Together AI
Together AI is an AI acceleration cloud delivering fast, scalable, and reliable generative-AI infrastructure. The Together API serves open-source and proprietary foundation models for chat, embeddings, vision, audio, image and video generation, fine-tuning, code execution, and dedicated GPU compute.
3 channels
across 1 AsyncAPI spec
· Provider profile
Channels
-
Text-to-speech (TTS). When `"stream": true` the server responds with `text/event-stream` emitting `audio.tts.chunk` events containing base64-encoded raw PCM audio. When streaming, the only supported `Together AI Streaming Inference API
-
OpenAI-compatible chat completions. Send a `POST` with `"stream": true` and a chat `messages` array. The server responds with `text/event-stream` and emits one `chat.completion.chunk` per token (or toTogether AI Streaming Inference API
-
Legacy text completions endpoint. With `"stream": true` the server returns `text/event-stream` emitting `completion.chunk` events terminated by `[DONE]`.Together AI Streaming Inference API