Model Components
API (Application Programming Interface)
An API defines a set of protocols, endpoints, and data formats through which external code can access a service's functionality. AI APIs (OpenAI, Anthropic, Google) allow developers to send prompts and receive completions from frontier models without deploying or managing the models themselves.
AI APIs have democratized access to powerful models, enabling startups to build AI-powered products without the infrastructure costs of training and serving models. Rate limits, pricing per token, latency, and reliability are key considerations when choosing an AI API.
Authority Links
Related Terms
Model Components
Large Language Model (LLM)
A transformer-based neural network with billions to trillions of parameters, trained on broad text corpora to predict the next token and able to generate, summarize, classify, and reason over natural language.
Techniques & Methods
Inference
Using a trained AI model to generate predictions or responses on new, unseen data.
Miscellaneous
Deployment
The process of making a trained AI model available for real-world use in production environments.
Model Components
Maximum Response Length
The upper limit on the number of tokens a model can generate in a single response.