# Model provider

Concept · [Building with AI](https://ecosystem.samcarlton.com/ai)

Also called: AI provider, LLM provider, model vendor, inference provider, model API, AI vendor

The company or service that runs an [AI model](https://ecosystem.samcarlton.com/model) and answers requests to it, usually over the internet through an [API](https://ecosystem.samcarlton.com/terms/api). [Anthropic](https://ecosystem.samcarlton.com/claude), [OpenAI](https://ecosystem.samcarlton.com/chatgpt) and [Google](https://ecosystem.samcarlton.com/google) are examples, and a model can also run on your own machine. Your provider sets the price per [token](https://ecosystem.samcarlton.com/token), the [rate limits](https://ecosystem.samcarlton.com/rate-limit) and the data terms you agree to.

**For example:** A startup sends its users' questions to a model provider and pays a monthly bill based on how many [tokens](https://ecosystem.samcarlton.com/token) went [back and forth](https://ecosystem.samcarlton.com/turn).

## Connects to (11)

- [Model](https://ecosystem.samcarlton.com/model): The trained system at the center of an AI product.
- [Inference](https://ecosystem.samcarlton.com/inference): An AI model producing an answer to a request.
- [API](https://ecosystem.samcarlton.com/terms/api): Application programming interface.
- [Model provider request](https://ecosystem.samcarlton.com/model-provider-request): One trip from an AI product to the model provider and back.
- [Rate limit](https://ecosystem.samcarlton.com/rate-limit): A cap on how many requests or tokens an account can send to an API in a set period.
- [Local model](https://ecosystem.samcarlton.com/local-model): A model that is downloaded and run on a person's own computer or a company's own servers, not on a provider's.
- [Data privacy](https://ecosystem.samcarlton.com/data-privacy): How a company collects, uses, stores and shares information about people.
- [Token](https://ecosystem.samcarlton.com/token): In AI, a small chunk of text, roughly a word or a piece of a word, that an LLM reads and writes.
- [Frontier model](https://ecosystem.samcarlton.com/frontier-model): One of the most capable general-purpose AI models available at a given time.
- [Prefix cache](https://ecosystem.samcarlton.com/prefix-cache): A provider feature that remembers the opening of a request it has just handled.
- [Cache tokens](https://ecosystem.samcarlton.com/cache-tokens): Input tokens the provider did not need to process again because they matched the start of a recent request in its cache.

Map view: https://ecosystem.samcarlton.com/model-provider