API Reference

Completions

Copy Markdown

Open in Claude

Open in ChatGPT

Open in Cursor

---

Copy Markdown

View as Markdown

Generate legacy text completion from prompt

client.Completions.New(ctx, body) (*Completion, error)

POST/v5/completions

Generates a legacy text completion from a raw prompt (a string or list of strings).

Use this endpoint for non-chat, prompt-in/text-out inference using the OpenAI text-completion contract; use /v5/chat/completions when you have a structured messages array, /v5/responses for the OpenAI Responses API, and /v5/inference for payloads that follow no OpenAI schema. The model is selected from model given as vendor/name and routed to the matching per-vendor gateway. When stream is set the response is delivered as server-sent events; otherwise a single text_completion object is returned. Token usage is recorded for the account, read from the final chunk on streaming responses.

ParametersExpand Collapse

body CompletionNewParams

Model param.Field[string]

model specified as model_vendor/model, for example openai/gpt-4o

Prompt param.Field[CompletionNewParamsPromptUnion]

The prompt to generate completions for, encoded as a string

string

[]string

BestOf param.Field[int64]Optional

Generates best_of completions server-side and returns the best one. Must be greater than n when used together.

Echo param.Field[bool]Optional

Echo back the prompt in addition to the completion

FrequencyPenalty param.Field[float64]Optional

Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text.

LogitBias param.Field[map[string, int64]]Optional

Modify the likelihood of specified tokens appearing in the completion. Maps tokens to bias values from -100 to 100.

Logprobs param.Field[int64]Optional

Include log probabilities of the most likely tokens. Maximum value is 5.

MaxTokens param.Field[int64]Optional

The maximum number of tokens that can be generated in the completion.

N param.Field[int64]Optional

How many completions to generate for each prompt.

PresencePenalty param.Field[float64]Optional

Number between -2.0 and 2.0. Positive values penalize new tokens based on their presence in the text so far.

Seed param.Field[int64]Optional

If specified, attempts to generate deterministic samples. Determinism is not guaranteed.

Stop param.Field[CompletionNewParamsStopUnion]Optional

Up to 4 sequences where the API will stop generating further tokens.

string

[]string

StreamOptions param.Field[map[string, any]]Optional

Options for streaming response. Only set this when stream is True.

Suffix param.Field[string]Optional

The suffix that comes after a completion of inserted text. Only supported for gpt-3.5-turbo-instruct.

Temperature param.Field[float64]Optional

Sampling temperature between 0 and 2. Higher values make output more random, lower more focused.

TopP param.Field[float64]Optional

Alternative to temperature. Consider only tokens with top_p probability mass. Range 0-1.

User param.Field[string]Optional

A unique identifier representing your end-user, which can help OpenAI monitor and detect abuse.

ReturnsExpand Collapse

type Completion struct{…}

ID string

Choices []CompletionChoice

FinishReason string

One of the following:

const CompletionChoiceFinishReasonStop CompletionChoiceFinishReason = "stop"

const CompletionChoiceFinishReasonLength CompletionChoiceFinishReason = "length"

const CompletionChoiceFinishReasonContentFilter CompletionChoiceFinishReason = "content_filter"

Index int64

Text string

Logprobs CompletionChoiceLogprobsOptional

TextOffset []int64Optional

TokenLogprobs []float64Optional

Tokens []stringOptional

TopLogprobs []map[string, float64]Optional

Created int64

Model string

Object CompletionObjectOptional

SystemFingerprint stringOptional

Usage CompletionUsageOptional

Usage statistics for the completion request.

CompletionTokens int64

PromptTokens int64

TotalTokens int64

CompletionTokensDetails CompletionUsageCompletionTokensDetailsOptional

Breakdown of tokens used in a completion.

AcceptedPredictionTokens int64Optional

AudioTokens int64Optional

ReasoningTokens int64Optional

RejectedPredictionTokens int64Optional

PromptTokensDetails CompletionUsagePromptTokensDetailsOptional

Breakdown of tokens used in the prompt.

AudioTokens int64Optional

CachedTokens int64Optional

type Completion struct{…}

ID string

Choices []CompletionChoice

FinishReason string

One of the following:

const CompletionChoiceFinishReasonStop CompletionChoiceFinishReason = "stop"

const CompletionChoiceFinishReasonLength CompletionChoiceFinishReason = "length"

const CompletionChoiceFinishReasonContentFilter CompletionChoiceFinishReason = "content_filter"

Index int64

Text string

Logprobs CompletionChoiceLogprobsOptional

TextOffset []int64Optional

TokenLogprobs []float64Optional

Tokens []stringOptional

TopLogprobs []map[string, float64]Optional

Created int64

Model string

Object CompletionObjectOptional

SystemFingerprint stringOptional

Usage CompletionUsageOptional

Usage statistics for the completion request.

CompletionTokens int64

PromptTokens int64

TotalTokens int64

CompletionTokensDetails CompletionUsageCompletionTokensDetailsOptional

Breakdown of tokens used in a completion.

AcceptedPredictionTokens int64Optional

AudioTokens int64Optional

ReasoningTokens int64Optional

RejectedPredictionTokens int64Optional

PromptTokensDetails CompletionUsagePromptTokensDetailsOptional

Breakdown of tokens used in the prompt.

AudioTokens int64Optional

CachedTokens int64Optional

Generate legacy text completion from prompt

Go

HTTP

TypeScript

Python

Go

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.Completions.New(context.TODO(), sgpdev.CompletionNewParams{
    Model: "model",
    Prompt: sgpdev.CompletionNewParamsPromptUnion{
      OfString: sgpdev.String("string"),
    },
  })
  if err != nil {
    panic(err.Error())
  }
  fmt.Printf("%+v\n", completion.ID)
}

200 example

{
  "id": "id",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "text": "text",
      "logprobs": {
        "text_offset": [
          0
        ],
        "token_logprobs": [
          0
        ],
        "tokens": [
          "string"
        ],
        "top_logprobs": [
          {
            "foo": 0
          }
        ]
      }
    }
  ],
  "created": 0,
  "model": "model",
  "object": "text_completion",
  "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

200 example

{
  "id": "id",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "text": "text",
      "logprobs": {
        "text_offset": [
          0
        ],
        "token_logprobs": [
          0
        ],
        "tokens": [
          "string"
        ],
        "top_logprobs": [
          {
            "foo": 0
          }
        ]
      }
    }
  ],
  "created": 0,
  "model": "model",
  "object": "text_completion",
  "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
    }
  }
}