user_idinteger required
ID of the user that owns the router.
type'automatic-speech-recognition' | 'image-text-to-text' | 'image-to-text' | 'text-embeddings-inference' | 'text-generation' | 'text-classification' required
aliasesstring[] required
Aliases of the model. It will be used to identify the model by users.
load_balancing_strategy'shuffle' | 'least_busy' required
vector_sizeinteger nullable
Dimension of the vectors, if the models are embeddings. Make sure it is the same for all models.
max_context_lengthinteger nullable
Maximum amount of tokens a context could contains. Make sure it is the same for all models.
cost_prompt_tokensnumber required
Cost of a million prompt tokens (decrease user budget)
cost_completion_tokensnumber required
Cost of a million completion tokens (decrease user budget)
providersinteger
Number of providers in the router.
createdinteger required
Time of creation, as Unix timestamp.
updatedinteger required
Time of last update, as Unix timestamp.