aimux providers

August 13, 2026 · View on GitHub

GENERATED by scripts/gen_providers_doc.py — do not edit by hand. Regenerate with: python scripts/gen_providers_doc.py

251 registry-backed OpenAI-compatible providers (construct via provider(name, ...) / ProviderName) + 78 non-registry providers (construct via the typed factories listed below).

Registry-backed (OpenAI-compatible) — 251

namedisplayenv varbase_url
abacusAbacusABACUS_API_KEYhttps://routellm.abacus.ai/v1
abliteration_aiAbliteration AIABLIT_KEYhttps://api.abliteration.ai/v1
ai21AI21 LabsAI21_API_KEYhttps://api.ai21.ai/v1
ai302302.AIAI302_API_KEYhttps://api.302.ai/v1
ai_routerAI-ROUTERAI_ROUTER_API_KEYhttps://api.ai-router.dev/v1
aiandAIandAIAND_API_KEYhttps://api.aiand.com/v1
aibadgrAI BadgrAIBADGR_API_KEYhttps://api.aibadgr.com/v1
aigc2dAIGC2DAIGC2D_API_KEYhttps://api.aigc2d.com/v1
aihubmixAIHubMixAIHUBMIX_API_KEYhttps://aihubmix.com/v1
ailsAILSAILS_API_KEYhttps://api.caipacity.com/v1
aimlAI/ML APIAIML_API_KEYhttps://api.aimlapi.com/v1
aki_ioAKI.IOAKI_IO_API_KEYhttps://aki.io/openai/v1
albertAlbertALBERT_API_KEYhttps://api.albert.ai/v1
alibabaAlibaba Cloud (DashScope)ALIBABA_API_KEYhttps://dashscope-intl.aliyuncs.com/compatible-mode/v1
alibaba_coding_planAlibaba Coding PlanALIBABA_CODING_PLAN_API_KEYhttps://coding-intl.dashscope.aliyuncs.com/v1
alibaba_coding_plan_cnAlibaba Coding Plan (China)ALIBABA_CODING_PLAN_API_KEYhttps://coding.dashscope.aliyuncs.com/v1
alibaba_token_planAlibaba Token PlanALIBABA_TOKEN_PLAN_API_KEYhttps://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1
alibaba_token_plan_cnAlibaba Token Plan (China)ALIBABA_TOKEN_PLAN_API_KEYhttps://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1
ambientAmbientAMBIENT_API_KEYhttps://api.ambient.xyz/v1
anyapiAnyAPIANYAPI_KEYhttps://api.anyapi.ai/v1
anyscaleAnyscaleANYSCALE_API_KEYhttps://api.endpoints.anyscale.com/v1
apertisApertisSTIMA_API_KEYhttps://api.stima.tech/v1
api2dAPI2DAPI2D_API_KEYhttps://oa.api2d.net/v1
api2gptAPI2GPTAPI2GPT_API_KEYhttps://api.api2gpt.com/v1
apiserpentAPI SerpentAPISERPENT_API_KEYhttps://api.apiserpent.com/v1
atlascloudAtlasCloudATLASCLOUD_API_KEYhttps://api.atlascloud.com/v1
atomic_chatAtomic ChatATOMIC_CHAT_API_KEYhttp://127.0.0.1:1337/v1
aurikoAurikoAURIKO_API_KEYhttps://api.auriko.ai/v1
azure_aiAzure AIAZURE_AI_API_KEYhttps://models.inference.ai.azure.com
baichuanBaichuan AIBAICHUAN_API_KEYhttps://api.baichuan-ai.com/v1
baiduBaidu (文心/ERNIE)BAIDU_API_KEYhttps://qianfan.baidubce.com/v2
baidu_v2BaiduV2QIANFAN_API_KEYhttps://qianfan.baidubce.com/v2
bailingBailingBAILING_API_TOKENhttps://api.ant-ling.com/v1
basetenBasetenBASETEN_API_KEYhttps://inference.baseten.co/v1
bergetBerget.AIBERGET_API_KEYhttps://api.berget.ai/v1
bigmodelBigModel (智谱)BIGMODEL_API_KEYhttps://open.bigmodel.cn/api/paas/v4
blueclawBlue ClawBLUECLAW_API_KEYhttps://openai.blueclaw.network/v1
