App

• Added “upscale menu” providing 2x and 4x upscale options for Pro users.

  

API Dashboard

• The API key dashboard now shows the last date an API key was used, and the trailing 7 day usage in USD and VCU.

API

• Added support for scale parameter when upscaling. Available options are 2 and 4.

  Postman has been updated.

• Added API traits endpoint at /api/v1/models/traits — Postman has been updated.

• Add new traits on models to map OpenAI’s models to Venice’s current model fleet. The current mapping is as follows. Postman has been updated.

 {
        "function_calling_default": [
            "llama-3.3-70b"
        ],
        "default": [
            "llama-3.3-70b"
        ],
        "o1-mini": [
            "llama-3.3-70b"
        ],
        "o1-mini-2024-09-12": [
            "llama-3.3-70b"
        ],
        "o3-mini": [
            "llama-3.3-70b"
        ],
        "chatgpt-4o-latest": [
            "llama-3.3-70b"
        ],
        "gpt-4o-mini": [
            "llama-3.3-70b"
        ],
        "gpt-4o-mini-2024-07-18": [
            "llama-3.3-70b"
        ],
        "claude-3-5-haiku-20241022": [
            "llama-3.3-70b"
        ],
        "claude-3-haiku-20240307": [
            "llama-3.3-70b"
        ],
        "gpt-3.5-turbo-1106": [
            "llama-3.3-70b"
        ],
        "gpt-3.5-turbo-instruct": [
            "llama-3.3-70b"
        ],
        "gpt-3.5-turbo-instruct-0914": [
            "llama-3.3-70b"
        ],
        "gpt-3.5-turbo-0125": [
            "llama-3.3-70b"
        ],
        "gpt-3.5-turbo": [
            "llama-3.3-70b"
        ],
        "gpt-3.5-turbo-16k": [
            "llama-3.3-70b"
        ],
        "gpt-4o": [
            "llama-3.3-70b"
        ],
        "gpt-4o-2024-08-06": [
            "llama-3.3-70b"
        ],
        "gpt-4o-2024-05-13": [
            "llama-3.3-70b"
        ],
        "gpt-4o-2024-11-20": [
            "llama-3.3-70b"
        ],
        "claude-3-5-sonnet-20241022": [
            "llama-3.3-70b"
        ],
        "claude-3-5-sonnet-20240620": [
            "llama-3.3-70b"
        ],
        "fastest": [
            "llama-3.2-3b"
        ],
        "most_uncensored": [
            "dolphin-2.9.2-qwen2-72b"
        ],
        "most_intelligent": [
            "llama-3.1-405b"
        ],
        "o1": [
            "llama-3.1-405b"
        ],
        "o1-preview": [
            "llama-3.1-405b"
        ],
        "o1-preview-2024-09-12": [
            "llama-3.1-405b"
        ],
        "claude-3-opus-20240229": [
            "llama-3.1-405b"
        ],
        "default_code": [
            "qwen32b"
        ]
    }

Model Updates

• Adjust Qwen VL context down to ~32k tokens to resolve memory issues with server infrastructure.