# Nexrouting > One API for AI models from OpenAI, Anthropic, Google, xAI and other providers, paid per token from one prepaid balance. OpenAI-compatible (/v1/chat/completions, /v1/responses, /v1/embeddings) and Anthropic-compatible (/v1/messages). - Base URL: https://api.nexrouting.com/v1 (Anthropic SDK: https://api.nexrouting.com) - Auth: `Authorization: Bearer nr-v1-…` (the `x-api-key` header also works). Keys start with `nr-v1-`. - Model IDs: `provider/model`, for example `openai/gpt-6-astra`; add `:eco` for the cheaper Eco lane where a model has one. - Model list with prices per token and supported endpoints: GET https://api.nexrouting.com/v1/models (no key needed). - Errors use the OpenAI error shape, except /v1/messages, which uses the Anthropic shape. ## Get started - [Quickstart](https://nexrouting.com/docs/quickstart): Create an account, add credits, make a key and send your first request to the Nexrouting API. - [Authentication & API keys](https://nexrouting.com/docs/authentication): Send your key as a bearer token, limit keys with a budget, a model list and an expiry date, and revoke a key that leaked. - [OpenAI SDK](https://nexrouting.com/docs/openai-sdk): Use the official OpenAI SDK for Python or Node with Nexrouting: set the base URL and your key, and every model works. - [Anthropic SDK](https://nexrouting.com/docs/anthropic-sdk): Use the official Anthropic SDK for Python or Node with Nexrouting through the Messages API at /v1/messages. ## Guides - [Models & lanes](https://nexrouting.com/docs/models): How model IDs work, what the Standard and Eco lanes are, how fallback between routes works, and how to list every model. - [Streaming](https://nexrouting.com/docs/streaming): Stream tokens as server-sent events on every chat endpoint, get usage at the end of a stream, and handle errors mid-stream. - [Pricing & usage](https://nexrouting.com/docs/pricing): How each request is billed per input and output token, the rates for long prompts, caching and reasoning, and where you see your usage. - [Errors](https://nexrouting.com/docs/errors): Every error the Nexrouting API returns: HTTP status, code, what it means and what to do, plus the error shapes and when to retry. - [Rate limits](https://nexrouting.com/docs/rate-limits): How many requests per minute each API key can send, which headers the API returns, and what happens when you hit the limit. - [Images & video](https://nexrouting.com/docs/images-video): Send images to vision models through chat completions or messages. Image generation, video and audio are not available yet. - [NexPods](https://nexrouting.com/docs/nexpods): NexPods, GPUs by the hour on the same account and balance, are coming soon. Join the waitlist in the dashboard. ## API reference - [POST /v1/chat/completions](https://nexrouting.com/docs/api-chat-completions): POST /v1/chat/completions: create a chat completion with any chat model, in the OpenAI format, with or without streaming. - [POST /v1/messages](https://nexrouting.com/docs/api-messages): POST /v1/messages: create a message in the Anthropic Messages format, for Claude and the other models that support it. - [POST /v1/responses](https://nexrouting.com/docs/api-responses): POST /v1/responses: create a model response in the OpenAI Responses format, for the models that support it. - [POST /v1/embeddings](https://nexrouting.com/docs/api-embeddings): POST /v1/embeddings: turn text into vectors with an embedding model, in the OpenAI format. - [GET /v1/models](https://nexrouting.com/docs/api-models): GET /v1/models: every model lane you can use right now, with its price per token, context length and endpoints. No key needed. - [GET /v1/credits](https://nexrouting.com/docs/api-credits): GET /v1/credits: the balance of your organization, with total credits and total usage, in US dollars and micro-dollars. - [GET /v1/key](https://nexrouting.com/docs/api-key): GET /v1/key: the name, budget, spend, rate limit, allowed models and expiry date of the key you call it with. ## Integrations - [LangChain](https://nexrouting.com/docs/langchain): Use Nexrouting models in LangChain for Python and JavaScript through the OpenAI integration. - [n8n](https://nexrouting.com/docs/n8n): Use Nexrouting models in n8n workflows and AI agents with an OpenAI credential and a custom base URL. - [Cursor](https://nexrouting.com/docs/cursor): Use Nexrouting models in Cursor with your own key: override the OpenAI base URL and add the model ID. ## Optional - [Models](https://nexrouting.com/models): every model with its price per million tokens - [Pricing](https://nexrouting.com/pricing): how pricing works - [Status](https://nexrouting.com/status): uptime per service and model - [Terms](https://nexrouting.com/legal/terms): terms of service