bytedanceByteDanceARK_API_KEYhttps://ark.cn-beijing.volces.com/api/v3
byteplusBytePlus (Volcano)BYTEPLUS_API_KEYhttps://ark.bytepluses.com/api/v3
bytezBytezBYTEZ_API_KEYhttps://api.bytez.com/v2
canopywaveCanopywaveCANOPYWAVE_API_KEYhttps://api.canopywave.com/v1
cerebrasCerebrasCEREBRAS_API_KEYhttps://api.cerebras.ai/v1
chatgptChatGPT (订阅)CHATGPT_API_KEYhttps://chatgpt.com/backend-api/codex
cherryincherryinCHERRYIN_API_KEYhttps://open.cherryin.net
chutesChutesCHUTES_API_KEYhttps://llm.chutes.ai/v1
clarifaiClarifaiCLARIFAI_API_KEYhttps://api.clarifai.com/v2/ext/openai/v1
claudinioClaudinioCLAUDINIO_API_KEYhttps://api.claudin.io
cline_passClineCLINE_API_KEYhttps://api.cline.bot/v1
closeaiCloseAICLOSEAI_API_KEYhttps://api.closeai-proxy.xyz/v1
cloudferro_sherlockCloudFerro SherlockCLOUDFERRO_SHERLOCK_API_KEYhttps://api-sherlock.cloudferro.com/openai/v1
cloudflareCloudflareCLOUDFLARE_API_KEYhttps://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1
cloudflare_workers_aiCloudflare Workers AICLOUDFLARE_API_KEYhttps://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1
codestralCodestral (Mistral)CODESTRAL_API_KEYhttps://api.mistral.ai/v1
cometapiCometAPICOMETAPI_API_KEYhttps://api.cometapi.com/v1
commandcodeCommandCodeCOMMANDCODE_API_KEYhttps://api.commandcode.com/v1
compactifaiCompactifAICOMPACTIFAI_API_KEYhttps://api.compactif.ai/v1
copilotGitHub CopilotCOPILOT_API_KEYhttps://api.githubcopilot.com
cortecsCortecsCORTECS_API_KEYhttps://api.cortecs.ai/v1/
cozeCoze (扣子)COZE_API_KEYhttps://api.coze.cn/v1
crofCrofAICROF_API_KEYhttps://crof.ai/v1
crossmodelCrossModelCROSSMODEL_API_KEYhttps://api.crossmodel.ai/v1
crusoeCrusoeCRUSOE_API_KEYhttps://api.inference.crusoecloud.com/v1
daoxeDaoXEDAOXE_API_KEYhttps://daoxe.com/v1
darkbloomDarkbloomDARKBLOOM_API_KEYhttps://api.darkbloom.dev/v1
databricksDatabricksDATABRICKS_API_KEYhttps://databricks.com/serving-endpoints
datarobotDataRobotDATAROBOT_API_TOKENhttps://app.datarobot.com/api/v2
deepbricksDeepBricksDEEPBRICKS_API_KEYhttps://api.deepbricks.ai/v1
deepinfraDeepInfraDEEPINFRA_API_KEYhttps://api.deepinfra.com/v1/openai
deepseekDeepSeekDEEPSEEK_API_KEYhttps://api.deepseek.com/v1
digitaloceanDigitalOceanDIGITALOCEAN_ACCESS_TOKENhttps://inference.do-ai.run
dinferenceDInferenceDINFERENCE_API_KEYhttps://api.dinference.com/v1
doubaoDoubaoARK_API_KEYhttps://ark.cn-beijing.volces.com/api/v3
doublewordDoublewordDOUBLEWORD_API_KEYhttps://api.doubleword.ai/v1
drunD.Run (China)DRUN_API_KEYhttps://chat.d.run/v1
ebcloudEBCloudEBCLOUD_API_KEYhttps://maas-api.ebcloud.com/v1
embercloudEmbercloudEMBERCLOUD_API_KEYhttps://api.embercloud.com/v1
empiriolabsEmpirioLabs AIEMPIRIOLABS_API_KEYhttps://api.empiriolabs.ai/v1
evrocevrocEVROC_API_KEYhttps://models.think.evroc.com/v1
fastcrwFastCRWFASTCRW_API_KEYhttps://fastcrw.com/api/v1
fastgptFastGPTFASTGPT_API_KEYhttps://api.fastgpt.in/v1
fastrouterFastRouterFASTROUTER_API_KEYhttps://api.fastrouter.ai/v1
