ModelRush
Access text, image, video, and audio models through one API
Access chat, image, and video models through one API

DeepRelay gives developers a single API for running language, image, and video models from multiple providers. Its OpenAI-compatible endpoints let existing clients connect by changing their base URL and API key, while supporting streaming responses, tool calls, structured output, and usage reporting.
Teams can use it to build assistants, generate images, or submit video generation jobs that run asynchronously and return downloadable results. The platform also offers Python and TypeScript SDKs, a command-line interface, and an MCP server for connecting coding agents. Monthly subscriptions cover selected models within published usage limits, while other models and usage beyond those limits are billed separately. A shared account brings model access and usage management together.
Tried it? Share a useful thought or ask a question.
Sign in to join the discussion.
Sign in to comment