Model IDs and endpoints
Every model has an ID like maker/model. GET /v1/models lists them with prices and endpoints.
El centro de ayuda está escrito en inglés y neerlandés. Estás leyendo la versión en inglés.
Model IDs look like anthropic/claude-opus-5.5 or openai/gpt-6-astra: the maker, a slash and the model. Add :eco for the Eco lane.
GET /v1/models lists every model you can use right now. It needs no key:
curl https://api.nexrouting.com/v1/models- id
- The ID to put in
model. - lane
- standard or eco.
- context_length
- How many tokens fit in one request, where known.
- pricing
- The price per input token (
prompt) and per output token (completion), in US dollars. - endpoints
- The formats the model supports:
/v1/chat/completions,/v1/messages,/v1/responsesor/v1/embeddings.
Calling a model on an endpoint it doesn’t support returns 400 (unsupported_endpoint), with the endpoint to use instead. If the part after the slash is unique, the API also accepts the ID without the maker, but the full ID is safer.
You can also browse and compare every model on nexrouting.com/models.