featherless_aiFeatherless AIFEATHERLESS_API_KEYhttps://api.featherless.ai/v1
firepassFireworks (Firepass)FIREWORKS_API_KEYhttps://api.fireworks.ai/inference/v1
fireworksFireworksFIREWORKS_API_KEYhttps://api.fireworks.ai/inference/v1
freemodelFreeModelFREEMODEL_API_KEYhttps://api.freemodel.dev/v1
friendliaiFriendliAIFRIENDLIAI_API_KEYhttps://inference.friendli.ai/v1
frogbotFrogBotFROGBOT_API_KEYhttps://app.frogbot.ai/api/v1
galadrielGaladrielGALADRIEL_API_KEYhttps://api.galadriel.com/v1
gdcGDCGDC_API_KEYhttps://api.gdc.ai/v1
gigachatGigaChat (Sberbank)GIGACHAT_API_KEYhttps://gigachat.devices.sberbank.ru/api/v1
githubGitHub ModelsGITHUB_TOKENhttps://models.inference.ai.azure.com
gmiGMIGMI_API_KEYhttps://api.gmi-serving.com/v1
gmicloudGMI CloudGMI_API_KEYhttps://api.gmi-serving.com/v1
gonka24Gonka24GONKA24_API_KEYhttps://api.gonka24.com/v1
gradient_aiGradient AIGRADIENT_API_KEYhttps://inference.do-ai.run/v1
groqGroqGROQ_API_KEYhttps://api.groq.com/openai/v1
heliconeHeliconeHELICONE_API_KEYhttps://api.helicone.ai/v1
herokuHeroku AIHEROKU_API_KEYhttps://api.heroku.com/inference/v1
hetznerHetznerHETZNER_VLLM_API_KEYhttps://inference.hetzner.com/api/v1
hosted_vllmHosted vLLMHOSTED_VLLM_API_KEYhttps://hosted-vllm-api.com/v1
hpc_aiHPC-AIINFERENCE_API_KEYhttps://api.hpc-ai.com/inference/v1
hyperbolicHyperbolicHYPERBOLIC_API_KEYhttps://api.hyperbolic.xyz/v1
iflowcniFlowIFLOW_API_KEYhttps://apis.iflow.cn/v1
inceptionInception LabsINCEPTION_API_KEYhttps://api.inceptionlabs.ai/v1
inceptronInceptronINCEPTRON_API_KEYhttps://api.inceptron.io/v1
inference_netInference.netINFERENCE_NET_API_KEYhttps://api.inference.net/v1
inferencehubInferenceHubINFERENCEHUB_API_KEYhttps://app.inferencehub.tech/v1
inferxInferXINFERX_API_KEYhttps://model.inferx.net/v1
infinityInfinity AIINFINITY_API_KEYhttps://infinity.ai/api/v1
io_netIO.NETIOINTELLIGENCE_API_KEYhttps://api.intelligence.io.solutions/api/v1
jiekouJiekou.AIJIEKOU_API_KEYhttps://api.highwayapi.ai/openai
kenariKenariKENARI_API_KEYhttps://kenari.id/v1
kiloKiloKILO_API_KEYhttps://api.kilo.ai/v1
kimiKimiMOONSHOT_API_KEYhttps://api.moonshot.ai/v1
kimi_for_codingKimi For CodingKIMI_API_KEYhttps://api.kimi.com/coding/v1
kiroKiroKIRO_API_KEYhttps://api.kiro.dev/v1
kluster_aiKluster AIKLUSTER_API_KEYhttps://api.kluster.ai/v1
krutrimKrutrimKRUTRIM_API_KEYhttps://api.krutrim.ai/v1
kuae_cloud_coding_planKUAE Cloud Coding PlanKUAE_API_KEYhttps://coding-plan-endpoint.kuaecloud.net/v1
lambda_aiLambda AILAMBDA_API_KEYhttps://api.lambda.ai/v1
lemonadeLemonadeLEMONADE_API_KEYhttp://localhost:13305/v1
lemonfox_aiLemonfox AILEMONFOX_API_KEYhttps://api.lemonfox.ai/v1
libertaiLibertaiLIBERTAI_API_KEYhttps://api.libertai.io/v1
lilacLilacLILAC_API_KEYhttps://api.getlilac.com/v1
lingyiwanwuLingyiwanwu (零一万物)LINGYIWANWU_API_KEYhttps://api.lingyiwanwu.com/v1
llamaLlamaLLAMA_API_KEYhttps://api.llama.com/compat/v1/
