Helicone · Schema
ChatCompletion.Choice
AI GatewaysAI MonitoringGatewaysLLM ObservabilityLLM RoutingPrompt Management
Properties
| Name | Type | Description |
|---|---|---|
| finish_reason | string | The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, `length` if the maximum number of tokens specified in the request |
| index | number | The index of the choice in the list of choices. |
| logprobs | object | Log probability information for the choice. |
| message | object | A chat completion message generated by the model. |
JSON Schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "#/components/schemas/ChatCompletion.Choice",
"title": "ChatCompletion.Choice",
"properties": {
"finish_reason": {
"type": "string",
"enum": [
"stop",
"length",
"tool_calls",
"content_filter",
"function_call"
],
"description": "The reason the model stopped generating tokens. This will be `stop` if the model\nhit a natural stop point or a provided stop sequence, `length` if the maximum\nnumber of tokens specified in the request was reached, `content_filter` if\ncontent was omitted due to a flag from our content filters, `tool_calls` if the\nmodel called a tool, or `function_call` (deprecated) if the model called a\nfunction."
},
"index": {
"type": "number",
"format": "double",
"description": "The index of the choice in the list of choices."
},
"logprobs": {
"allOf": [
{
"$ref": "#/components/schemas/ChatCompletion.Choice.Logprobs"
}
],
"nullable": true,
"description": "Log probability information for the choice."
},
"message": {
"$ref": "#/components/schemas/ChatCompletionMessage",
"description": "A chat completion message generated by the model."
}
},
"required": [
"finish_reason",
"index",
"logprobs",
"message"
],
"type": "object",
"additionalProperties": false
}