POST
/
v1
/
completions
curl --request POST \
  --url https://api.pulze.ai/v1/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "<string>",
  "max_tokens": 123,
  "temperature": 0.5,
  "top_p": 123,
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "<string>",
        "description": "<string>",
        "parameters": {
          "type": "object",
          "properties": {},
          "required": [
            "<string>"
          ]
        }
      }
    }
  ],
  "tool_choice": "none",
  "n": 2,
  "stream": true,
  "logprobs": 2,
  "stop": "<string>",
  "presence_penalty": 0,
  "frequency_penalty": 0,
  "best_of": 2,
  "logit_bias": {},
  "response_format": {
    "type": "text"
  },
  "prompt": "<string>"
}'
{
  "choices": [
    {
      "index": 123,
      "finish_reason": "<string>",
      "text": "<string>",
      "logprobs": 123
    }
  ],
  "created": 0,
  "metadata": {
    "app_id": "<string>",
    "model": {
      "model": "<string>",
      "provider": "<string>",
      "owner": "<string>",
      "namespace": "<string>",
      "at": "<string>"
    },
    "costs": {
      "total_tokens": 123,
      "prompt_tokens": 123,
      "completion_tokens": 123
    },
    "cost_savings": {
      "total_tokens": 123,
      "prompt_tokens": 123,
      "completion_tokens": 123
    },
    "generated_artifacts": {
      "items": [
        {}
      ]
    },
    "search_results": {
      "items": [
        {}
      ]
    },
    "latency": 123,
    "labels": {},
    "error": "<string>",
    "scores": {
      "best_models": [],
      "candidates": [
        {}
      ]
    },
    "score": 123,
    "temperature": 123,
    "max_tokens": 0,
    "status_code": 123,
    "retries": 0,
    "extra": {},
    "warning": "<string>"
  },
  "id": "<string>",
  "usage": {
    "total_tokens": 123,
    "prompt_tokens": 123,
    "completion_tokens": 123
  },
  "model": "<string>",
  "object": "text_completion"
}

This endpoint supports:

Weights

Labels

Policies

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
​
prompt
required

The prompt text sent (for a /completions request)

Minimum length: 1
​
model
string | null
default:pulze

https://docs.pulze.ai/overview/models Specify the model you'd like Pulze to use. (optional). Can be the full model name, or a subset for multi-matching.

Defaults to our dynamic routing, i.e. best model for this request.

​
max_tokens
integer | null

The maximum number of tokens that the response can contain.

​
temperature
number | null
default:1

Optionally specify the temperature for this request only. Leave empty to allow Pulze to guess it for you.

Required range: 0 <= x <= 1
​
top_p
number | null
default:1

https://octo.ai/docs/text-gen-solution/rest-api#input-parameters A value between 0.0 and 1.0 that controls the probability of the model generating a particular token.

​
tools
object[] | null
​
tool_choice
default:none
Available options:
none,
auto
​
n
integer | null

How many completions to generate for each prompt. @default 1

Required range: x >= 1
​
stream
boolean | null
default:false

Specify if you want the response to be streamed or to be returned as a standard HTTP request. Currently we only support streaming for OpenAI-compatible models.

​
logprobs
integer | null

COMING SOON https://platform.openai.com/docs/api-reference/completions/create#completions/create-logprobs Include the log probabilities on the logprobs most likely tokens, as well the chosen tokens.

Required range: 0 <= x <= 5
​
stop
default:

Stop responding when this sequence of characters is generated. Leave empty to allow the model to decide.

​
presence_penalty
number | null

https://platform.openai.com/docs/api-reference/completions/create#completions/create-presence_penalty Increase the model's likelihood to talk about new topics

Required range: -2 <= x <= 2
​
frequency_penalty
number | null

https://platform.openai.com/docs/api-reference/completions/create#completions/create-frequency_penalty Increase the model's likelihood to not repeat tokens/words

Required range: -2 <= x <= 2
​
best_of
integer | null

The number of responses to generate. Out of those, it will return the best n.

Required range: x >= 1
​
logit_bias
object | null

COMING SOON https://platform.openai.com/docs/api-reference/completions/create#completions/create-logit_bias Modify the likelihood of specified tokens appearing in the completion.

See here for a detailed explanation on how to use: https://help.openai.com/en/articles/5247780-using-logit-bias-to-define-token-probability

​
response_format
object | null

https://platform.openai.com/docs/api-reference/chat/create#chat-create-response_format An object specifying the format that the model must output. Must be one of "text" or "json_object". Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. To help ensure you don't forget, the API will throw an error if the string "JSON" does not appear somewhere in the context.

Response

200
application/json
Successful Response

The response returned to the user by the (text) Completions endpoint

​
choices
object[]
required
​
model
string
required

The fully qualified model name used by PulzeEngine

​
object
enum<string>
required

The type of response object

Available options:
text_completion,
chat.completion
​
created
integer
default:0

Creation timestamp -- in milliseconds (!)

​
metadata
object

Metadata of the response

​
id
string

This ID gets generated by the database when we save the request

​
usage
object

Tokens used

Was this page helpful?

Raise issue