Completion API return huge chunks with empty content

I get below response for json schema output, and it will consume much more token than normal response.


data: {“id”:“chatcmpl-AMPweDwF7xbl6vT9FHz5UFYbg2r6W”,“object”:“chat.completion.chunk”,“created”:1729906312,“model”:“gpt-4o-mini-2024-07-18”,“system_fingerprint”:“fp_f59a81427f”,“choices”:[{“index”:0,“delta”:{“content”:" “},“logprobs”:null,“finish_reason”:null}],“usage”:null}
data: {“id”:“chatcmpl-AMPweDwF7xbl6vT9FHz5UFYbg2r6W”,“object”:“chat.completion.chunk”,“created”:1729906312,“model”:“gpt-4o-mini-2024-07-18”,“system_fingerprint”:“fp_f59a81427f”,“choices”:[{“index”:0,“delta”:{“content”:” “},“logprobs”:null,“finish_reason”:null}],“usage”:null}
data: {“id”:“chatcmpl-AMPweDwF7xbl6vT9FHz5UFYbg2r6W”,“object”:“chat.completion.chunk”,“created”:1729906312,“model”:“gpt-4o-mini-2024-07-18”,“system_fingerprint”:“fp_f59a81427f”,“choices”:[{“index”:0,“delta”:{“content”:” “},“logprobs”:null,“finish_reason”:null}],“usage”:null}
data: {“id”:“chatcmpl-AMPweDwF7xbl6vT9FHz5UFYbg2r6W”,“object”:“chat.completion.chunk”,“created”:1729906312,“model”:“gpt-4o-mini-2024-07-18”,“system_fingerprint”:“fp_f59a81427f”,“choices”:[{“index”:0,“delta”:{“content”:” “},“logprobs”:null,“finish_reason”:null}],“usage”:null}
data: {“id”:“chatcmpl-AMPweDwF7xbl6vT9FHz5UFYbg2r6W”,“object”:“chat.completion.chunk”,“created”:1729906312,“model”:“gpt-4o-mini-2024-07-18”,“system_fingerprint”:“fp_f59a81427f”,“choices”:[{“index”:0,“delta”:{“content”:” "},“logprobs”:null,“finish_reason”:null}],“usage”:null}