Completions

Supported providers

1. AI21

2. Anthropic

3. Anyscale

4. Azure OpenAI

5. AWS Bedrock

6. Cohere

7. Fireworks AI

8. Novita AI

9. OpenAI

10. Together AI

11. Cloudflare Workers AI

Create Completion

POST /completions

Generate text completions using the selected Large Language Model (LLM).

Completions

post

Authorizations

Portkey-KeyVirtual-KeyProvider-AuthProvider-NameConfigCustom-Host

Body

modelany ofRequired

ID of the model to use. You can use the List models API to see all of your available models, or see our Model overview for descriptions of them.

stringOptional

or

string · enumOptionalPossible values:

promptone of | nullableRequired

The prompt(s) to generate completions for, encoded as a string, array of strings, array of tokens, or array of token arrays.

Note that <|endoftext|> is the document separator that the model sees during training, so if a prompt is not specified the model will generate as if from the beginning of a new document.

Default: <|endoftext|>

stringOptionalDefault: ""Example: This is a test.

or

string[]OptionalExample: This is a test.

or

integer[] · min: 1OptionalExample: [1212, 318, 257, 1332, 13]

or

best_ofinteger | nullableOptional

Generates best_of completions server-side and returns the "best" (the one with the highest log probability per token). Results cannot be streamed.

When used with n, best_of controls the number of candidate completions and n specifies how many to return – best_of must be greater than n.

Note: Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for max_tokens and stop.

Default: 1

echoboolean | nullableOptional

Echo back the prompt in addition to the completion

Default: false

frequency_penaltynumber | nullableOptional

Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.

See more information about frequency and presence penalties.

Default: 0

logprobsinteger | nullableOptional

Include the log probabilities on the logprobs most likely output tokens, as well the chosen tokens. For example, if logprobs is 5, the API will return a list of the 5 most likely tokens. The API will always return the logprob of the sampled token, so there may be up to logprobs+1 elements in the response.

The maximum value for logprobs is 5.

Default: null

max_tokensinteger | nullableOptional

The maximum number of tokens that can be generated in the completion.

The token count of your prompt plus max_tokens cannot exceed the model's context length. Example Python code for counting tokens.

Default: 16Example: 16

ninteger | nullableOptional

How many completions to generate for each prompt.

Note: Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for max_tokens and stop.

Default: 1Example: 1

presence_penaltynumber | nullableOptional

Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.

See more information about frequency and presence penalties.

Default: 0

seedinteger | nullableOptional

If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.

Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.

stopone of | nullableOptional

Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.

Default: null

string | nullableOptionalDefault: <|endoftext|>Example:

or

string[] · min: 1 · max: 4OptionalExample: ["\n"]

streamboolean | nullableOptional

Whether to stream back partial progress. If set, tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message. Example Python code.

Default: false

suffixstring | nullableOptional

The suffix that comes after a completion of inserted text.

This parameter is only supported for gpt-3.5-turbo-instruct.

Default: nullExample: test.

temperaturenumber | nullableOptional

What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.

We generally recommend altering this or top_p but not both.

Default: 1Example: 1

top_pnumber | nullableOptional

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.

We generally recommend altering this or temperature but not both.

Default: 1Example: 1

userstringOptional

A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.

Example: user-1234

Responses

200

OK

application/json

post

DefaultDefaultDefaultSelf-HostedSelf-HostedSelf-Hosted

curl https://api.portkey.ai/v1/completions \
  -H "Content-Type: application/json" \
  -H "x-portkey-api-key: $PORTKEY_API_KEY" \
  -H "x-portkey-virtual-key: $PORTKEY_PROVIDER_VIRTUAL_KEY" \
  -d '{
    "model": "gpt-3.5-turbo-instruct",
    "prompt": "Say this is a test",
    "max_tokens": 7,
    "temperature": 0
  }'

200

OK

{
  "id": "text",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 1,
      "logprobs": {
        "text_offset": [
          1
        ],
        "token_logprobs": [
          1
        ],
        "tokens": [
          "text"
        ],
        "top_logprobs": [
          {
            "ANY_ADDITIONAL_PROPERTY": 1
          }
        ]
      },
      "text": "text"
    }
  ],
  "created": 1,
  "model": "text",
  "system_fingerprint": "text",
  "object": "text_completion",
  "usage": {
    "completion_tokens": 1,
    "prompt_tokens": 1,
    "total_tokens": 1
  }
}

The request body for this endpoint is structured to generate text completions based on a given prompt and model selection. The response will be a Completion Object.

Pass the config parameters for the request in the headers as defined here.

Portkey automatically transforms the parameters for LLMs other than OpenAI. If some parameters don't exist in the other LLMs, they will be dropped.

SDK Usage

The completions.create method in the Portkey SDK allows you to generate text completions using various LLMs. This method provides a straightforward interface for requesting text completions similar to the OpenAI API.

Method Signature

NodeJS

portkey.completions.create(requestParams[configParams]);

Python

# with only request params
portkey.completions.create(requestParams);
# with request and config params
portkey.with_options(configParams).completions.create(requestParams);

For REST API examples, scroll here.