llamagateLlamagateLLAMAGATE_API_KEYhttps://api.llamagate.dev/v1
llmgatewayLLM GatewayLLM_GATEWAY_API_KEYhttps://api.llmgateway.io/v1
llmtrLLMTRLLMTR_API_KEYhttps://llmtr.com/v1
longcatLongCatLONGCAT_API_KEYhttps://api.longcat.chat/v1
lucidqueryLucidQueryLUCIDQUERY_API_KEYhttps://api.lucidquery.com/v1
lynkrLynkrLYNKR_API_KEYhttp://localhost:8081/v1
matteraiMatter AIMATTERAI_API_KEYhttps://api.matterai.com/v1
meganovaMeganovaMEGANOVA_API_KEYhttps://api.meganova.ai/v1
merge_gatewayMerge GatewayMERGE_GATEWAY_API_KEYhttps://api-gateway.merge.dev/v1/openai
metaMetaMODEL_API_KEYhttps://api.meta.ai/v1
meta_llamaMeta Llama APILLAMA_API_KEYhttps://api.llama.com/compat/v1
mimoMimoMIMO_API_KEYhttps://api.xiaomimimo.com/v1
minimaxMiniMaxMINIMAX_API_KEYhttps://api.minimax.io/v1
minimax_cnMiniMax (minimaxi.com)MINIMAX_API_KEYhttps://api.minimaxi.com/v1
minimax_cn_coding_planMiniMax Token Plan (minimaxi.com)MINIMAX_API_KEYhttps://api.minimaxi.com/v1
minimax_coding_planMiniMax Token Plan (minimax.io)MINIMAX_API_KEYhttps://api.minimax.io/anthropic/v1
miraMiraMIRA_API_KEYhttps://api.mira.so/v1
mixlayerMixlayerMIXLAYER_API_KEYhttps://models.mixlayer.ai/v1
moarkMoarkMOARK_API_KEYhttps://api.moark.com/v1
modalModalMODAL_API_KEYhttps://modal.com/v1
model_oracle_aiModel Oracle AIMODEL_ORACLE_API_KEYhttps://api.modeloracle.com/api/v1
modelscopeModelScopeMODELSCOPE_API_KEYhttps://api-inference.modelscope.cn/v1
moonshotaiMoonshot AIMOONSHOT_API_KEYhttps://api.moonshot.cn/v1
moonshotai_cnMoonshot AI (China)MOONSHOT_API_KEYhttps://api.moonshot.cn/anthropic/v1
morphMorph LLMMORPH_API_KEYhttps://api.morphllm.com/v1
nanogptNanoGPTNANOGPT_API_KEYhttps://api.nanogpt.com/v1
ncompassNcompassNCOMPASS_API_KEYhttps://api.ncompass.tech/v1
nearaiNEAR AI CloudNEARAI_API_KEYhttps://cloud-api.near.ai/v1
nebiusNebius AINEBIUS_API_KEYhttps://api.studio.nebius.ai/v1
neonNeonNEON_AI_GATEWAY_TOKENhttps://<branch-host>/v1
neuralwattNeuralwattNEURALWATT_API_KEYhttps://api.neuralwatt.com/v1
nextbitNextBitNEXTBIT_API_KEYhttps://api.nextbit.ai/v1
nlp_cloudNLP CloudNLPCLOUD_API_KEYhttps://api.nlpcloud.io/v1
nous_researchNous ResearchNOUS_API_KEYhttps://api.nousresearch.com/v1
novitaNovita AINOVITA_API_KEYhttps://api.novita.ai/v1
nscaleNscaleNSCALE_API_KEYhttps://inference.api.nscale.com/v1
nvidia_nimNVIDIA NIMNVIDIA_API_KEYhttps://integrate.api.nvidia.com/v1
ociOCIOCI_API_KEYhttps://inference.generativeai.${region}.oci.oraclecloud.com/openai/v1
ofoxOfoxAIOFOX_API_KEYhttps://api.ofox.ai/v1
ohmygptOhMyGPTOHMYGPT_API_KEYhttps://api.ohmygpt.com/v1
ollama_cloudOllama CloudOLLAMA_CLOUD_API_KEYhttps://api.ollama.com/v1
openaimaxOpenAIMaxOPENAIMAX_API_KEYhttps://api.openaimax.com/v1
openaisbOpenAI-SBOPENAISB_API_KEYhttps://api.openaisb.com/v1
opencodeOpenCode ZenOPENCODE_API_KEYhttps://api.opencode.zen/v1
opencode_goOpenCode GoOPENCODE_GO_API_KEYhttps://api.opencode.dev/v1
