Short answer
No. Every AI Factory model has an OpenAI-compatible API, so an app built on an OpenAI SDK only needs a new base URL and API key.
In detail: Using AI Factory GPUs without a rewrite
You point any OpenAI SDK at https://api.firstcore.ai/v1 and call the standard endpoints:
- /chat/completions for chat, agents and coding
- /embeddings for search and retrieval
- /audio/transcriptions for speech to text
- /rerank for retrieval reranking
An Anthropic-compatible API is also available if your tools use that format instead. Every key carries its own limits and spend cap, and you see usage and spend per key as it happens.
For an application already built on an OpenAI SDK, moving to AI Factory is a configuration change rather than a rebuild. The difference is where it runs: inference happens in FirstNet's Durban data centre on dedicated or fractional GPU capacity, billed in rand. A time-boxed trial key is the easiest way to test it with your own code.