A valid request URL is required to generate request examples{
"id": "<string>",
"object": "chat.completion",
"created": 123,
"model": "<string>",
"choices": [
{
"index": 123,
"message": {
"role": "system",
"content": "<string>",
"name": "<string>",
"tool_calls": [
{
"id": "<string>",
"type": "function",
"function": {
"name": "<string>",
"arguments": "<string>"
}
}
],
"tool_call_id": "<string>"
},
"finish_reason": "stop",
"logprobs": {
"content": [
{
"token": "<string>",
"logprob": 123,
"bytes": [
123
],
"top_logprobs": [
{
"token": "<string>",
"logprob": 123,
"bytes": [
123
]
}
]
}
]
}
}
],
"usage": {
"prompt_tokens": 123,
"completion_tokens": 123,
"total_tokens": 123,
"prompt_tokens_details": {
"cached_tokens": 123
},
"completion_tokens_details": {
"reasoning_tokens": 123,
"accepted_prediction_tokens": 123,
"rejected_prediction_tokens": 123
},
"cache_creation_input_tokens": 123,
"cache_read_input_tokens": 123
},
"system_fingerprint": "<string>"
}A simple wrapper around the Chat Completion API for persistent, multi-turn text conversations via WebSocket.
Clients send standard ChatRequest JSON objects and receive streaming ChatResponse chunks.
A valid request URL is required to generate request examples{
"id": "<string>",
"object": "chat.completion",
"created": 123,
"model": "<string>",
"choices": [
{
"index": 123,
"message": {
"role": "system",
"content": "<string>",
"name": "<string>",
"tool_calls": [
{
"id": "<string>",
"type": "function",
"function": {
"name": "<string>",
"arguments": "<string>"
}
}
],
"tool_call_id": "<string>"
},
"finish_reason": "stop",
"logprobs": {
"content": [
{
"token": "<string>",
"logprob": 123,
"bytes": [
123
],
"top_logprobs": [
{
"token": "<string>",
"logprob": 123,
"bytes": [
123
]
}
]
}
]
}
}
],
"usage": {
"prompt_tokens": 123,
"completion_tokens": 123,
"total_tokens": 123,
"prompt_tokens_details": {
"cached_tokens": 123
},
"completion_tokens_details": {
"reasoning_tokens": 123,
"accepted_prediction_tokens": 123,
"rejected_prediction_tokens": 123
},
"cache_creation_input_tokens": 123,
"cache_read_input_tokens": 123
},
"system_fingerprint": "<string>"
}Was this page helpful?