Parameters

1. requestParams (Object): Parameters for the completion request. These parameters should include the prompt and model, and are transformed automatically by Portkey for LLMs other than OpenAI. Unsupported parameters for other LLMs will be dropped.

2. configParams (Object): Additional configuration options for the request. This is an optional parameter that can include custom config options for this specific request. These will override the configs set in the Portkey Client.

Example Usage

NodeJS

import Portkey from 'portkey-ai';

// Initialize the Portkey client
const portkey = new Portkey({
    apiKey: "PORTKEY_API_KEY",  // Replace with your Portkey API key
    virtualKey: "VIRTUAL_KEY"   // Optional: For virtual key management
});

// Generate a text completion
async function getTextCompletion() {
    const completion = await portkey.completions.create({
        prompt: "Say this is a test",
        model: "gpt-3.5-turbo-instruct",
    });

    console.log(completion);
}
await getTextCompletion();

// Generate a streaming text completion
async function getTextCompletionStream(){
    const completionStream = await portkey.completions.create({
        prompt: "Continuously stream this test",
        model: "gpt-3.5-turbo-instruct",
        stream: true
    });

    for await (const chunk of completionStream) {
        console.log(chunk.content);
    }
}
await getTextCompletionStream();

// Generate a text completion with config params
async function getTextCompletionWithConfig() {
    const completion = await portkey.completions.create({
        prompt: "Say this is a test with specific config",
        model: "gpt-3.5-turbo-instruct",
    }, {config: "custom-config-123"});

    console.log(completion);
}
await getTextCompletionWithConfig();

Python

from portkey_ai import Portkey

# Initialize the Portkey client
portkey = Portkey(
    api_key="PORTKEY_API_KEY",  # Replace with your Portkey API key
    virtual_key="VIRTUAL_KEY"   # Optional: For virtual key management
)

# Generate a text completion
def get_text_completion():
    completion = portkey.completions.create(
        prompt="Say this is a test",
        model="gpt-3.5-turbo-instruct"
    )
    print(completion)

get_text_completion()

# Example with config parameters
def get_chat_completion_with_config():
    completion = portkey.with_options({'config': 'sample-7g5tr4'}).completions.create(
        messages=[{'role': 'user', 'content': 'Say this is a test'}],
        model='gpt-3.5-turbo-instruct'
    )
    print(completion)

get_chat_completion_with_config()

# Generate a streaming chat completion
async def get_chat_completion_stream():
    completion_stream = portkey.completions.create(
        messages=[{'role': 'user', 'content': 'Say this is a test'}],
        model='gpt-3.5-turbo-instruct',
        stream=True
    })

    for chunk in completion:
        print(chunk.choices[0].delta)

await get_chat_completion_stream()

REST API Example

In REST calls, x-portkey-api-key is a compulsory header, it can be paired with the following options for sending provider details:

1. x-portkey-provider & Authorization (or similar auth headers)

2. x-portkey-virtual-key

3. x-portkey-config

Example request using Provider + Auth:

curl "https://api.portkey.ai/v1/completions" \
  -H "Content-Type: application/json" \
  -H "x-portkey-api-key: $PORTKEY_API_KEY" \
  -H "x-portkey-provider: openai" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -d '{
    "model": "gpt-3.5-turbo-instruct",
    "prompt": "Hello!"
  }'

Example request using Virtual Key:

curl "https://api.portkey.ai/v1/completions" \
  -H "Content-Type: application/json" \
  -H "x-portkey-api-key: $PORTKEY_API_KEY" \
  -H "x-portkey-virtual-key: openai-virtual-key" \
  -d '{
    "model": "gpt-3.5-turbo-instruct",
    "prompt": "Hello!"
  }'

Example request using Config:

curl "https://api.portkey.ai/v1/completions" \
  -H "Content-Type: application/json" \
  -H "x-portkey-api-key: $PORTKEY_API_KEY" \
  -H "x-portkey-config: config-key" \
  -d '{
    "model": "gpt-3.5-turbo-instruct",
    "prompt": "Hello!"
  }'

You can send 3 other headers in your Portkey requests

• x-portkey-trace-id: Send trace id

• x-portkey-metadata: Send custom metadata

• x-portkey-cache-force-refresh: Force refresh cache for this request

Example request using these 3:

curl "https://api.portkey.ai/v1/completions" \
  -H "Content-Type: application/json" \
  -H "x-portkey-api-key: $PORTKEY_API_KEY" \
  -H "x-portkey-config: config-key" \
  -H "x-portkey-trace-id: $UNIQUE_TRACE_ID" \
  -H "x-portkey-metadata: {\"_user\":\"john\"}" \
  -H "x-portkey-cache-force-refresh: True" \
  -d '{
    "model": "gpt-3.5-turbo-instruct",
    "prompt": "Hello!"
  }'

Response Format

The response will conform to the Text Completions Object schema from the Portkey API, typically including the generated text based on the prompt and the selected model.