8k",

  2534.                     "max_tokens": 8192,

  2535.                     "model_type": "chat"

  2536.                 },

  2537.                 {

  2538.                     "llm_name": "Meta-Llama-3-70B-Instruct-GPTQ-Int4",

  2539.                     "tags": "LLM,CHAT,1k",

  2540.                     "max_tokens": 1024,

  2541.                     "model_type": "chat"

  2542.                 },

  2543.                 {

  2544.                     "llm_name": "Meta-Llama-3-8B-Instruct",

  2545.                     "tags": "LLM,CHAT,8k",

  2546.                     "max_tokens": 8192,

  2547.                     "model_type": "chat"

  2548.                 },

  2549.                 {

  2550.                     "llm_name": "Mistral-7B-Instruct",

  2551.                     "tags": "LLM,CHAT,32k",

  2552.                     "max_tokens": 32768,

  2553.                     "model_type": "chat"

  2554.                 },

  2555.                 {

  2556.                     "llm_name": "MindChat-Qwen-7B-v2",

  2557.                     "tags": "LLM,CHAT,2k",

  2558.                     "max_tokens": 2048,

  2559.                     "model_type": "chat"

  2560.                 },

  2561.                 {

  2562.                     "llm_name": "phi-2",

  2563.                     "tags": "LLM,CHAT,2k",

  2564.                     "max_tokens": 2048,

  2565.                     "model_type": "chat"

  2566.                 },

  2567.                 {

  2568.                     "llm_name": "SOLAR-10_7B-Instruct",

  2569.                     "tags": "LLM,CHAT,4k",

  2570.                     "max_tokens": 4096,

  2571.                     "model_type": "chat"

  2572.                 },

  2573.                 {

  2574.                     "llm_name": "Mixtral-8x7B-Instruct-v0.1-GPTQ",

  2575.                     "tags": "LLM,CHAT,32k",

  2576.                     "max_tokens": 32768,

  2577.                     "model_type": "chat"

  2578.                 },

  2579.                 {

  2580.                     "llm_name": "Qwen1.5-7B",

  2581.                     "tags": "LLM,CHAT,32k",

  2582.                     "max_tokens": 32768,

  2583.                     "model_type": "chat"

  2584.                 },

  2585.                 {

  2586.                     "llm_name": "BAAI/bge-large-en-v1.5",

  2587.                     "tags": "TEXT EMBEDDING",

  2588.                     "max_tokens": 512,

  2589.                     "model_type": "embedding"

  2590.                 },

  2591.                 {

  2592.                     "llm_name": "BAAI/bge-large-zh-v1.5",

  2593.                     "tags": "TEXT EMBEDDING",

  2594.                     "max_tokens": 1024,

  2595.                     "model_type": "embedding"

  2596.                 },

  2597.                 {

  2598.                     "llm_name": "BAAI/bge-m3",

  2599.                     "tags": "TEXT EMBEDDING",

  2600.                     "max_tokens": 8192,

  2601.                     "model_type": "embedding"

  2602.                 }

  2603.             ]

  2604.         },

  2605.         {

  2606.             "name": "Upstage",

  2607.             "logo": "",

  2608.             "tags": "LLM,TEXT EMBEDDING",

  2609.             "status": "1",

  2610.             "llm": [

  2611.                 {

  2612.                     "llm_name": "solar-1-mini-chat",

  2613.                     "tags": "LLM,CHAT,32k",

  2614.                     "max_tokens": 32768,

  2615.                     "model_type": "chat"

  2616.                 },

  2617.                 {

  2618.                     "llm_name": "solar-1-mini-chat-ja",

  2619.                     "tags": "LLM,CHAT,32k",

  2620.                     "max_tokens": 32768,

  2621.                     "model_type": "chat"

  2622.                 },

  2623.                 {

  2624.                     "llm_name": "solar-embedding-1-large-query",

  2625.                     "tags": "TEXT EMBEDDING",

  2626.                     "max_tokens": 4000,

  2627.                     "model_type": "embedding"

  2628.                 },

  2629.                 {

  2630.                     "llm_name": "solar-embedding-1-large-passage",

  2631.                     "tags": "TEXT EMBEDDING",

  2632.                     "max_tokens": 4000,

  2633.                     "model_type": "embedding"

  2634.                 }

  2635.             ]

  2636.         },

  2637.         {

  2638.             "name": "novita.ai",

  2639.             "logo": "",

  2640.             "tags": "LLM",

  2641.             "status": "1",

  2642.             "llm": [

  2643.                 {

  2644.                     "llm_name": "meta-llama/llama-3-8b-instruct",

  2645.                     "tags": "LLM,CHAT,8k",

  2646.                     "max_tokens": 8192,

  2647.                     "model_type": "chat"

