API
Completions
Use the legacy OpenAI-compatible completions endpoint for prompt-in, text-out models.
Overview
The Completions endpoint is retained for legacy clients. New applications should prefer Chat Completions unless a model or client specifically requires this shape.
Request
`POST https://uouo.cloud/v1/completions`
Body parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
| model | string | Yes | Completion model ID. |
| prompt | string or array | Yes | Input prompt. |
| max_tokens | integer | No | Maximum output tokens. |
| temperature | number | No | Sampling temperature. |
| top_p | number | No | Nucleus sampling. |
| stream | boolean | No | Return SSE chunks when true. |
| stop | string or array | No | Stop sequences. |
Example
curl https://uouo.cloud/v1/completions \
-H "Authorization: Bearer $UOUODUO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-3.5-turbo-instruct",
"prompt": "Write a one-sentence release note:",
"max_tokens": 80
}'Notes
- Prefer Chat Completions for multi-turn conversations.
- Legacy completion models may not support tools or multimodal input.
- Streaming follows the same `data:` and `[DONE]` SSE pattern as Chat Completions.