Anthropic-compatible API 3

Unified low-cost API access to pooled AI subscription quotas Wokey is an AI subscription group-buying and API aggregation platform. It combines unused quotas from services such as Claude, ChatGPT, Kimi, DeepSeek, Grok, and other AI providers into a unified API service. Developers can use one API key and compatible OpenAI Chat Completions or Anthropic Messages protocols to access multiple models at usage-based prices, with advertised savings of up to 90% compared with official pricing. Wokey also provides image and video generation services, provider earnings through shared subscription capacity, intelligent routing, quota isolation, and cryptographic verification based on AWS Nitro attestation.

Unified pay-as-you-go API for leading AI models reAPI is a pay-as-you-go AI API aggregator that provides one unified endpoint and API key for accessing more than 100 image, video, language, music, audio, and code models. It routes requests across vendors based on health, latency, and load, provides automatic failover, preserves familiar SDK request formats, and charges users through prepaid credits. Supported models include GPT Image 2.5, GPT Image 2, Seedance, Seedream, Nano Banana, Claude, Kimi, GLM, Suno, and many others.

Native macOS server for fast local AI model inference oMLX is a native macOS inference server for running local AI models on Apple Silicon using Apple's MLX framework. It provides paged SSD KV caching to reduce time-to-first-token for coding agents, continuous batching for higher throughput, and OpenAI- and Anthropic-compatible APIs. oMLX supports LLM, vision-language, embedding, and reranker models, along with tool calling, MCP integration, multi-model serving, and a native menu bar application with a web dashboard.