DeepSeek
DeepSeek lets RealTimeX use DeepSeek-hosted chat and reasoning models directly.
Open it from Settings > AI Providers > LLM, then choose DeepSeek.
What you need
Before RealTimeX can use DeepSeek:
- you need a valid DeepSeek API key
- the RealTimeX instance must be able to reach the DeepSeek API
đź’ˇ
Current builds query the DeepSeek model API directly. If discovery fails, the app can still fall back to common defaults such as deepseek-chat and deepseek-reasoner.
Current setup flow
- Open
Settings > AI Providers > LLM. - Choose
DeepSeek. - Paste your DeepSeek API key.
- Wait for the model list to load.
- Select the model you want to use.
- Save the provider settings.
- Test a normal chat.
Troubleshooting
No models appear
Check that:
- the API key is correct
- the RealTimeX host can reach
https://api.deepseek.com/v1 - your account has access to the model family you expect