I am using Assistant streaming API with gpt-4-turbo. My input token is almost 16K and after generating 3K tokens for output it stops generating output. Can someone tell where the issue is?
Related Topics
Topic | Replies | Views | Activity | |
---|---|---|---|---|
Why does chat completion API stop sometimes during generation? Max tokens not an issue | 2 | 1170 | February 2, 2024 | |
Large JSON Responses from Assistant API are truncated | 5 | 813 | June 20, 2024 | |
Optimizing Token Utilization for GPT-4 with Vector Database: Overcoming 1000-Token Limit Challenges | 2 | 75 | October 9, 2024 | |
4096 completion token limit with gpt-4o. Using assistant streaming API | 0 | 159 | July 20, 2024 | |
Token overflow with code interpreter | 0 | 116 | July 15, 2024 |