  2648.                 },

  2649.                 {

  2650.                     "llm_name": "meta-llama/llama-3-70b-instruct",

  2651.                     "tags": "LLM,CHAT,8k",

  2652.                     "max_tokens": 8192,

  2653.                     "model_type": "chat"

  2654.                 },

  2655.                 {

  2656.                     "llm_name": "mistralai/mistral-nemo",

  2657.                     "tags": "LLM,CHAT,32k",

  2658.                     "max_tokens": 32768,

  2659.                     "model_type": "chat"

  2660.                 },

  2661.                 {

  2662.                     "llm_name": "microsoft/wizardlm-2-7b",

  2663.                     "tags": "LLM,CHAT,32k",

  2664.                     "max_tokens": 32768,

  2665.                     "model_type": "chat"

  2666.                 },

  2667.                 {

  2668.                     "llm_name": "openchat/openchat-7b",

  2669.                     "tags": "LLM,CHAT,4k",

  2670.                     "max_tokens": 4096,

  2671.                     "model_type": "chat"

  2672.                 },

  2673.                 {

  2674.                     "llm_name": "meta-llama/llama-3.1-8b-instruct",

  2675.                     "tags": "LLM,CHAT,8k",

  2676.                     "max_tokens": 8192,

  2677.                     "model_type": "chat"

  2678.                 },

  2679.                 {

  2680.                     "llm_name": "meta-llama/llama-3.1-70b-instruct",

  2681.                     "tags": "LLM,CHAT,8k",

  2682.                     "max_tokens": 8192,

  2683.                     "model_type": "chat"

  2684.                 },

  2685.                 {

  2686.                     "llm_name": "meta-llama/llama-3.1-405b-instruct",

  2687.                     "tags": "LLM,CHAT,32k",

  2688.                     "max_tokens": 32768,

  2689.                     "model_type": "chat"

  2690.                 },

  2691.                 {

  2692.                     "llm_name": "google/gemma-2-9b-it",

  2693.                     "tags": "LLM,CHAT,8k",

  2694.                     "max_tokens": 8192,

  2695.                     "model_type": "chat"

  2696.                 },

  2697.                 {

  2698.                     "llm_name": "jondurbin/airoboros-l2-70b",

  2699.                     "tags": "LLM,CHAT,4k",

  2700.                     "max_tokens": 4096,

  2701.                     "model_type": "chat"

  2702.                 },

  2703.                 {

  2704.                     "llm_name": "nousresearch/hermes-2-pro-llama-3-8b",

  2705.                     "tags": "LLM,CHAT,8k",

  2706.                     "max_tokens": 8192,

  2707.                     "model_type": "chat"

  2708.                 },

  2709.                 {

  2710.                     "llm_name": "mistralai/mistral-7b-instruct",

  2711.                     "tags": "LLM,CHAT,32k",

  2712.                     "max_tokens": 32768,

  2713.                     "model_type": "chat"

  2714.                 },

  2715.                 {

  2716.                     "llm_name": "cognitivecomputations/dolphin-mixtral-8x22b",

  2717.                     "tags": "LLM,CHAT,15k",

  2718.                     "max_tokens": 16000,

  2719.                     "model_type": "chat"

  2720.                 },

  2721.                 {

  2722.                     "llm_name": "sao10k/l3-70b-euryale-v2.1",

  2723.                     "tags": "LLM,CHAT,15k",

  2724.                     "max_tokens": 16000,

  2725.                     "model_type": "chat"

  2726.                 },

  2727.                 {

  2728.                     "llm_name": "sophosympatheia/midnight-rose-70b",

  2729.                     "tags": "LLM,CHAT,4k",

  2730.                     "max_tokens": 4096,

  2731.                     "model_type": "chat"

  2732.                 },

  2733.                 {

  2734.                     "llm_name": "gryphe/mythomax-l2-13b",

  2735.                     "tags": "LLM,CHAT,4k",

  2736.                     "max_tokens": 4096,

  2737.                     "model_type": "chat"

  2738.                 },

  2739.                 {

  2740.                     "llm_name": "nousresearch/nous-hermes-llama2-13b",

  2741.                     "tags": "LLM,CHAT,4k",

  2742.                     "max_tokens": 4096,

  2743.                     "model_type": "chat"

  2744.                 },

  2745.                 {

  2746.                     "llm_name": "Nous-Hermes-2-Mixtral-8x7B-DPO",

  2747.                     "tags": "LLM,CHAT,32k",

  2748.                     "max_tokens": 32768,

  2749.                     "model_type": "chat"

