Together AI
10 3What is TogetherAI ?
Together AI is a research-driven artificial intelligence company. They contribute leading open-source research, models, and datasets to advance the frontier of AI.
TogetherAI API Features
-
Run leading open-source models like Llama-2 on the fastest inference stack available, up to 3x faster1 than TGI, vLLM, or other inference APIs like Perplexity, Anyscale, or Mosaic ML.
-
Access 100+ models through serverless endpoints – including Llama 2, RedPajama, Falcon and Stable Diffusion XL. Endpoints are OpenAI compatible.
-
Access 8 leading embeddings models – including models that outperform OpenAI’s ada-002 and Cohere’s Embed-v3 in MTEB and LoCo Benchmarks.
TogetherAI API
Pre-configured instances of popular models hosted for free, priced per 1M tokens used. The below models are available through the inference API as serverless endpoints.
Run the following command to see the correct prompt format and stop sequence(s): together models info $MODEL_API_STRING. Request for a model to be added to serverless endpoints or for dedicated instance or capacity for these models.