opencode_zenOpenCode ZenOPENCODE_ZEN_API_KEYhttps://api.opencode.zen/v1
orcarouterOrcaRouterORCAROUTER_API_KEYhttps://api.orcarouter.com/v1
ovhcloudOVHcloud AIOVHCLOUD_API_KEYhttps://oai.endpoints.kepler.ai.cloud.ovh.net/v1
parasailParasailPARASAIL_API_KEYhttps://api.parasail.io/v1
perfxcloudPerfXCloudPERFXCLOUD_API_KEYhttps://api.perfxcloud.com/v1
perplexityPerplexityPERPLEXITY_API_KEYhttps://api.perplexity.ai
perplexity_agentPerplexity AgentPERPLEXITY_API_KEYhttps://api.perplexity.ai/v1
petalsPetalsPETALS_API_KEYhttps://api.petals.dev/v1
pinstripesPinstripesPINSTRIPES_API_KEYhttps://api.pinstripes.io/v1
pioneerPioneerPIONEER_API_KEYhttps://api.pioneer.ai/v1
poePoePOE_API_KEYhttps://api.poe.com/v1
poolsidePoolsidePOOLSIDE_API_KEYhttps://inference.poolside.ai/v1
portkeyPortkey GatewayPORTKEY_API_KEYhttps://api.portkey.ai/v1
ppinfraPPInfra（PPIO 派欧云）PPIO_API_KEYhttps://api.ppio.com/openai
predibasePredibasePREDIBASE_API_KEYhttps://serving.app.predibase.com/v1
privatemode_aiPrivatemode AIPRIVATEMODE_API_KEYhttp://localhost:8080/v1
publicaiPublicaiPUBLICAI_API_KEYhttps://platform.publicai.co/v1
qihang_aiQiHang（启航 AI）QIHANG_API_KEYhttps://api.qhaigc.net/v1
qihoo360360 AIAI360_API_KEYhttps://api.360.cn/v1
qiniu_aiQiniu AIQINIU_API_KEYhttps://api.qiniu.com/v1
regolo_aiRegolo AIREGOLO_API_KEYhttps://api.regolo.ai/v1
reka_aiReka AIREKA_API_KEYhttps://api.reka.ai/v1
requestyRequestyREQUESTY_API_KEYhttps://api.requesty.ai/v1
reveReveREVE_API_KEYhttps://api.reve.ai/v1
routing_runrouting.runROUTING_RUN_API_KEYhttps://api.routing.run/v1
sakanaSakana AISAKANA_API_KEYhttps://api.sakana.ai/v1
sambanovaSambaNovaSAMBANOVA_API_KEYhttps://api.sambanova.ai/v1
sarvamSarvam AISARVAM_API_KEYhttps://api.sarvam.ai/v1
scalewayScaleway AISCALEWAY_API_KEYhttps://api.scaleway.ai/v1
scx_aiSCX AISCX_AI_API_KEYhttps://api.scx.ai/v1
siliconflowSiliconFlowSILICONFLOW_API_KEYhttps://api.siliconflow.cn/v1
snowflakeSnowflakeSNOWFLAKE_PAThttps://<account-identifier>.snowflakecomputing.com/api/v2/cortex/v1
snowflake_cortexSnowflake CortexSNOWFLAKE_CORTEX_PAThttps://<account-identifier>.snowflakecomputing.com/api/v2/cortex/v1
stackitSTACKITSTACKIT_API_KEYhttps://api.openai-compat.model-serving.eu01.onstackit.cloud/v1
stepfunStepFun (阶跃星辰)STEPFUN_API_KEYhttps://api.stepfun.com/v1
stepfun_ai_step_planStepFun Step Plan (Global)STEPFUN_API_KEYhttps://api.stepfun.ai/step_plan/v1
stepfun_step_planStepFun Step Plan (China)STEPFUN_API_KEYhttps://api.stepfun.com/step_plan/v1
subconsciousSubconsciousSUBCONSCIOUS_API_KEYhttps://api.subconscious.dev/v1
submodelSubModelSUBMODEL_API_KEYhttps://api.submodel.com/v1
syntheticSyntheticSYNTHETIC_API_KEYhttps://api.synthetic.new/openai/v1
tencentTencent (混元/Hunyuan)TENCENT_API_KEYhttps://api.hunyuan.cloud.tencent.com/v1
tencent_coding_planTencent Coding Plan (China)TENCENT_CODING_PLAN_API_KEYhttps://api.lkeap.cloud.tencent.com/coding/v3
