6ioAPI
RUEN

Venice models (group vn)

The vn group gives access to the chat models of Venice. A model name is vn/<Venice model ID>, for example vn/llama-3.3-70b. Requests and responses are OpenAI-compatible: POST /v1/chat/completions (see Chat).

The request body is passed to Venice as it is, so the parameters are described in the Venice documentation: Chat Completions and API Specification (the Venice-specific venice_parameters are there too). The list of Venice models is in List Models and its prices in Pricing. Here you get the same models with prices in credits.

Finding a model

GET /v1/models returns every model on sale with prices in credits. Venice models start with vn/. There is no provider choice as in OpenRouter: Venice runs its own models.

How it differs from a plain chat

  • The Venice system prompt is off. By default Venice adds its own prompt, about 1500 tokens on every request, and you would pay for them. Turn it on with venice_parameters.include_venice_system_prompt: true.
  • Paid search is not accepted. Web search, page scraping and X search (venice_parameters.enable_web_search, enable_web_scraping, enable_x_search) and suffixes in the model name (model:parameter=value) are refused for now with 400 unsupported_parameter or 404 model_not_found: their cost is not part of the reserve.
  • Models with client-side encryption (e2ee-…) are not on sale.
  • All other venice_parameters and request parameters are passed on as they are.
  • Price. Venice reports the cost in the cost field of the response (usd and diem). If the cost is not in dollars (diem is not zero), you get the result at once and the money for the request is closed after a check (status billing_pending, then billing_review); see Balance and prices.

Free models (price 0) work while the API balance is above zero: see Chat.