Reference guides for the AI apps an AI agent can work with: every endpoint, the permission each one needs, and how to give agents safe, governed access.
The Anthropic API is how an app or AI agent works with Claude: sending a conversation and getting the next message back, running large jobs as asynchronous batches, listing models, counting tokens, and uploading files to reuse across calls.
The Cohere API is how an app or AI agent works with Cohere's models: generating a chat reply, turning text or images into embeddings, reranking a list of documents against a query, or classifying text into labels.
The ElevenLabs API is how an app or AI agent works with an ElevenLabs account: turning text into spoken audio, transcribing speech back into text, managing the voices in the account, and dubbing media into other languages.
The Google Gemini API is how an app or AI agent works with Google's Gemini models: generating text and images from a prompt, turning text into embeddings for search, uploading files for a model to read, caching context to reuse, and fine-tuning a model.
The Hugging Face API is how an app or AI agent works with the Hugging Face Hub and the models on it: searching and reading models, datasets, and Spaces, creating and committing to a repository, and running a model for chat, embeddings, or image generation.
The OpenAI API is how an app or AI agent generates text and tool-using responses, turns text into embeddings, transcribes or synthesizes audio, generates images, and runs content moderation.
The Perplexity API is how an app or AI agent gets answers from the web: asking a grounded question and getting an answer with its sources, running a raw web search, or kicking off an in-depth research report.
The Replicate API is how an app or AI agent runs machine-learning models: creating a prediction to generate an image or transcribe audio, fine-tuning a model through a training, fetching a result, or listing models and deployments.
An AI API is how an app or AI agent reaches a model provider to generate text, transcribe speech, rank results, or create images and audio. The providers here, including Anthropic, OpenAI, Google Gemini, and ElevenLabs, each take a prompt in a request and return a result, so an agent can use them as its own reasoning and generation layer.
Access runs on an access key tied to a billing account, and most providers allow that key to be limited to specific projects or models and capped with a spending limit. The reach of a single key matters, because it can run up cost and, where a provider retains conversation history or uploaded files, read past inputs. A governed layer in front of each provider gives an agent a key with only the limits it needs, and records every call made with it.
Bollard AI sits between a team's AI agents and the apps it runs on. Grant each agent exactly the access it needs, read or write, app by app, and every call is checked and logged.