AI Model Services › Model Inference

Model Inference

AE-110.10 Level 2 API Evangelist extension API Evangelist extension, CC BY-NC-SA 124 providers 251 API surfaces 70 rated strong or better

Serving model calls on demand.

Model Inference (AE-110.10) is a level-2 business capability under AI Model Services in the API Evangelist extension model. The catalog holds 251 API surface(s) from 124 provider(s) that can perform some part of it, 70 of them rated strong or better. Reach is the vendor surface that lands on this capability — it is not a claim about what any particular organisation has deployed.

Where this capability definition comes from. This capability is part of the API Evangelist extension to the business-capability model, written by API Evangelist and licensed CC BY-NC-SA 4.0. API Evangelist capability extension — https://apievangelist.com Audience: b2bagent It extends, and never modifies, Turbo EA Capabilities by Vincent Verdet (CC BY 4.0). · Extension provenance and licence

Sub-capabilities

Hosted LLM Inference AE-110.10.10API Evangelist extension, CC BY-NC-SA

b2bagent

Text generation behind an API.

no catalog coverage

OpenAI-Compatible Endpoints AE-110.10.20API Evangelist extension, CC BY-NC-SA

b2bagent

Inference behind the de facto chat-completions interface.

no catalog coverage

Model Routing & Gateways AE-110.10.30API Evangelist extension, CC BY-NC-SA

b2bagent

Choosing between models and providers per request.

no catalog coverage

On-Device & Edge Inference AE-110.10.40API Evangelist extension, CC BY-NC-SA

consumerb2b

Running models on phones, devices and the edge.

no catalog coverage

Providers that reach this capability

Ordered by rating band. Reach means a provider publishes an API surface that can perform some part of this capability — it is not a claim that any particular organisation has deployed it.

Exemplar 26 Complete, well-documented, and agent-ready

TelnyxAnthropic MessagesChatDecision ModelsOpenAI Chat4 APIs87.6 AnthropicCompleteMessages2 APIs85.7 OpenAIChat CompletionsCompletions2 APIs82.6 Treasure DataChat1 API74.6 ClarivatePrediction1 API73.0 ForceDreamOracle1 API72.8 OctenChat CompletionsMessages2 APIs72.8 Hive Civilizationarb-computekimi2 APIs72.7 BenchlingPredictionBatch1 API72.4 SpicyAPIOpenAI CompatibleTasks2 APIs72.0 ParallelChat API (Beta)Responses API2 APIs71.3 AxonFlowOpenAI Compatible1 API70.2 Amazon SageMakeramazon-sagemaker-inference-component-api1 API70.1 Mergesubpackage_responses1 API69.1 Elastic Stackobservability_ai_assistant1 API68.8 EmporixAI Completions1 API68.8 EmpirioLabs AICompletionsMessagesModelsResponses6 APIs68.7 Hugging FaceChat Completions1 API67.9 IBMMessagesText Generation2 APIs67.6 Eden AIAnthropic MessagesChatDecisions3 APIs67.5 NexGen CloudConversations1 API67.5 Kimi (Moonshot AI)BatchChat CompletionsMessagesResponses4 APIs66.9 LangdockChat CompletionsFIMGoogleMessages5 APIs66.8 falStreaming1 API66.7 Microsoft AzureChat CompletionsMultiSlotRank2 APIs66.7 ElasticInference1 API66.5

Strong 44 Solid coverage with minor gaps

Amazon Qamazon-q-conversations-api1 API66.0 AIMLAPIChat CompletionsMessagesResponsesThreads > Runs4 APIs65.3 Opper AICompatibilityModels2 APIs65.3 Live Direct MarketingAI1 API64.8 VercelChat Completions1 API64.5 Scale AIAsync TasksBatch CompletionsBetaChat Completions14 APIs64.4 MicrosoftChat CompletionsCompletions2 APIs64.2 Infer by Flow7Chat CompletionsMessages2 APIs63.8 Amazon Personalizeamazon-personalize-batch-inference-job-apiamazon-personalize-campaign-apiamazon-personalize-recommender-api3 APIs63.6 SAKURA internetChatMessagesResponses3 APIs63.6 CometChat Completions1 API63.5 FastlyChat Completions1 API63.5 Red Hat Ansible Automation PlatformAI1 API63.4 Cerebras SystemsChat CompletionsCompletions2 APIs62.8 Amazon Lookout for Equipmentamazon-lookout-for-equipment-inference-scheduler-api1 API62.6 Dedalus LabsChat CompletionsResponses2 APIs62.6 CoastyPredict1 API62.5 FriendliAIServerless.Model1 API62.5 RightNow AIChat CompletionsResponses2 APIs62.4 NVIDIA NIMBiology1 API61.5 Coin RailzAI Services1 API61.4 HUDCompletions1 API61.4 EdgeeChat CompletionsMessagesResponses3 APIs61.0 PerplexityAsyncSonar2 APIs60.8 GumloopChat Completions1 API60.4 brick.blueModels1 API60.3 Sail ResearchModels API1 API59.2 Altimate AIAgentsChat Completions2 APIs57.9 CONNSKILLEU-LLM1 API57.9 SarvamChat Completions1 API57.6 HyperbolicChat CompletionsCompletions2 APIs57.5 PortkeyChat CompletionsCompletions2 APIs57.5 gpt55-token-gatewayChat CompletionsResponsesgpt55-model-gateway3 APIs57.3 H2O.aiChat1 API56.8 Fastino Labsopenai-compat1 API56.6 AkkioInference1 API56.4 Venice.aiChat CompletionsResponses2 APIs56.2 RouterPlexChat CompletionsMessagesResponses3 APIs56.1 AppDirectAI ModelsChat CompletionsChat SessionsResponses API v24 APIs55.9 Arcade.devLLM1 API55.6 Microsoft CopilotChat1 API55.6 InterfazeChat Completions1 API55.1 TypeSafe AISystemone1 API55.1 OpenRouterChat CompletionsCompletions2 APIs55.0

