REST: Update chat completion
[CURRENTLY NOT SUPPORTED]
HTTP request
POST https://ai.api.cloud.yandex.net/v1/chat/completions/{completion_id}
Path parameters
|
Field |
Description |
|
completion_id |
string Required field. The ID of the chat completion to update. |
Body parameters
Request schema: application/json
{
"metadata": "unknown"
}
|
Field |
Description |
|
metadata |
Any of object (map<string, string>) | null |
Response
HTTP Code: 200
A chat completion
Response schema: application/json
{
"id": "string",
"choices": [
{
"finish_reason": "string",
"index": "integer",
"message": {
"content": "unknown",
"refusal": "unknown",
"tool_calls": [
{
"<anyOf>": [
{
"id": "string",
"type": "string",
"function": {
"name": "string",
"arguments": "string"
}
},
{
"id": "string",
"type": "string",
"custom": {
"name": "string",
"input": "string"
}
}
]
}
],
"annotations": [
{
"type": "string",
"url_citation": {
"end_index": "integer",
"start_index": "integer",
"url": "string",
"title": "string"
}
}
],
"role": "string",
"function_call": "unknown",
"audio": "unknown"
},
"logprobs": "unknown"
}
],
"created": "integer",
"model": "string",
"service_tier": "unknown",
"system_fingerprint": "string",
"object": "string",
"usage": {
"completion_tokens": "integer",
"prompt_tokens": "integer",
"total_tokens": "integer",
"completion_tokens_details": {
"accepted_prediction_tokens": "integer",
"audio_tokens": "integer",
"reasoning_tokens": "integer",
"rejected_prediction_tokens": "integer"
},
"prompt_tokens_details": {
"audio_tokens": "integer",
"cached_tokens": "integer"
}
}
}
Represents a chat completion response returned by model, based on the provided input.
|
Field |
Description |
|
id |
string Required field. A unique identifier for the chat completion. |
|
choices[] |
Required field. |
|
created |
integer Required field. The Unix timestamp (in seconds) of when the chat completion was created. |
|
model |
string Required field. The model used for the chat completion. |
|
service_tier |
unknown [CURRENTLY NOT SUPPORTED] |
|
system_fingerprint |
string This fingerprint represents the backend configuration that the model runs with. Can be used in conjunction with the |
|
object |
enum Required field. The object type, which is always
|
|
usage |
Required field. Usage statistics for the completion request. |
ChoicesItem
|
Field |
Description |
|
finish_reason |
enum Required field. The reason the model stopped generating tokens. This will be
|
|
index |
integer Required field. The index of the choice in the list of choices. |
|
message |
Required field. A chat completion message generated by the model. |
|
logprobs |
Any of Logprobs0 | null |
ChatCompletionResponseMessage
A chat completion message generated by the model.
|
Field |
Description |
|
content |
Any of string | null |
|
refusal |
Any of string | null |
|
tool_calls[] |
unknown |
|
annotations[] |
Required field. A URL citation when using web search. |
|
role |
enum Required field. The role of the author of this message.
|
|
function_call |
unknown DEPRECATED - This field is deprecated and will be removed in a future version. Use Controls which (if any) function is called by the model.
|
|
audio |
Any of Audio0 | null |
AnnotationsItem
A URL citation when using web search.
|
Field |
Description |
|
type |
enum Required field. The type of the URL citation. Always
|
|
url_citation |
Required field. A URL citation when using web search. |
UrlCitation
A URL citation when using web search.
|
Field |
Description |
|
end_index |
integer Required field. The index of the last character of the URL citation in the message. |
|
start_index |
integer Required field. The index of the first character of the URL citation in the message. |
|
url |
string Required field. The URL of the web resource. |
|
title |
string Required field. The title of the web resource. |
Audio0
If the audio output modality is requested, this object contains data about the audio response from the model.'
|
Field |
Description |
|
id |
string Required field. Unique identifier for this audio response. |
|
expires_at |
integer Required field. The Unix timestamp (in seconds) for when this audio response will |
|
data |
string Required field. Base64 encoded audio bytes generated by the model, in the format |
|
transcript |
string Required field. Transcript of the audio generated by the model. |
Logprobs0
Log probability information for the choice.
|
Field |
Description |
|
content |
Any of ChatCompletionTokenLogprob | null |
|
refusal |
Any of ChatCompletionTokenLogprob | null |
ChatCompletionTokenLogprob
|
Field |
Description |
|
token |
string Required field. The token. |
|
logprob |
number Required field. The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value |
|
bytes |
Any of integer | null |
|
top_logprobs[] |
Required field. |
TopLogprobsItem
|
Field |
Description |
|
token |
string Required field. The token. |
|
logprob |
number Required field. The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value |
|
bytes |
Any of integer | null |
CompletionUsage
Usage statistics for the completion request.
|
Field |
Description |
|
completion_tokens |
integer Required field. Number of tokens in the generated completion. |
|
prompt_tokens |
integer Required field. Number of tokens in the prompt. |
|
total_tokens |
integer Required field. Total number of tokens used in the request (prompt + completion). |
|
completion_tokens_details |
Breakdown of tokens used in a completion. |
|
prompt_tokens_details |
Breakdown of tokens used in the prompt. |
CompletionTokensDetails
Breakdown of tokens used in a completion.
|
Field |
Description |
|
accepted_prediction_tokens |
integer When using Predicted Outputs, the number of tokens in the |
|
audio_tokens |
integer Audio input tokens generated by the model. |
|
reasoning_tokens |
integer Tokens generated by the model for reasoning. |
|
rejected_prediction_tokens |
integer When using Predicted Outputs, the number of tokens in the |
PromptTokensDetails
Breakdown of tokens used in the prompt.
|
Field |
Description |
|
audio_tokens |
integer Audio input tokens present in the prompt. |
|
cached_tokens |
integer Cached tokens present in the prompt. |