  2750.                 },

  2751.                 {

  2752.                     "llm_name": "lzlv_70b",

  2753.                     "tags": "LLM,CHAT,4k",

  2754.                     "max_tokens": 4096,

  2755.                     "model_type": "chat"

  2756.                 },

  2757.                 {

  2758.                     "llm_name": "teknium/openhermes-2.5-mistral-7b",

  2759.                     "tags": "LLM,CHAT,4k",

  2760.                     "max_tokens": 4096,

  2761.                     "model_type": "chat"

  2762.                 },

  2763.                 {

  2764.                     "llm_name": "microsoft/wizardlm-2-8x22b",

  2765.                     "tags": "LLM,CHAT,64k",

  2766.                     "max_tokens": 65535,

  2767.                     "model_type": "chat"

  2768.                 }

  2769.             ]

  2770.         },

  2771.         {

  2772.             "name": "SILICONFLOW",

  2773.             "logo": "",

  2774.             "tags": "LLM,TEXT EMBEDDING,TEXT RE-RANK",

  2775.             "status": "1",

  2776.             "llm": [

  2777.                 {

  2778.                     "llm_name": "Qwen/Qwen2-7B-Instruct",

  2779.                     "tags": "LLM,CHAT,32k",

  2780.                     "max_tokens": 32768,

  2781.                     "model_type": "chat"

  2782.                 },

  2783.                 {

  2784.                     "llm_name": "Qwen/Qwen2-1.5B-Instruct",

  2785.                     "tags": "LLM,CHAT,32k",

  2786.                     "max_tokens": 32768,

  2787.                     "model_type": "chat"

  2788.                 },

  2789.                 {

  2790.                     "llm_name": "Qwen/Qwen1.5-7B-Chat",

  2791.                     "tags": "LLM,CHAT,32k",

  2792.                     "max_tokens": 32768,

  2793.                     "model_type": "chat"

  2794.                 },

  2795.                 {

  2796.                     "llm_name": "THUDM/glm-4-9b-chat",

  2797.                     "tags": "LLM,CHAT,32k",

  2798.                     "max_tokens": 32768,

  2799.                     "model_type": "chat"

  2800.                 },

  2801.                 {

  2802.                     "llm_name": "THUDM/chatglm3-6b",

  2803.                     "tags": "LLM,CHAT,32k",

  2804.                     "max_tokens": 32768,

  2805.                     "model_type": "chat"

  2806.                 },

  2807.                 {

  2808.                     "llm_name": "01-ai/Yi-1.5-9B-Chat-16K",

  2809.                     "tags": "LLM,CHAT,16k",

  2810.                     "max_tokens": 16384,

  2811.                     "model_type": "chat"

  2812.                 },

  2813.                 {

  2814.                     "llm_name": "01-ai/Yi-1.5-6B-Chat",

  2815.                     "tags": "LLM,CHAT,4k",

  2816.                     "max_tokens": 4096,

  2817.                     "model_type": "chat"

  2818.                 },

  2819.                 {

  2820.                     "llm_name": "google/gemma-2-9b-it",

  2821.                     "tags": "LLM,CHAT,8k",

  2822.                     "max_tokens": 8192,

  2823.                     "model_type": "chat"

  2824.                 },

  2825.                 {

  2826.                     "llm_name": "internlm/internlm2_5-7b-chat",

  2827.                     "tags": "LLM,CHAT,32k",

  2828.                     "max_tokens": 32768,

  2829.                     "model_type": "chat"

  2830.                 },

  2831.                 {

  2832.                     "llm_name": "meta-llama/Meta-Llama-3-8B-Instruct",

  2833.                     "tags": "LLM,CHAT,8k",

  2834.                     "max_tokens": 8192,

  2835.                     "model_type": "chat"

  2836.                 },

  2837.                 {

  2838.                     "llm_name": "meta-llama/Meta-Llama-3.1-8B-Instruct",

  2839.                     "tags": "LLM,CHAT,8k",

  2840.                     "max_tokens": 8192,

  2841.                     "model_type": "chat"

  2842.                 },

  2843.                 {

  2844.                     "llm_name": "mistralai/Mistral-7B-Instruct-v0.2",

  2845.                     "tags": "LLM,CHAT,32k",

  2846.                     "max_tokens": 32768,

  2847.                     "model_type": "chat"

  2848.                 },

  2849.                 {

  2850.                     "llm_name": "Pro/Qwen/Qwen2-7B-Instruct",

  2851.                     "tags": "LLM,CHAT,32k",

  2852.                     "max_tokens": 32768,

  2853.                     "model_type": "chat"