tencent_token_planTencent Token PlanTENCENT_TOKEN_PLAN_API_KEYhttps://api.lkeap.cloud.tencent.com/plan/v3
tencent_token_plan_enterprise_auto腾讯云 Token Plan / Token Plan 企业版轻享套餐TENCENT_TOKEN_PLAN_ENTERPRISE_API_KEYhttps://tokenhub.tencentmaas.com/plan/v3
tencent_token_plan_enterprise_pro腾讯云 Token Plan / Token Plan 企业版专业套餐TENCENT_TOKEN_PLAN_ENTERPRISE_API_KEYhttps://tokenhub.tencentmaas.com/plan/v3
tencent_token_plan_general_personal腾讯云 Token Plan / 通用 Token Plan（个人版）TENCENT_TOKEN_PLAN_API_KEYhttps://api.lkeap.cloud.tencent.com/plan/v3
tencent_token_plan_hy_personal腾讯云 Token Plan / Hy Token Plan（个人版）TENCENT_TOKEN_PLAN_API_KEYhttps://api.lkeap.cloud.tencent.com/plan/v3
tencent_tokenhubTencent TokenHubTENCENT_TOKENHUB_API_KEYhttps://tokenhub.tencentmaas.com/v1
tensormeshTensormeshYOUR_API_KEYhttps://serverless.tensormesh.ai
the_grid_aiThe Grid AITHEGRIDAI_API_KEYhttps://api.thegrid.ai/v1
thinkingmachinesThinking MachinesTINKER_API_KEYhttps://tinker.thinkingmachines.dev/services/tinker-prod/oai/api/v1
tinfoilTinfoilTINFOIL_API_KEYhttps://inference.tinfoil.sh/v1
togetheraiTogether AITOGETHER_API_KEYhttps://api.together.xyz/v1
tokenfluxTokenfluxTOKENFLUX_API_KEYhttps://tokenflux.ai/v1
tokenponyTokenPonyTOKENPONY_API_KEYhttps://api.tokenpony.com/v1
trustedrouterTrustedRouterTRUSTEDROUTER_API_KEYhttps://api.trustedrouter.com/v1
tundraTundraTUNDRA_API_KEYhttps://api.tundra.ai/v1
umans_aiUmans AIUMANS_AI_API_KEYhttps://api.code.umans.ai/v1
unorouterUnoRouterUNOROUTER_API_KEYhttps://unorouter.com/en
upstageUpstageUPSTAGE_API_KEYhttps://api.upstage.ai/v1
v0v0 (Vercel)V0_API_KEYhttps://api.v0.dev/v1
veniceVeniceVENICE_API_KEYhttps://api.venice.ai/api/v1
vercelVercelVERCEL_API_KEYhttps://api.v0.dev/v1
vivgridVivgridVIVGRID_API_KEYhttps://api.vivgrid.com/v1
volc_engineVolcEngineARK_API_KEYhttps://ark.cn-beijing.volces.com/api/v3
vultrVultrVULTR_API_KEYhttps://api.vultrinference.com/v1
waferWaferWAFER_API_KEYhttps://api.wafer.ai/v1
wandbWeights & BiasesWANDB_API_KEYhttps://api.inference.wandb.ai/v1
xiaomi_token_plan_amsXiaomi Token Plan (Europe)MIMO_API_KEYhttps://token-plan-ams.xiaomimimo.com/v1
xiaomi_token_plan_cnXiaomi Token Plan (China)MIMO_API_KEYhttps://token-plan-cn.xiaomimimo.com/v1
xiaomi_token_plan_sgpXiaomi Token Plan (Singapore)MIMO_API_KEYhttps://token-plan-sgp.xiaomimimo.com/v1
xiaomimimoXiaomi MiMoXIAOMI_API_KEYhttps://mimo.xiaomi.com/v1
xpersonaXpersonaXPERSONA_API_KEYhttps://www.xpersona.co/v1
xunfeiXunfeiXUNFEI_API_PASSWORDhttps://spark-api-open.xf-yun.com/v1
zaiZaiZAI_API_KEYhttps://api.z.ai/api/paas/v4
zai_coding_planZ.AI Coding PlanZHIPU_API_KEYhttps://api.z.ai/api/anthropic
zeldocZeldocZELDOC_API_KEYhttps://api.zeldoc.ai/v1
zenmuxZenMuxZENMUX_API_KEYhttps://zenmux.ai/api/v1
zhipu_v4ZhipuV4ZHIPU_API_KEYhttps://open.bigmodel.cn/api/paas/v4
zhipuai_coding_planZhipu AI Coding PlanZHIPU_API_KEYhttps://open.bigmodel.cn/api/coding/paas/v4

