Create Completion

POST /v1/completions - Generate text completions

Endpoint

POST /v1/completions

Creates a completion for the provided prompt using the specified model.

The completions endpoint is considered legacy. Use the Chat Completions endpoint for new applications.

Request

Headers

Content-Type · string · required

Must be application/json

x-portkey-provider · string · required

The AI provider to use

x-portkey-api-key · string · required

Your API key for the specified provider

Body Parameters

model · string · required

The model to use for completion (e.g., gpt-3.5-turbo-instruct, text-davinci-003)

prompt · string | array · required

The prompt(s) to generate completions for

max_tokens · integer · default: 16

Maximum number of tokens to generate

temperature · number · default: 1

Sampling temperature between 0 and 2

top_p · number · default: 1

Nucleus sampling parameter

n · integer · default: 1

Number of completions to generate

stream · boolean · default: false

Whether to stream the response

stop · string | array

Up to 4 sequences where the API will stop generating

presence_penalty · number · default: 0

Penalty for token presence (-2.0 to 2.0)

frequency_penalty · number · default: 0

Penalty for token frequency (-2.0 to 2.0)

suffix · string

Text to append after the completion

echo · boolean · default: false

Echo back the prompt in addition to the completion

best_of · integer · default: 1

Generate multiple completions server-side and return the best

logprobs · integer

Include log probabilities on the most likely tokens

user · string

Unique identifier for the end-user

Response

id · string

Unique identifier for the completion

object · string

Object type, always text_completion

created · integer

Unix timestamp of creation

model · string

The model used for completion

choices · array

Array of completion choices

text · string

The generated text

index · integer

Choice index

logprobs · object

Log probability information (if requested)

finish_reason · string

Reason for completion: stop, length, or content_filter

usage · object

Token usage information

prompt_tokens · integer

Number of tokens in the prompt

completion_tokens · integer

Number of tokens in the completion

total_tokens · integer

Total tokens used

Examples

Basic Completion

curl http://localhost:8787/v1/completions \
  -H "Content-Type: application/json" \
  -H "x-portkey-provider: openai" \
  -H "x-portkey-api-key: sk-..." \
  -d '{
    "model": "gpt-3.5-turbo-instruct",
    "prompt": "Write a tagline for an ice cream shop.",
    "max_tokens": 20
  }'

Response

{
  "id": "cmpl-123",
  "object": "text_completion",
  "created": 1677652288,
  "model": "gpt-3.5-turbo-instruct",
  "choices": [{
    "text": " Sweet treats for every occasion!",
    "index": 0,
    "logprobs": null,
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 7,
    "total_tokens": 17
  }
}

Python SDK

from portkey_ai import Portkey

client = Portkey(
    provider="openai",
    Authorization="sk-..."
)

response = client.completions.create(
    model="gpt-3.5-turbo-instruct",
    prompt="Write a tagline for an ice cream shop.",
    max_tokens=20
)

print(response.choices[0].text)

JavaScript SDK

import Portkey from 'portkey-ai';

const client = new Portkey({
  provider: 'openai',
  Authorization: 'sk-...'
});

const response = await client.completions.create({
  model: 'gpt-3.5-turbo-instruct',
  prompt: 'Write a tagline for an ice cream shop.',
  max_tokens: 20
});

console.log(response.choices[0].text);

Multiple Completions

curl http://localhost:8787/v1/completions \
  -H "Content-Type: application/json" \
  -H "x-portkey-provider: openai" \
  -H "x-portkey-api-key: sk-..." \
  -d '{
    "model": "gpt-3.5-turbo-instruct",
    "prompt": "Complete this sentence: The future of AI is",
    "max_tokens": 30,
    "n": 3
  }'

Streaming Completion

from portkey_ai import Portkey

client = Portkey(
    provider="openai",
    Authorization="sk-..."
)

stream = client.completions.create(
    model="gpt-3.5-turbo-instruct",
    prompt="Write a short poem about coding",
    max_tokens=50,
    stream=True
)

for chunk in stream:
    if chunk.choices[0].text:
        print(chunk.choices[0].text, end="", flush=True)

With Stop Sequences

curl http://localhost:8787/v1/completions \
  -H "Content-Type: application/json" \
  -H "x-portkey-provider: openai" \
  -H "x-portkey-api-key: sk-..." \
  -d '{
    "model": "gpt-3.5-turbo-instruct",
    "prompt": "List three programming languages:\n1.",
    "max_tokens": 50,
    "stop": ["\n4."]
  }'