Generate OpenAI chat completion from messages
Generates a chat completion from an OpenAI-style messages array.
Use this endpoint for standard messages-based chat inference; use /v5/completions instead when you
have a raw text prompt rather than messages, /v5/responses for the OpenAI Responses API contract,
and /v5/inference when the payload does not follow any OpenAI schema. The request accepts the OpenAI
Chat Completions parameters (extra fields are allowed and forwarded), and the model is selected from
model given as vendor/name; most vendors are served through the litellm proxy gateway, while
OpenAI may use a native gateway. When stream is set the response is delivered as server-sent events
of chat.completion.chunk; otherwise a single chat.completion object is returned. Token usage is
recorded for the account, and for streaming responses it is read from the final chunk.
Generate OpenAI chat completion from messages
package main
import (
"context"
"fmt"
"github.com/scaleapi/sgp-dev-go"
"github.com/scaleapi/sgp-dev-go/option"
)
func main() {
client := sgpdev.NewClient(
option.WithAPIKey("My API Key"),
option.WithAccountID("My Account ID"),
)
completion, err := client.Chat.Completions.New(context.TODO(), sgpdev.ChatCompletionNewParams{
Messages: []map[string]any{map[string]any{
"foo": "bar",
}},
Model: "model",
})
if err != nil {
panic(err.Error())
}
fmt.Printf("%+v\n", completion)
}
{
"id": "id",
"choices": [
{
"finish_reason": "stop",
"index": 0,
"message": {
"role": "assistant",
"annotations": [
{
"type": "url_citation",
"url_citation": {
"end_index": 0,
"start_index": 0,
"title": "title",
"url": "url"
}
}
],
"audio": {
"id": "id",
"data": "data",
"expires_at": 0,
"transcript": "transcript"
},
"content": "content",
"function_call": {
"arguments": "arguments",
"name": "name"
},
"refusal": "refusal",
"tool_calls": [
{
"id": "id",
"function": {
"arguments": "arguments",
"name": "name"
},
"type": "function"
}
]
},
"logprobs": {
"content": [
{
"token": "token",
"logprob": 0,
"top_logprobs": [
{
"token": "token",
"logprob": 0,
"bytes": [
0
]
}
],
"bytes": [
0
]
}
],
"refusal": [
{
"token": "token",
"logprob": 0,
"top_logprobs": [
{
"token": "token",
"logprob": 0,
"bytes": [
0
]
}
],
"bytes": [
0
]
}
]
}
}
],
"created": 0,
"model": "model",
"object": "chat.completion",
"service_tier": "auto",
"system_fingerprint": "system_fingerprint",
"usage": {
"completion_tokens": 0,
"prompt_tokens": 0,
"total_tokens": 0,
"completion_tokens_details": {
"accepted_prediction_tokens": 0,
"audio_tokens": 0,
"reasoning_tokens": 0,
"rejected_prediction_tokens": 0
},
"prompt_tokens_details": {
"audio_tokens": 0,
"cached_tokens": 0
}
}
}Returns Examples
{
"id": "id",
"choices": [
{
"finish_reason": "stop",
"index": 0,
"message": {
"role": "assistant",
"annotations": [
{
"type": "url_citation",
"url_citation": {
"end_index": 0,
"start_index": 0,
"title": "title",
"url": "url"
}
}
],
"audio": {
"id": "id",
"data": "data",
"expires_at": 0,
"transcript": "transcript"
},
"content": "content",
"function_call": {
"arguments": "arguments",
"name": "name"
},
"refusal": "refusal",
"tool_calls": [
{
"id": "id",
"function": {
"arguments": "arguments",
"name": "name"
},
"type": "function"
}
]
},
"logprobs": {
"content": [
{
"token": "token",
"logprob": 0,
"top_logprobs": [
{
"token": "token",
"logprob": 0,
"bytes": [
0
]
}
],
"bytes": [
0
]
}
],
"refusal": [
{
"token": "token",
"logprob": 0,
"top_logprobs": [
{
"token": "token",
"logprob": 0,
"bytes": [
0
]
}
],
"bytes": [
0
]
}
]
}
}
],
"created": 0,
"model": "model",
"object": "chat.completion",
"service_tier": "auto",
"system_fingerprint": "system_fingerprint",
"usage": {
"completion_tokens": 0,
"prompt_tokens": 0,
"total_tokens": 0,
"completion_tokens_details": {
"accepted_prediction_tokens": 0,
"audio_tokens": 0,
"reasoning_tokens": 0,
"rejected_prediction_tokens": 0
},
"prompt_tokens_details": {
"audio_tokens": 0,
"cached_tokens": 0
}
}
}