Your AI SaaS business, ready by this week!
Try demoYour AI SaaS business, ready by this week!
Try demoAn LLM (large language model) is an AI model trained on very large amounts of text to predict the next token, which lets it write, summarise, translate, reason and hold a conversation.
An LLM reads text as tokens and, one token at a time, predicts what should come next. Trained on enough text, that simple objective produces models that can follow instructions, write code and answer questions.
Well-known LLM families include OpenAI GPT, Anthropic Claude, Google Gemini, xAI Grok, Mistral, DeepSeek and Llama. They differ in quality, speed, context window and price per token.
Most AI products do not train their own LLM. They call one or more models through an API and add the interface, the workflow and the billing around them.
Aikeedo connects to many LLM providers at once, including OpenAI, Anthropic, Google, xAI, OpenRouter and local models through Ollama. You choose which models each plan can use and what each costs in credits.
Discover more terms connected to this one
Tokens are the small pieces of text an AI model reads and writes, roughly four characters or three quarters of an English word each, and the unit most AI providers bill by.
The context window is the maximum number of tokens a model can take into account at once, covering the instructions, the conversation, any attached documents and its own answer.
A foundation model is a large model trained on broad data that can be adapted to many tasks, such as GPT, Claude, Gemini or Llama, as opposed to a model built for one job.