Skip to main content
POST
/
v1
/
completions
Completions
curl --request POST \
  --url https://modelswitch.io/v1/completions \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "prompt": "<string>",
  "max_tokens": 123,
  "temperature": 123,
  "stream": true
}
'
{
  "id": "<string>",
  "object": "<string>",
  "created": 123,
  "model": "<string>",
  "choices": [
    {
      "text": "<string>",
      "index": 123,
      "finish_reason": "<string>"
    }
  ],
  "usage": {
    "prompt_tokens": 123,
    "completion_tokens": 123,
    "total_tokens": 123
  }
}
The Completions API is the legacy text completion format. For most use cases, use the Chat Completions API instead. Only a small set of models (e.g., gpt-3.5-turbo-instruct) support this format.
Generate a text completion from a single prompt string. Unlike chat completions, this endpoint takes a raw prompt rather than a structured message array. Authentication: Authorization: Bearer ms-YOUR_KEY

​
Parameters

​
model
string
required
Model ID. This endpoint requires a model that supports the legacy completions format, such as gpt-3.5-turbo-instruct.
​
prompt
string
required
The prompt text to complete. The model continues from this input.
​
max_tokens
integer
default:"16"
Maximum number of tokens to generate in the completion.
​
temperature
number
default:"1"
Sampling temperature between 0 and 2. Lower values produce more deterministic output.
​
stream
boolean
default:"false"
When true, the response is delivered as server-sent events (SSE), ending with data: [DONE].

​
Example

​
Request

{
  "model": "gpt-3.5-turbo-instruct",
  "prompt": "def bubble_sort(arr):\n",
  "max_tokens": 256,
  "temperature": 0.3
}

curl https://modelswitch.io/v1/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer ms-YOUR_KEY" \
  -d '{
    "model": "gpt-3.5-turbo-instruct",
    "prompt": "def bubble_sort(arr):\n",
    "max_tokens": 256,
    "temperature": 0.3
  }'

​
Response

{
  "id": "cmpl-xyz789",
  "object": "text_completion",
  "created": 1709000000,
  "model": "gpt-3.5-turbo-instruct",
  "choices": [{
    "text": "\n    n = len(arr)\n    for i in range(n)...",
    "index": 0,
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 85,
    "total_tokens": 97
  }
}
​
id
string
Unique identifier for this completion request.
​
object
string
Always "text_completion".
​
created
integer
Unix timestamp of when the completion was created.
​
model
string
The model that generated the response.
​
choices
array
Array of generated completions.
​
usage
object
Token counts for this request, used for billing.