What Nexrouting is
One API key and one balance for AI models from many providers, paid in euros.
Le centre d’aide est rédigé en anglais et en néerlandais. Vous lisez la version anglaise.
Nexrouting is one API for AI models from OpenAI, Anthropic, Google, xAI and other providers. You send every request to one address with one key, and we route it to the model you name. You pay per token from a balance you top up in advance.
How it works
- One address.
https://api.nexrouting.com/v1works with the OpenAI SDK and other OpenAI-compatible tools. You change the base URL and the key; the rest of your code stays the same. - One key. Keys start with
nr-v1-. A key works for every model, unless you limit it. - You choose the model. Set
modelto an ID such asopenai/gpt-6-astra. Some models also have a cheaper Eco lane: add:eco. - One balance. You top up in euros. Your balance is kept in US dollars, the currency of all model prices, and every request is paid from it.
- You see what each request cost. Your dashboard lists every request with its model, tokens, cost and request ID.
What you can call
POST /v1/chat/completions: chat in the OpenAI format.POST /v1/messages: the Anthropic Messages format, for models that support it.POST /v1/responses: the OpenAI Responses format, for models that support it.POST /v1/embeddings: embeddings, for models that make them.GET /v1/models: every model you can use right now, with prices. No key needed.GET /v1/creditsandGET /v1/key: your balance, and the limits and spend of the key you send.
Which formats a model supports is in the endpoints field of GET /v1/models. See Model IDs and endpoints.
Your dashboard is at app.nexrouting.com. The price list is on nexrouting.com/models.