Xinference
Xinference is an enterprise AI inference platform for teams that want to run open models without building the serving stack themselves. Most teams start on the Model API: 300+ open models behind one OpenAI-compatible endpoint hosted in Australia. Switching from an existing provider takes two lines of code. As usage grows, the same workloads move to Dedicated Inference on reserved GPUs, or to a private deployment inside the customer's own cloud or data centre. Every deployment includes one control plane: per-request logs, live TTFT and TPOT monitoring, role-based access control, audit logs and SSO. Xinference does not train on customer data and does not retain it by default. Common workloads include enterprise RAG, customer assistants, agents and function calling, coding assistance, document extraction, speech and image generation.
Learn more
APIFree
APIFree is a unified AI Model-as-a-Service platform that provides developers and enterprises with seamless access to multiple leading AI models through a single standardized API layer. It aggregates mainstream open-source and proprietary models across text, image, video, audio, and code, allowing teams to integrate multimodal AI capabilities without managing separate vendor accounts, SDKs, or billing systems. Built to reduce infrastructure complexity, APIFree offers an OpenAI-compatible endpoint so applications can connect quickly while maintaining flexibility to switch between providers as needed. It emphasizes broad model coverage, lower end-to-end latency, and high availability, enabling organizations to focus on product innovation rather than platform fragmentation. With unified authentication, quota management, usage analytics, and cost controls at the platform level, APIFree simplifies AI deployment workflows and improves operational efficiency.
Learn more
RouterBase
RouterBase is a unified API gateway that gives developers and teams access to 200+ AI models, including GPT, Claude, Gemini, Llama, Mistral and DeepSeek, through a single OpenAI-compatible endpoint. Instead of maintaining separate keys and billing for each provider, you switch models with one line of configuration. RouterBase adds smart routing, automatic failover across providers, and unified billing, so your application keeps running even when an upstream provider has an outage. A free tier is available with no credit card required.
Learn more
Meta Model API
Meta Model API is a new developer API for building with Muse Spark 1.1, Meta’s multimodal reasoning model built for agentic tasks, coding, tool use, computer use, and multimodal understanding. Now in public preview, it gives developers a way to access Muse Spark 1.1 through an OpenAI-compatible package, making it easier to point existing clients at the API, keep the same code structure, and set the model to muse-spark-1.1. Muse Spark 1.1 is designed for personal agentic tasks that require planning and orchestration across external apps and services, with the ability to generalize to new native tools, MCP servers, and custom skills. As a main agent, it can gather context, make a plan, and delegate execution across parallel subagents; as a subagent, it follows its role, understands available tools, and knows when to escalate back. The model can actively manage a 1 million-token context window, remember actions, retrieve information from much earlier work, and compact context.
Learn more
