Using the gemini-1.5-pro-preview-0409 model through the API, but when the number of tokens is high (10k), the server directly reports 'Socket closed'.
You must be reaching either the input or the output token limit for 1.5 version:
Input token limit 1048576 Output token limit 8192
The model is in preview state, it may lack support and is unstable vs GA models available at the moment.
Ref:
User | Count |
---|---|
10 | |
2 | |
1 | |
1 | |
1 |