More other models supported

[Kejiasir]

Have you considered supporting the deepseek model?

[nezhyborets]

Hi @Kejiasir , thanks for the question/request! I wanted to take a look at their API reference before answering, so that I'd see what would be required to add such support and if we'd do that. But API Ref site is down, so I will have to wait

[Kejiasir]

Hey @nezhyborets , Thank you for your reply. Yes, I also noticed that deepseek's open platform is currently inaccessible. I will continue to pay attention and look forward to your follow-up processing.

[Kejiasir]

Hey @nezhyborets ,You can access the DeepSeek API Docs documentation.

[nezhyborets]

@Kejiasir I've just tried to init OpenAI with configuration initialised with DeepSeek API key as token, api.deepseek.com as host, and then use deepseek-chat as Model for requests/queries. The demo app replied that I don't have sufficient balance, and I can't top up because

Due to current server resource constraints, we have temporarily suspended API service recharges to prevent any potential impact on your operations. Existing balances can still be used for calls. We appreciate your understanding!

If you have a balance, could you try the above and see if it works for you?

[Kejiasir]

Sorry, like you, I don’t have an API balance available for testing. However, I read the DeepSeek API Docs, which states:

The DeepSeek API uses an API format compatible with OpenAI. By modifying the configuration, you can use the OpenAI SDK or softwares compatible with the OpenAI API to access the DeepSeek API.

To implement this, I extended the Model type as follows:

extension Model {
    static let deepseek_v3 = "deepseek-chat"
    static let deepseek_r1 = "deepseek-reasoner"
}

I will test this later.