Skip to content

Enter at least 2 characters to search

completions

Create text completion

Create a text completion, supports streaming

Request

POST /completions

Request Body

FieldTypeRequiredDescription
modelstringYesModel name
promptstringYesPrompt text
best_ofintegerNoGenerate multiple results and return the best one
echobooleanNoWhether to echo the prompt
frequency_penaltynumberNo-
logit_biasobjectNo-
max_tokensintegerNo-
nintegerNo-
presence_penaltynumberNo-
seedintegerNo-
stopstringNo-
streambooleanNo-
temperaturenumberNo-
top_pnumberNo-
userstringNo-

Request Examples

Simple text completion

{
  "model": "gpt-5.6-luna",
  "prompt": "Once upon a time",
  "max_tokens": 50
}

Completion with options

{
  "model": "qwen-plus",
  "prompt": "Write a haiku about coding",
  "max_tokens": 100,
  "temperature": 0.8,
  "top_p": 1,
  "n": 1
}

Streaming completion

{
  "model": "gpt-5.6-luna",
  "prompt": "List 3 benefits of unit testing",
  "max_tokens": 64,
  "stream": true,
  "stop": [
    "\n\n"
  ]
}

Code completion example

{
  "model": "qwen3-coder-plus",
  "prompt": "def fibonacci(n):",
  "max_tokens": 80,
  "temperature": 0.3,
  "top_p": 0.9
}

Successful response

Response Schema

FieldTypeRequiredDescription
idstringYes-
objectstringYes-
createdintegerYes-
modelstringYes-
choicesArray<CompletionChoice>Yes-
usageobjectNo-

Response Example

{
  "id": "cmpl-123",
  "object": "completion",
  "created": 1677652288,
  "model": "gpt-5.6-luna",
  "choices": [
    {
      "text": ", there was a young programmer who loved to code.",
      "index": 0,
      "logprobs": null,
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 5,
    "completion_tokens": 12,
    "total_tokens": 17
  }
}

Code Examples

JavaScript (Fetch)

const response = await fetch('https://api.uuroute.ai/v1/completions', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
  "model": "gpt-5.6-luna",
  "prompt": "Once upon a time",
  "max_tokens": 50
})
});

const data = await response.json();
console.log(data);

Python (requests)

import requests

url = "https://api.uuroute.ai/v1/completions"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}

response = requests.post(url, json={
  "model": "gpt-5.6-luna",
  "prompt": "Once upon a time",
  "max_tokens": 50
}, headers=headers)
data = response.json()
print(data)

cURL

curl -X POST "https://api.uuroute.ai/v1/completions" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-5.6-luna","prompt":"Once upon a time","max_tokens":50}'

Schema Reference

CompletionRequest

FieldTypeRequiredDescription
modelstringYesModel name
promptstringYesPrompt text
best_ofintegerNoGenerate multiple results and return the best one
echobooleanNoWhether to echo the prompt
frequency_penaltynumberNo-
logit_biasobjectNo-
max_tokensintegerNo-
nintegerNo-
presence_penaltynumberNo-
seedintegerNo-
stopstringNo-
streambooleanNo-
temperaturenumberNo-
top_pnumberNo-
userstringNo-

CompletionResponse

FieldTypeRequiredDescription
idstringYes-
objectstringYes-
createdintegerYes-
modelstringYes-
choicesArray<CompletionChoice>Yes-
usageobjectNo-

CompletionChoice

FieldTypeRequiredDescription
textstringYes-
indexintegerYes-
logprobsobjectNo-
finish_reasonstring (stop, length, content_filter)Yes-

Usage

FieldTypeRequiredDescription
prompt_tokensintegerYesNumber of tokens in the prompt (input)
prompt_tokens_detailsobjectNoDetails about prompt tokens
completion_tokensintegerYesNumber of tokens in the completion (output)
completion_tokens_detailsobjectNoDetails about completion tokens
total_tokensintegerYesTotal number of tokens (prompt + completion)

Related APIs