Typed factories (non-registry)

These providers are not name-addressable: provider("anthropic", ...) fails with NoSuchProvider. Use the typed entry points below (Rust type names; per-binding constructors: see reference.md).

Native protocol providers

moduletyped entry points
replay—
catalogueCatalogue
anthropicAnthropicConfig / AnthropicProvider
anthropic_awsAnthropicAwsConfig / AnthropicAwsProvider
azureAzureConfig / AzureProvider
bedrockBedrockConfig / BedrockProvider
cohereCohereConfig / CohereProvider
googleGoogleConfig / GoogleProvider
mistralMistralConfig / MistralProvider
openaiOpenAIConfig / OpenAIProvider
vertexVertexConfig / VertexProvider
voyageVoyageConfig / VoyageProvider
codexCodexConfig / CodexProvider
openrouterOpenRouterConfig / OpenRouterProvider
xaiXAIConfig / XAIProvider

OpenAI-compatible thin wrappers (second batch)

moduletyped entry points
huggingfaceHuggingFaceConfig / HuggingFaceProvider
llamafileLlamafileConfig / LlamafileProvider
lmstudioLmStudioConfig / LmStudioProvider
mistralrsMistralrsConfig / MistralrsProvider
ollamaOllamaConfig / OllamaProvider

Speech-only providers (TTS)

moduletyped entry points
cartesiaCartesiaConfig / CartesiaProvider
elevenlabsElevenLabsConfig / ElevenLabsProvider
humeHumeConfig / HumeProvider
lmntLMNTConfig / LMNTProvider

Transcription-only providers (STT)

moduletyped entry points
assemblyaiAssemblyAIConfig / AssemblyAIProvider
deepgramDeepgramConfig / DeepgramProvider
falFalConfig / FalProvider
gladiaGladiaConfig / GladiaProvider
revaiRevaiConfig / RevaiProvider

Image-only providers

moduletyped entry points
black_forest_labsBlackForestLabsConfig / BlackForestLabsProvider
lumaLumaConfig / LumaProvider
prodiaProdiaConfig / ProdiaProvider
replicateReplicateConfig / ReplicateProvider