Developing 38 Usable, with meaningful gaps to close

TaleModel endpointsThreads2 APIs53.9 DiscountedTokens APIMessagesModelsResponses3 APIs53.6 Novita AIOpenai1 API53.2 FastrouterChat CompletionsGetAsyncResponseModelResponses4 APIs53.1 Multiverse ComputingCompletions1 API53.0 SolvelaModels1 API53.0 Mistral AIChat CompletionsFIM2 APIs52.7 AIHubMixAnthropic CompatibleGoogle Vertex AI Compatible2 APIs52.6 TextcortexResponses1 API51.7 Blazing Bullet Private LimitedCompletionsResponsesgoogle genai endpoints3 APIs51.6 NixtlaAnomaly DetectionForecastOnline Anomaly Detection3 APIs51.2 InceptionEdit1 API51.0 Agent ExchangeLLM1 API50.9 Arcee AICompletions1 API50.2 LettaChat Completions1 API49.9 APIClawAnthropic Pass-throughAssistantsAzure AI Pass-throughAzure Pass-through21 APIs49.5 Standard ComputeChat CompletionsCompletionsMessagesModels5 APIs49.2 MixedbreadCompletions1 API49.1 0G LabsInference1 API48.8 PryonGenerative1 API46.9 ParasailCompletions1 API46.6 Aleph AlphaResponses1 API46.3 MartianChat CompletionsMessages2 APIs45.7 OpikChat Completions1 API45.5 ProbablAnthropic Compatible AgentOpenAI Compatible Agent2 APIs45.1 Qubrid AIModels1 API45.1 Contextual AIGenerate1 API44.4 Understudy LabsConversations1 API44.4 DeepSeekChat CompletionsCompletions2 APIs44.3 Azure OpenAI ServiceCompletions1 API44.0 FuriosaAIModels1 API43.7 GistChat1 API43.3 Sahara AIDiscovery1 API42.8 QuantCDNAI Models1 API42.6 UnifyAgent1 API41.9 AI21 LabsMaestro1 API41.2 Vellum AIExecute Prompt StreamExecute WorkflowExecute Workflow AsyncExecute Workflow Stream4 APIs41.0 LangChainPrompts1 API40.8

Thin 14 Limited public surface area

Anomaly DetectionChangePoint1 API39.0 CohereChat1 API38.3 EnvoyText Completions1 API38.1 LangflowOpenAI Responses API1 API38.0 Sber ID / SberCloudChat CompletionsModels2 APIs36.5 University of AmsterdamAnthropic Pass-throughChat CompletionsCompletionsGoogle AI Studio Pass-through11 APIs36.4 Jina AIGenerative Models1 API35.3 Together AIChat CompletionsCompletionEndpoints3 APIs34.8 RekaChat Completions1 API34.6 MarqoModels1 API33.8 xAIChatCompleteCompletionsMessages5 APIs33.7 Keywords AIGateway1 API33.0 BasetenMessagesNon-RegionalRegional3 APIs32.7 Haystack / deepsetDeployments1 API30.1

Emerging 2 Early or largely undocumented

CablesTools1 API23.9 SageoxLLM1 API16.5

This page carries no rating. Capabilities are not rated. A capability is a description of what a business does, not a thing a company publishes, so a Kin Score would have nothing to measure.

The edge table is a Pro feature. This page shows which providers and tags reach Model Inference. The underlying tag → capability edges — each with the quoted fragment of the provider's own OpenAPI that evidences it, a calibrated confidence score, and the contract-provenance gate it passed — are available through the API, along with company-level capability maps. Only edges at confidence ≥ 0.7 with evidence found verbatim in the source contract are published at all.

See plans → · How the edges are graded →