  2854.                 },

  2855.                 {

  2856.                     "llm_name": "Pro/Qwen/Qwen2-1.5B-Instruct",

  2857.                     "tags": "LLM,CHAT,32k",

  2858.                     "max_tokens": 32768,

  2859.                     "model_type": "chat"

  2860.                 },

  2861.                 {

  2862.                     "llm_name": "Pro/Qwen/Qwen1.5-7B-Chat",

  2863.                     "tags": "LLM,CHAT,32k",

  2864.                     "max_tokens": 32768,

  2865.                     "model_type": "chat"

  2866.                 },

  2867.                 {

  2868.                     "llm_name": "Pro/THUDM/glm-4-9b-chat",

  2869.                     "tags": "LLM,CHAT,32k",

  2870.                     "max_tokens": 32768,

  2871.                     "model_type": "chat"

  2872.                 },

  2873.                 {

  2874.                     "llm_name": "Pro/THUDM/chatglm3-6b",

  2875.                     "tags": "LLM,CHAT,32k",

  2876.                     "max_tokens": 32768,

  2877.                     "model_type": "chat"

  2878.                 },

  2879.                 {

  2880.                     "llm_name": "Pro/01-ai/Yi-1.5-9B-Chat-16K",

  2881.                     "tags": "LLM,CHAT,16k",

  2882.                     "max_tokens": 16384,

  2883.                     "model_type": "chat"

  2884.                 },

  2885.                 {

  2886.                     "llm_name": "Pro/01-ai/Yi-1.5-6B-Chat",

  2887.                     "tags": "LLM,CHAT,4k",

  2888.                     "max_tokens": 4096,

  2889.                     "model_type": "chat"

  2890.                 },

  2891.                 {

  2892.                     "llm_name": "Pro/internlm/internlm2_5-7b-chat",

  2893.                     "tags": "LLM,CHAT,32k",

  2894.                     "max_tokens": 32768,

  2895.                     "model_type": "chat"

  2896.                 },

  2897.                 {

  2898.                     "llm_name": "Pro/google/gemma-2-9b-it",

  2899.                     "tags": "LLM,CHAT,8k",

  2900.                     "max_tokens": 8192,

  2901.                     "model_type": "chat"

  2902.                 },

  2903.                 {

  2904.                     "llm_name": "Pro/meta-llama/Meta-Llama-3.1-8B-Instruct",

  2905.                     "tags": "LLM,CHAT,32k",

  2906.                     "max_tokens": 32768,

  2907.                     "model_type": "chat"

  2908.                 },

  2909.                 {

  2910.                     "llm_name": "Pro/meta-llama/Meta-Llama-3-8B-Instruct",

  2911.                     "tags": "LLM,CHAT,8k",

  2912.                     "max_tokens": 8192,

  2913.                     "model_type": "chat"

  2914.                 },

  2915.                 {

  2916.                     "llm_name": "Pro/mistralai/Mistral-7B-Instruct-v0.2",

  2917.                     "tags": "LLM,CHAT,32k",

  2918.                     "max_tokens": 32768,

  2919.                     "model_type": "chat"

  2920.                 },

  2921.                 {

  2922.                     "llm_name": "Qwen/Qwen2-72B-Instruct",

  2923.                     "tags": "LLM,CHAT,32k",

  2924.                     "max_tokens": 32768,

  2925.                     "model_type": "chat"

  2926.                 },

  2927.                 {

  2928.                     "llm_name": "Qwen/Qwen2-Math-72B-Instruct",

  2929.                     "tags": "LLM,CHAT,32k",

  2930.                     "max_tokens": 32768,

  2931.                     "model_type": "chat"

  2932.                 },

  2933.                 {

  2934.                     "llm_name": "Qwen/Qwen2-57B-A14B-Instruct",

  2935.                     "tags": "LLM,CHAT,32k",

  2936.                     "max_tokens": 32768,

  2937.                     "model_type": "chat"

  2938.                 },

  2939.                 {

  2940.                     "llm_name": "Qwen/Qwen1.5-110B-Chat",

  2941.                     "tags": "LLM,CHAT,32k",

  2942.                     "max_tokens": 32768,

  2943.                     "model_type": "chat"

  2944.                 },

  2945.                 {

  2946.                     "llm_name": "Qwen/Qwen1.5-32B-Chat",

  2947.                     "tags": "LLM,CHAT,32k",

  2948.                     "max_tokens": 32768,

  2949.                     "model_type": "chat"

  2950.                 },

  2951.                 {

  2952.                     "llm_name": "Qwen/Qwen1.5-14B-Chat",

  2953.                     "tags": "LLM,CHAT,32k",

  2954.                     "max_tokens": 32768,

  2955.                     "model_type": "chat"

