# Model provider request

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

Also called: API request, API call, LLM call, model request, round trip, provider request

One trip from an AI product to the [model provider](https://ecosystem.samcarlton.com/model-provider) and back. The product sends everything the model should see, and gets one reply. A single task can take dozens of these behind the scenes, and each one is billed.

**For example:** A [founder](https://ecosystem.samcarlton.com/founder) asks a [coding agent](https://ecosystem.samcarlton.com/coding-agent) to fix one [bug](https://ecosystem.samcarlton.com/bug), and the [agent](https://ecosystem.samcarlton.com/ai-agent) quietly makes 30 model provider requests while it reads files, edits code and reruns the tests.

## Connects to (8)

- [Model provider](https://ecosystem.samcarlton.com/model-provider): The company or service that runs an AI model and answers requests to it, usually over the internet through an API.
- [Inference](https://ecosystem.samcarlton.com/inference): An AI model producing an answer to a request.
- [Input tokens](https://ecosystem.samcarlton.com/input-tokens): The tokens an AI product sends to the model on each request: the instructions, the conversation so far, files and tool results.
- [Output tokens](https://ecosystem.samcarlton.com/output-tokens): The tokens the model writes back.
- [Harness](https://ecosystem.samcarlton.com/harness): The software wrapped around an AI model that turns it into a working agent.
- [Turn](https://ecosystem.samcarlton.com/turn): One round of a conversation with an agent: you send a message, and the agent works until it hands control back to you.
- [Stateless](https://ecosystem.samcarlton.com/stateless): Describes something that keeps nothing between uses.
- [Prefix cache](https://ecosystem.samcarlton.com/prefix-cache): A provider feature that remembers the opening of a request it has just handled.

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