Integrations

Composable Prompts integrates with leading GenAI model and inference providers. Users can assemble multiple models from different providers into a synthetic LLM environment for load balancing between models or multi-head execution and LLM-mediated selection.

The integration with OpenAI provides access to AI models such as GPT-3.5 and GPT-4.

The Bedrock integration supports Claude, Cohere, LLama 2, AI21's models, and AWS Titan.

Google's Vertex AI is a machine learning (ML) platform for use in AI-powered applications.

Groq provides extremely fast inference for computationally intensive applications.

Run and fine-tune open-source models and deploy custom models at scale.

Together AI offers one of the fastest inference stacks available for open-source models.

MistralAI is a fully integrated AI model provider that gives access to models such as Mistral 7B and Mixtral 8×7B.

Support for Hugging Face Inference Endpoints to easily deploy Transformers and Diffusion models.