OpenAI
NativeAI · OpenAI · Website ↗
Access OpenAI's language models including GPT-4o, GPT-4o-mini, o1, and o1-mini. Use for text generation, reasoning, vision, and function calling via the Assistants API.
4 tools your agents can use
openai_chat
Send a chat completion request to OpenAI. Use for general text generation, Q&A, summarisation, translation, and reasoning tasks. Always prefer this tool over answering from trainin...
openai_vision
Analyse images using OpenAI's vision model (GPT-4o). Use to describe, extract text from, or answer questions about images.
openai_embeddings
Generate vector embeddings for text using OpenAI's embedding models. Use for semantic search, similarity comparison, or as input to vector databases.
openai_audio_transcribe
Transcribe audio to text using OpenAI's Whisper model. Supports MP3, WAV, M4A, FLAC, and other common audio formats.
Governed by default
Like every connector, OpenAI runs inside the ApiSpi governance layer: admins can set it to full, read-only, or approval-required access, every call is audit-logged and firewall-screened, and spend caps apply.