# Neutrino AI

## Docs

- [Model Gateway](https://docs.neutrinoapp.com/gateway/gateway.md): Concurrently generate and compare responses from different models in a single request.
- [Supported Models](https://docs.neutrinoapp.com/gateway/models.md)
- [Optimized Inference Engines](https://docs.neutrinoapp.com/inference-engines/engines.md): Inference Engines are designed to generate optimal LLM inference for their respective use-case. They have access to a carefully curated model selection and intelligently route queries to the best-suited LLM for each prompt. Maximize response quality while optimizing for cost and latency.
- [LangChain](https://docs.neutrinoapp.com/integrations/langchain.md): Call the Neutrino Router using LangChain
- [LlamaIndex](https://docs.neutrinoapp.com/integrations/llamaindex.md): Call the Neutrino Router using LlamaIndex
- [Quickstart](https://docs.neutrinoapp.com/introduction.md): Getting started with Neutrino AI
- [Model Pricing](https://docs.neutrinoapp.com/pricing/models.md)
- [Manually Upload Queries](https://docs.neutrinoapp.com/router-tags/batchupload.md): Ingest past queries with batch upload for Neutrino's exploration system.
- [Quickstart](https://docs.neutrinoapp.com/router-tags/quickstart.md): Routing tags allow you to gather observability metrics for specific sections of your AI application,  explore how different models perform on your use-case, and get the highest quality responses while balancing for cost and latency for your LLM queries.
- [Function Calling](https://docs.neutrinoapp.com/structured-outputs/function-calling.md): Use OpenAI's function calling API with the Neutrino router and supported models.

## OpenAPI Specs

- [openapi](https://docs.neutrinoapp.com/api-reference/openapi.json)