established · 1.5 capabilitymarket

Inference

Score 29.7 / 100 149 providers 80 APIs Search apis.io →

Variants seen in the corpus: Inferenceinference

Providers using this tag (149)

Ranked by API Evangelist rating — Exemplar and Strong are expanded by default.

Exemplar 2 Complete, well-documented, and agent-ready

NVIDIA NIMArtificial IntelligenceMicroservicesLLM11 APIs71.2 falArtificial IntelligenceGenerative AIGenerative MediaImage-Generation12 APIs69.7

Strong 18 Solid coverage with minor gaps

Developing 43 Usable, with meaningful gaps to close

Thin 55 Limited public surface area

Emerging 18 Early or largely undocumented

Minimal 13 Almost no public developer surface

APIs with this tag (77)

Ranked by the provider's API Evangelist rating — the Kin Score is scored per provider, not per API, so every API of a provider shares its band. How the rating works →

Exemplar 2 Complete, well-documented, and agent-ready

fal Realtime APIWebSocket-based realtime inference for ultra-low latency interactive generative experiences such as LCM/SDX...69.7 fal Streaming APIHTTP streaming endpoint (`/{model-id}/stream`) that emits progressive partial outputs as a model runs — use...69.7

Strong 12 Solid coverage with minor gaps

Autoderm – AI Dermatology API Inference APIThe inference API from Autoderm – AI Dermatology API — 5 operation(s) for inference.66.2 Amazon SageMaker Runtime APIThe Amazon SageMaker AI runtime API for invoking deployed model endpoints to get real-time inference predic...65.0 Swiss AI Platform Inference Endpoints APIOpenAI-compatible inference endpoints for chat, multimodal, audio, embedding, reasoning and guardrail model...63.8 Viam Inference APICloud-hosted inference against registry-deployed models.61.6 Compresr Inference APIThe Inference API from Compresr — 1 operation(s) for inference.61.4 Seekr Inference APIThe Inference API from Seekr — 12 operation(s) for inference.61.3 Crusoe Managed Inference APIOpenAI-compatible inference API from the Crusoe Intelligence Foundry. Send chat/completions and embeddings ...60.6 Paperspace Deployments APIContainer-as-a-service deployments that run user-provided images on Paperspace GPU machines with a managed ...60.2 Model Serving Endpoints APICreate and manage model serving endpoints for deploying machine learning models as REST API endpoints.56.5 Amazon Bedrock Inference APIOperations for invoking models and running inference.56.4 Prime Intellect Inference APIOpenAI-compatible inference API for hosted frontier and open models served at api.pinference.ai. Supports s...55.1 Pinecone Inference APIModel inference54.6

Developing 18 Usable, with meaningful gaps to close

Inference.net APIOpenAI-compatible inference API for open-source, frontier, and custom language models — chat completions, b...53.9 RunPod ServerlessRunPod Serverless provides pay-as-you-go inference endpoints with autoscaling workers, queue-based and load...52.2 Fastino Labs inference APIPioneer-native inference endpoint (encoder NER/classification/extraction and decoder text generation).51.5 0G Labs Inference APIThe Inference API from 0G Labs — 11 operation(s) for inference.51.2 Lambda Inference APILambda Inference API is an OpenAI-compatible REST gateway at https://api.lambda.ai/v1 that serves hosted op...50.9 OpenRelay Inference APIOpenAI-compatible chat completions API (POST /v1/chat/completions) and, for supporting models, an Anthropic...50.8 Openwork Inference APIThe Inference API from Openwork — 1 operation(s) for inference.49.7 Hugging Face Inference APIServerless inference API for running predictions against thousands of models hosted on the Hugging Face Hub...45.3 Sahara AI Inference APIOpenAI-compatible chat completion inference.45.2 CoreWeave Inference APIThe CoreWeave Inference API manages Deployments, Gateways, and Capacity Claims for serverless and dedicated...44.2 BentoML Service REST APIAuto-generated REST API endpoints produced when BentoML services are deployed. Each decorated service metho...44.1 AI21 Batch APIAsynchronous batch processing for large volumes of Jamba completions. Submit a batch job, poll for status, ...43.9 Cerebras Inference APIThe Cerebras Inference API exposes ultra-low-latency inference for open-weight large language models includ...42.0 Runware Inference APISingle task-based endpoint for image, video, audio, 3D, and text inference across 400K+ models, reachable o...41.0 Amazon Nova Inference APISynchronous and streaming inference operations.40.4 Ollama Cloud APIOllama Cloud provides cloud-hosted inference for large language models, giving access to larger models and ...40.4 AkashML Inference APIOpenAI-compatible AI inference API providing access to open-source LLMs hosted on decentralized compute acr...39.9 Predibase Inference APIThe Inference API from Predibase — 4 operation(s) for inference.39.9