Video-only providers

moduletyped entry points
klingaiKlingAIConfig / KlingAIProvider

Generic Responses API wrapper

moduletyped entry points
open_responsesOpenResponsesConfig / OpenResponsesProvider

Bulk-generated thin-wrapper providers

moduletyped entry points
cybertronCybertronConfig / CybertronProvider
docker_model_runnerDockerModelRunnerConfig / DockerModelRunnerProvider
gaudiGaudiConfig / GaudiProvider
jlamaJlamaConfig / JlamaProvider
litellm_proxyLitellmProxyConfig / LitellmProxyProvider
llamacppLlamacppConfig / LlamacppProvider
localLocalConfig / LocalProvider
localaiLocalaiConfig / LocalaiProvider
mlxMlxConfig / MlxProvider
omlxOmlxConfig / OmlxProvider
onnxOnnxConfig / OnnxProvider
oobaboobaOobaboobaConfig / OobaboobaProvider
openvinoOpenvinoConfig / OpenvinoProvider
sglangSglangConfig / SglangProvider
vllmVllmConfig / VllmProvider
xinferenceXinferenceConfig / XinferenceProvider

Modality-specific providers (non-language, e.g. rerank-only)

moduletyped entry points
jina_aiJinaAiConfig / JinaAiProvider

AWS Polly speech (TTS) provider — SigV4 authenticated, speech modality only

moduletyped entry points
aws_pollyAwsPollyConfig / AwsPollyProvider

Recraft image provider (OpenAI Images-compatible + Recraft extension fields)

moduletyped entry points
recraftRecraftConfig / RecraftProvider

Stability image provider (image modality only)

moduletyped entry points
stabilityStabilityConfig / StabilityProvider

Video-only provider (runwayml)

moduletyped entry points
runwaymlRunwaymlConfig / RunwaymlProvider

P1 thin-wrapper providers (provider-research batch)

moduletyped entry points
bedrock_mantleBedrockMantleConfig / BedrockMantleProvider

Vertex AI MaaS partner-model providers (OpenAI-compatible thin wrappers). Each wraps the shared OpenAIProvider against the Vertex AI MaaS OpenAPI endpoint, authenticating with a Google Cloud Bearer token

moduletyped entry points
vertex_ai_ai21_modelsVertexAiAi21ModelsConfig / VertexAiAi21ModelsProvider
vertex_ai_anthropic_modelsVertexAiAnthropicModelsConfig / VertexAiAnthropicModelsProvider
vertex_ai_deepseek_modelsVertexAiDeepseekModelsConfig / VertexAiDeepseekModelsProvider
vertex_ai_llama_modelsVertexAiLlamaModelsConfig / VertexAiLlamaModelsProvider
vertex_ai_minimax_modelsVertexAiMinimaxModelsConfig / VertexAiMinimaxModelsProvider
vertex_ai_mistral_modelsVertexAiMistralModelsConfig / VertexAiMistralModelsProvider
vertex_ai_moonshot_modelsVertexAiMoonshotModelsConfig / VertexAiMoonshotModelsProvider
vertex_ai_openai_modelsVertexAiOpenaiModelsConfig / VertexAiOpenaiModelsProvider
vertex_ai_qwen_modelsVertexAiQwenModelsConfig / VertexAiQwenModelsProvider
vertex_ai_zai_modelsVertexAiZaiModelsConfig / VertexAiZaiModelsProvider

Search-only providers (web search modality)

moduletyped entry points
dataforseoDataforseoConfig / DataforseoProvider
exa_aiExaAiConfig / ExaAiProvider
firecrawlFirecrawlConfig / FirecrawlProvider
google_pseGooglePseConfig / GooglePseProvider
linkupLinkupConfig / LinkupProvider
parallel_aiParallelAiConfig / ParallelAiProvider
searxngSearxngConfig / SearxngProvider
serperSerperConfig / SerperProvider
tavilyTavilyConfig / TavilyProvider
tinyfishTinyfishConfig / TinyfishProvider
you_comYouComConfig / YouComProvider