Support Venice.ai API

[julienrbrt]

Validations

• I believe this is a way to improve. I'll try to join the Continue Discord for questions
• I'm not able to find an open issue that requests the same enhancement

Problem

Venice.ai isn't supported. It has a free API for pro user and respect privacy.
I personally use it as an alternative to Ollama on a less powerful machine.)
They say they are compatible with OpenAI api, so maybe it is just a question of changing the api endpoint? (https://docs.venice.ai/welcome/about-venice#key-features)

Solution

Support venice.ai API.

[julienrbrt]

I should have read the docs better, I have managed to configure it for chat using https://docs.continue.dev/customize/model-providers/openai#openai-compatible-servers--apis.

[tkeitzl]

Which value did you choose for $provider$ and $model$ and potentially for $completionOptions$, @julienrbrt?

{
  "models": [
    {
      "title": "Venice.AI",
      "provider": "ollama",
      "model": "llama-3.3-70b",
      "apiKey": XXX,
      "apiBase": "https://api.venice.ai/api/v1",
      "completionOptions": {
        "endpoint": ""
      }
    }
  ]
}

Thank you for sharing!

[julienrbrt]

There is no completion api AFAICT. You can find the models by querying the api (https://www.postman.com/veniceai/venice-ai-workspace/request/9ujtbqt/list-models).

I have

    {
      "title": "Llama 3.1 405b (Venice.ai)",
      "provider": "openai",
      "model": "llama-3.1-405b",
      "apiKey": "redacted",
      "apiBase": "https://api.venice.ai/api/v1"
    },
    {
      "title": "Qwen Coder 2.5 (Venice.ai)",
      "provider": "openai",
      "model": "qwen32b",
      "apiKey": "redacted",
      "apiBase": "https://api.venice.ai/api/v1"
    },

[tomfotherby]

I created a pull-request to get Venice Added to the documentation: #4013