Azure AI Foundry Models / OpenAI
Catalog of OpenAI and open models with enterprise governance and Azure AI Inference APIs.
Sorting
Fireworks AI
High-throughput inference and fine-tuning for open models; global, scalable endpoints.
NVIDIA NIM
Prebuilt, optimized inference microservices for leading models on any NVIDIA-accelerated stack.
OpenRouter
One API that routes to hundreds of models with pricing, latency, and fallback controls.
Anthropic Claude API
Production API for Claude models with tools like web search and enterprise controls.
Replicate
Run and deploy community and custom models with a simple cloud API and playgrounds.
Mistral AI — La Plateforme
High-performance chat/embedding APIs and Studio; OpenAI-compatible endpoints.
Cerebras Inference
Wafer-scale engine cloud with OpenAI-style APIs for ultra-fast open-model inference.
Cohere Platform
Enterprise LLMs for chat, embeddings, rerank, and tools—private and secure by design.
SambaNova Cloud
RDU-accelerated inference platform with OpenAI-compatible API keys for top open models.
xAI API (Grok)
Grok models via OpenAI-compatible API; advanced reasoning, coding, and vision.
Anyscale Endpoints (Ray Serve)
OpenAI-compatible serving on Ray with autoscaling and many-model deployments.
IBM watsonx.ai
Business-ready foundation models and Model Gateway with governance and pricing controls.
Baseten
Production inference platform—dedicated deployments, autoscaling, and GPU options.
Databricks Mosaic AI Model Serving
Serve custom and foundation models as REST endpoints with AI Gateway governance.