Thin 36 Limited public surface area

SambaCloud APIThe SambaCloud API exposes OpenAI-compatible chat completions over SambaNova's RDU-accelerated infrastructu...38.9 Inferless Inference APIThe Inference API from Inferless — 1 operation(s) for inference.38.6 Seldon Inference APIThe Seldon Inference API provides REST and gRPC endpoints for serving machine learning model predictions at...38.6 Azure OpenAI Inference REST APIData-plane REST API for running inference against deployed Azure OpenAI models, including chat completions,...38.5 TensorFlow Inference APIModel inference operations including classify, regress, and predict38.2 Cerebrium Inference APIThe Inference API from Cerebrium — 1 operation(s) for inference.38.0 BentoML REST APIBentoML is an open-source unified inference platform for deploying and scaling AI models. It auto-generates...37.5 NVIDIA Triton Inference Server HTTP APINVIDIA Triton Inference Server is an open-source inference serving software that implements the KServe Open...37.5 Ray Serve REST APIRay Serve is a scalable model serving library built on Ray, designed for building online inference APIs. Su...37.5 Scalable Inference Serving Inference APIModel inference request endpoints37.5 vLLM OpenAI-Compatible APIvLLM is a high-throughput and memory-efficient inference engine for LLMs, implementing PagedAttention for e...37.5 Gcore Inference APIEverywhere Inference edge AI model deployments.37.2 W&B Serverless Inference (CoreWeave)OpenAI-compatible inference API for hosted open-source foundation models, running on CoreWeave GPU infrastr...36.7 Lamini Inference APIText completion and streaming generation endpoints.35.3 Taalas APITaalas-native REST interface for running inference against the HC1 hardcore-model silicon. Three operations...34.3 MAX Inference REST APIOpenAI-compatible inference API served by MAX. Exposes /v1/chat/completions, /v1/completions, /v1/embedding...34.0 Poolside APIOpenAI-compatible inference API for poolside's Laguna agentic-coding models. Send chat-completion and model...33.7 EigenAIEigenAI exposes deterministic, verifiable LLM inference over an OpenAI-compatible API surface, with executi...33.5 Triton GRPC APIHigh-performance gRPC API for model inference with support for streaming and binary tensor data.33.1 Triton Inference Server Inference APIModel inference requests33.1 Tinker APIManaged training/fine-tuning and sampling API for open-weight language models, consumed through the officia...33.0 Inworld LLM Router APIRouting layer over 220+ LLM models, billed at provider cost via Inworld's unified API.31.9 AnyscaleAnyscale is the production-scale AI platform built on Ray by the creators of Ray, supporting LLM inference ...31.8 NVIDIA NIMNVIDIA NIM is a set of inference microservices for streamlined AI model deployment, prebuilt and optimized ...31.8 Together AITogether AI is a full-stack AI Native Cloud for inference, fine-tuning, and GPU clusters powered by researc...31.8 Ember APIHosted mechanistic-interpretability API. OpenAI-compatible chat-completions sampling plus feature discovery...31.4 SAP AI Core APIREST API for SAP AI Core, enabling training, deployment, and inference of AI and machine learning models wi...30.9 Modelbit Deployment REST APIEvery Modelbit deployment is exposed as a versioned REST inference endpoint. POST an inference request (sin...29.7 Mango LLMBoost Inference Server APILLMBoost is MangoBoost's enterprise LLM inference server. It serves the OpenAI REST API on /v1 so an existi...29.6 KServe Inference APIKServe's standardized model inference protocol for serving predictions across multiple ML frameworks on Kub...29.4 Lattica Platform APIThe LatticaAI platform API for deploying and operating encrypted workloads. An RPC-style HTTPS surface root...27.9 Lightning AI Model APIsHosted inference API that serves frontier and open models behind a Lightning API key, billed per token with...27.2 Chariot Platform APIPer-tenant REST API for the Chariot AI operations platform, organized as versioned microservice paths under...27.0 Anyscale Services APIDeploys and manages production Ray Serve applications as long-running, autoscaling, multi-version services ...26.9 Aster Inference APIOpenAI-compatible inference API from Aster serving open-weight models (gpt-oss-120b, gpt-oss-120b-fast, GLM...26.5 KAITO RAGEngine APIRAGEngine exposes endpoints for managing retrieval-augmented generation services with embedded vector datab...26.3