  2956.                 },

  2957.                 {

  2958.                     "llm_name": "01-ai/Yi-1.5-34B-Chat-16K",

  2959.                     "tags": "LLM,CHAT,16k",

  2960.                     "max_tokens": 16384,

  2961.                     "model_type": "chat"

  2962.                 },

  2963.                 {

  2964.                     "llm_name": "deepseek-ai/DeepSeek-Coder-V2-Instruct",

  2965.                     "tags": "LLM,CHAT,32k",

  2966.                     "max_tokens": 32768,

  2967.                     "model_type": "chat"

  2968.                 },

  2969.                 {

  2970.                     "llm_name": "deepseek-ai/DeepSeek-V2-Chat",

  2971.                     "tags": "LLM,CHAT,32k",

  2972.                     "max_tokens": 32768,

  2973.                     "model_type": "chat"

  2974.                 },

  2975.                 {

  2976.                     "llm_name": "deepseek-ai/deepseek-llm-67b-chat",

  2977.                     "tags": "LLM,CHAT,4k",

  2978.                     "max_tokens": 4096,

  2979.                     "model_type": "chat"

  2980.                 },

  2981.                 {

  2982.                     "llm_name": "internlm/internlm2_5-20b-chat",

  2983.                     "tags": "LLM,CHAT,32k",

  2984.                     "max_tokens": 32768,

  2985.                     "model_type": "chat"

  2986.                 },

  2987.                 {

  2988.                     "llm_name": "meta-llama/Meta-Llama-3.1-405B-Instruct",

  2989.                     "tags": "LLM,CHAT,32k",

  2990.                     "max_tokens": 32768,

  2991.                     "model_type": "chat"

  2992.                 },

  2993.                 {

  2994.                     "llm_name": "meta-llama/Meta-Llama-3.1-70B-Instruct",

  2995.                     "tags": "LLM,CHAT,32k",

  2996.                     "max_tokens": 32768,

  2997.                     "model_type": "chat"

  2998.                 },

  2999.                 {

  3000.                     "llm_name": "meta-llama/Meta-Llama-3-70B-Instruct",

  3001.                     "tags": "LLM,CHAT,32k",

  3002.                     "max_tokens": 32768,

  3003.                     "model_type": "chat"

  3004.                 },

  3005.                 {

  3006.                     "llm_name": "mistralai/Mixtral-8x7B-Instruct-v0.1",

  3007.                     "tags": "LLM,CHAT,32k",

  3008.                     "max_tokens": 32768,

  3009.                     "model_type": "chat"

  3010.                 },

  3011.                 {

  3012.                     "llm_name": "google/gemma-2-27b-it",

  3013.                     "tags": "LLM,CHAT,8k",

  3014.                     "max_tokens": 8192,

  3015.                     "model_type": "chat"

  3016.                 },

  3017.                 {

  3018.                     "llm_name": "BAAI/bge-m3 ",

  3019.                     "tags": "TEXT EMBEDDING,8K",

  3020.                     "max_tokens": 8192,

  3021.                     "model_type": "embedding"

  3022.                 },

  3023.                 {

  3024.                     "llm_name": "BAAI/bge-large-en-v1.5 ",

  3025.                     "tags": "TEXT EMBEDDING,512",

  3026.                     "max_tokens": 512,

  3027.                     "model_type": "embedding"

  3028.                 },

  3029.                 {

  3030.                     "llm_name": "BAAI/bge-large-zh-v1.5 ",

  3031.                     "tags": "TEXT EMBEDDING,512",

  3032.                     "max_tokens": 512,

  3033.                     "model_type": "embedding"

  3034.                 },

  3035.                 {

  3036.                     "llm_name": "netease-youdao/bce-embedding-base_vl",

  3037.                     "tags": "TEXT EMBEDDING,512",

  3038.                     "max_tokens": 512,

  3039.                     "model_type": "embedding"

  3040.                 },

  3041.                 {

  3042.                     "llm_name": "BAAI/bge-reranker-v2-m3",

  3043.                     "tags": "RE-RANK, 512",

  3044.                     "max_tokens": 1024,

  3045.                     "model_type": "rerank"

  3046.                 },

  3047.                 {

  3048.                     "llm_name": "netease-youdao/bce-reranker-base-v1",

  3049.                     "tags": "RE-RANK, 512",

  3050.                     "max_tokens": 1024,

  3051.                     "model_type": "rerank"

  3052.                 }

  3053.             ]

  3054.         }        

  3055.     ]

  3056. }