Inference Engines & InfraFreemium
OrcaRouter
OrcaRouter sits in front of your existing SDK as a single OpenAI-compatible endpoint, grades each incoming prompt, and routes it to…
VerifiedFreemium
View OrcaRouterCategory
Model Hosting APIs
Hosted inference APIs (Replicate, Together, Fireworks).
Inference Engines & InfraFreemium
Foresight by Lightning Rod
The product is a forecasting API — you send a question, it returns a calibrated probability. The public Foresight Models are trained on…
VerifiedFreemium
View Foresight by Lightning Rod
Inference Engines & InfraFreemium
Oxlo.ai
Oxlo.ai is an inference hosting service offering an OpenAI-compatible API across 45+ open-source models, from DeepSeek R1 671B and Kimi…
VerifiedFreemium
View Oxlo.ai
Inference Engines & InfraFreemium
TokenOps by Lovie
TokenOPS is a unified API gateway that routes calls to Google Gemini, OpenAI GPT-4, Anthropic Claude 4, and xAI Grok-4 through one…
VerifiedFreemium
View TokenOps by Lovie
Inference Engines & InfraPaid
RunAPI
RunAPI is a unified inference API that routes requests across image, video, audio, and text generation models through a single endpoint and…
Verified
View RunAPI
Inference Engines & InfraFreemium
Apertis
Apertis functions as an API gateway layer that sits between your coding agents — Cursor, Cline, Claude Code and the like — and the…
VerifiedFreemium
View Apertis
Inference Engines & InfraPaid
APIDot
The platform routes requests to multiple underlying AI models for image and video generation, handling the vendor-side complexity so your…
Verified
View APIDot
Inference Engines & InfraPaid
APIMart
APIMart is a paid API gateway that routes requests to 500-plus models — including chat, image, video, and audio — through one…
Verified
View APIMart
Inference Engines & InfraFreemium
PromptUnit
AI proxy that automatically routes requests to cheaper models while maintaining quality.
VerifiedFreemium
View PromptUnit
Inference Engines & InfraFree
Xinference
Open-source library for unified deployment and serving of language, speech, and multimodal models across diverse hardware and…
VerifiedOSS
View Xinference