Emerging 8 Early or largely undocumented

IO Intelligence APIOpenAI-compatible inference API for open-source AI models hosted on io.net's decentralized GPU network. Exp...26.1 Cumulus Inference GatewayOpenAI-compatible HTTP inference gateway. One client works against every upstream provider; per-workflow ro...25.8 Nebius Token FactoryNebius Token Factory is the AI model inference platform offering OpenAI-compatible endpoints for serving op...25.6 PhariaInference APIThe PhariaInference HTTP API provides access to Aleph Alpha's specialized language models for text completi...25.3 Segmind Inference APISynchronous and asynchronous model inference25.3 Ray Serve HTTP APIHTTP interface for invoking models and applications deployed via Ray Serve. Each deployed application is ex...21.6 Mirai uzu Inference SDKuzu is Mirai's first-party, high-performance on-device inference engine. A single high-level API — shared a...19.0 Infini-AI GenStudio Large-Model Service (MaaS)OpenAI-compatible model-inference API over Infini-AI's catalog of open- and closed-source models. Bearer (A...12.4

Minimal 1 Almost no public developer surface

OctoStackOctoStack was OctoAI's self-contained generative-AI production stack for deploying open and customer-traine...8.2

Score breakdown

Frequency

64.2

log-scaled weighted occurrences

Breadth

4.1

spread across providers

Quality lift

43.8

mean composite of providers using it

Cohesion

25.7

strength of nearest seed neighbor

Where this tag comes from

Provider tag116

Api tag79

Openapi tag20

Openapi op tag60

Cohort brief

Auto-generated

The 149 providers in the APIs.io catalog tagged Inference, scored on the Kin Score. Every figure below is computed from the catalog — nothing here is written.

Providers

149

all scored

Mean Kin Score

36.3

+15.6 vs catalog 20.7

Mean Agent Readiness

20.2

+10.5 vs catalog 9.7

Spread

5–71.2

median 37.2 · σ 15.6

How the 149 split by band

Exemplar 2Strong 18Developing 43Thin 55Emerging 18Minimal 13

Facet averages, against the whole catalog

Facet	This cohort	Catalog	Difference	Scored
Contract Quality	40.1	17.5	+22.6	149
Developer Ergonomics	40.1	17.9	+22.2	149
Operational Transparency	23.4	11.3	+12.1	149
Discoverability	72.1	60.4	+11.7	149
Access Clarity	32.4	22.3	+10.1	149
Contract Governance	11.1	6.4	+4.7	149

A facet is averaged over the members that carry it, not over the whole cohort — the “Scored” column is that count. Averaging an absent facet as zero would score our own coverage gaps as the providers’ posture.

What this cohort publishes

Artifact	This cohort	Catalog	Difference
MCP server (any)	30%	16%	+14
MCP server (first-party)	13%	7%	+6
Agent Skills	0%	0%	0
OAuth scopes	5%	9%	-4
Security	96%	88%	+8
Arazzo workflows	6%	2%	+4
Governance rules	26%	13%	+13

mcp_pct counts any mcp/ artifact including ones API Evangelist derived from the provider OpenAPI; mcp_first_party_pct counts only servers the provider publishes. Prefer the latter.

Top by Kin Score

1 NVIDIA NIM 71.2
2 fal 69.7
3 Autoderm – AI Dermatology API 66.2
4 Modal 65.1
5 Amazon SageMaker 65
6 Hyperbolic 64.7
7 Cerebras Systems 63.8
8 Swisscom 63.8
9 Viam 61.6
10 Compresr 61.4

Work with this as data

Every tag here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for tags

7 MCP tools reach this

find_tagsBrowse and filter every tag in the catalog.
get_cohortThis tag as a scored cohort — every provider carrying it, with scores.
cohort_statsPRO — the distribution across this tag: mean, median, band split, adoption rates.
cohort_rankingsPRO — the leaderboard, on composite AND agent-readiness axes.
apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
resolveTurn a domain, URL or GitHub org into the provider it belongs to.
find_cohortsEvery scored population of providers in the catalog.

All 92 tools

Call it yourself

curl for this page

This tag

curl "https://apis.io/api/v1/tags/inference"

All tags

curl "https://apis.io/api/v1/tags?limit=25"

As a scored cohort

curl "https://apis.io/api/v1/cohorts/tag/inference"

The distribution (Pro)

curl "https://apis.io/api/v1/cohorts/tag/inference/stats" \
  -H "X-API-Key: $APIS_IO_KEY"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no email required.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.