OpenAI Text generation - ZnapAI Documentation

Request

curl --location 'https://api.znapai.com/v1/chat/completions' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer $ZnapAI_API_KEY' \
--header 'spend-logs-metadata: {"user_id": "user-123", "project_id": "proj_abc", "env": "production"}' \
--data '{
    "model": "gpt-4o-mini",
    "messages": [
      {
        "role": "user",
        "content": "Hello!"
      }
    ]
  }'

import openai
client = openai.OpenAI(
    api_key="$ZnapAI_API_KEY",
    base_url="https://api.znapai.com/"
)

completion = client.chat.completions.create(
    model="gpt-4o-mini",
    messages = [
        {
            "role": "user",
            "content": "hello"
        }
    ]
)

print(completion)

import OpenAI from "openai";
const openai = new OpenAI({
  apiKey: "$ZnapAI_API_KEY",
  baseURL: "https://api.znapai.com/"
});

const completion = await openai.chat.completions.create({
    model: "gpt-4o-mini",
    messages: [
        {
            role: "user",
            content: "hello",
        },
    ]
});

console.log(completion);

Response

{
  "id": "chatcmpl-B8rLGf4crBdVhX7a13Ae37NI9h2Re",
  "created": 1741451370,
  "model": "gpt-4o-mini",
  "object": "chat.completion",
  "system_fingerprint": "fp_ded0d14823",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "Hello! How can I assist you today?",
        "role": "assistant",
        "tool_calls": null,
        "function_call": null
      }
    }
  ],
  "usage": {
    "completion_tokens": 9,
    "prompt_tokens": 9,
    "total_tokens": 18,
    "completion_tokens_details": {
      "accepted_prediction_tokens": 0,
      "audio_tokens": 0,
      "reasoning_tokens": 0,
      "rejected_prediction_tokens": 0
    },
    "prompt_tokens_details": {
      "audio_tokens": 0,
      "cached_tokens": 0
    }
  },
  "service_tier": null,
  "prompt_filter_results": [
    {
      "prompt_index": 0,
      "content_filter_results": {
        "hate": {
          "filtered": false,
          "severity": "safe"
        },
        "jailbreak": {
          "filtered": false,
          "detected": false
        },
        "self_harm": {
          "filtered": false,
          "severity": "safe"
        },
        "sexual": {
          "filtered": false,
          "severity": "safe"
        },
        "violence": {
          "filtered": false,
          "severity": "safe"
        }
      }
    }
  ]
}

Parameters

header

An optional header used for spend logging metadata, containing JSON properties like user_id, project_id, and env.

string

required

Name of the model to use (for example: gpt-4o-mini). To see the complete list of supported chat models, visit: https://znapai.com/models/chat

array

required

A list of messages comprising the conversation so far.

Hide messages[]

string

default:"user"

required

Role type

user - User message
assistant - AI response (for multi-turn)
system - System prompt

string

required

Message contentYour question or message

Example:

[{"role": "user", "content": "Hello, please introduce yourself"}]

Advanced usage:Add system prompt (to define AI behavior):

[
  {"role": "system", "content": "You are a professional Python tutor"},
  {"role": "user", "content": "How do I learn programming?"}
]

number

default:"1.0"

Controls output randomness, range 0-2

Lower values (e.g., 0.2) make output more deterministic
Higher values (e.g., 1.8) make output more random

number

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.

integer

Maximum number of tokens to generateDifferent models have different maximum limits, please refer to specific model documentation

number

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.

number

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.

integer

How many chat completion choices to generate for each input message.

boolean

If set, partial message deltas will be sent, like in ChatGPT.

string | array

Up to 4 sequences where the API will stop generating further tokens.

Params to Avoid

Param	Reason
`stream_options`	Not supported by non-OpenAI models
`seed`	Not supported by non-OpenAI models
`logprobs`	Not supported by non-OpenAI models
`top_logprobs`	Not supported by non-OpenAI models
`logit_bias`	Not supported by non-OpenAI models
`spend-logs-metadata`	This metadata must be passed as an HTTP header, not in the JSON request body

​Request

​Response

​Parameters

​Params to Avoid

Request

Response

Parameters

Params to Avoid