---
title: "Completions"
method: POST
path: "/v1/completions"
tags: ["openai-compat"]
---

# Completions

`POST /v1/completions`

Generate one raw-prompt OpenAI legacy completion.

## Headers

- `X-SIE-MACHINE-PROFILE` string, nullable

## Request body

- OpenAICompletionRequestModel — Strict single-candidate subset of the OpenAI legacy Completions API.
  - `model` string, required — Generation model id
  - `prompt` union, required — One raw prompt string, or a one-element string array; no chat template is applied
    - string
    - string[]
  - `max_tokens` integer, nullable — Maximum generated tokens
  - `temperature` number, nullable — Sampling temperature override
  - `top_p` number, nullable — Nucleus-sampling probability override
  - `stop` union — One stop sequence or an array of stop sequences
    - string
    - string[]
  - `frequency_penalty` number, nullable — Frequency penalty
  - `presence_penalty` number, nullable — Presence penalty
  - `seed` integer, nullable — Optional signed 64-bit sampling seed
  - `stream` boolean, nullable — Return OpenAI text_completion Server-Sent Events
  - `stream_options` OpenAICompletionStreamOptionsModel — Supported OpenAI legacy-completions stream controls.
    - `include_usage` boolean, nullable — Emit one usage-only chunk immediately before the [DONE] terminator
  - `n` 1, nullable — Only one completion candidate is supported

## Response `200`

OpenAI text completion, or text_completion Server-Sent Events when stream is true

- OpenAICompletionResponseModel — Blocking OpenAI legacy-completions response.
  - `id` string, required
  - `object` 'text_completion', required
  - `created` integer, required
  - `model` string, required
  - `choices` OpenAICompletionChoiceModel[], required
    - `text` string, required
    - `index` integer, required
    - `finish_reason` string, required
  - `system_fingerprint` string, nullable
  - `usage` GenerateUsageModel, required — Token usage for one generation request.
    - `prompt_tokens` integer, required — Number of prompt tokens
    - `completion_tokens` integer, required — Number of generated tokens
    - `total_tokens` integer, required — Total prompt and generated tokens

## Other responses

- `400` — Invalid or unsupported request
- `404` — Model not found
- `413` — Request body or prompt is too large
- `422` — Validation Error
- `500` — Generation failed
- `503` — Model loading or temporarily unavailable

## Changes

> 43 revisions in range; 1 could not be searched.

- **2026-08-06** `8eefbfaad8f2` — 1 info
  - endpoint added

[Change history](https://skmtc.dev/superlinked/apis/sie-server/changes/v1/completions/post.md)

---

[API](https://skmtc.dev/superlinked/apis/sie-server.md) · [All operations](https://skmtc.dev/superlinked/apis/sie-server/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/superlinked/sie-server/revisions/26ac644915a4/schema)