Developer Documentation

Fully compatible with the OpenAI API format — just change base_url and you're ready to go.

⚡ Migrate in 3 Minutes

Already using the OpenAI SDK? Switch to itapi.ai with one line of code.

Before (OpenAI)

client = OpenAI(
    api_key="sk-...",
    # default base_url
)

After (itapi.ai)

client = OpenAI(
    api_key="it_...",
    base_url="https://www.itapi.ai/v1"
)

Sign up and get your API key at itapi.ai
Set base_url to https://www.itapi.ai/v1
Replace your key — that's it. Every other line of your code stays the same.

Get Your API Key →

Authentication

API Key

All API requests require an API key passed in the Authorization header using the Bearer scheme. Keys are prefixed with it_.

Authorization: Bearer it_your_api_key_here

Create and manage your API keys from the dashboard.

⚠️ Security: Never expose your API key in client-side code or public repositories. Use environment variables (e.g. ITAPI_KEY) in production.

Quick Start

Base URL

All endpoints are served under this base path:

https://www.itapi.ai/v1

Code Examples

All examples use the standard OpenAI SDK. No custom libraries required — just point the client at itapi.ai.

Python (OpenAI SDK)

from openai import OpenAI

client = OpenAI(
    base_url="https://www.itapi.ai/v1",
    api_key="it_your_api_key_here"
)

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Explain quantum computing in simple terms."}
    ]
)

print(response.choices[0].message.content)

Node.js (OpenAI SDK)

import OpenAI from 'openai'

const client = new OpenAI({
  baseURL: 'https://www.itapi.ai/v1',
  apiKey: 'it_your_api_key_here'
})

const response = await client.chat.completions.create({
  model: 'claude-3-5-sonnet-20241022',
  messages: [
    { role: 'system', content: 'You are a helpful assistant.' },
    { role: 'user', content: 'Explain quantum computing in simple terms.' }
  ]
})

console.log(response.choices[0].message.content)

cURL

curl https://www.itapi.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer it_your_api_key_here" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Explain quantum computing in simple terms."}
    ],
    "temperature": 0.7,
    "max_tokens": 512
  }'

Go (OpenAI SDK)

package main

import (
    "context"
    "fmt"
    "github.com/openai/openai-go"
    "github.com/openai/openai-go/option"
)

func main() {
    client := openai.NewClient(
        option.WithAPIKey("it_your_api_key_here"),
        option.WithBaseURL("https://www.itapi.ai/v1"),
    )

    completion, err := client.Chat.Completions.New(
        context.Background(),
        openai.ChatCompletionNewParams{
            Model: openai.F("gpt-4o"),
            Messages: openai.F([]openai.ChatCompletionMessageParamUnion{
                openai.SystemMessage("You are a helpful assistant."),
                openai.UserMessage("Explain quantum computing in simple terms."),
            }),
        },
    )
    if err != nil {
        panic(err)
    }

    fmt.Println(completion.Choices[0].Message.Content)
}

Streaming

Enable Server-Sent Events (SSE) streaming by setting stream: true. Streamed chunks follow the standard OpenAI delta format.

Python — Streaming

from openai import OpenAI

client = OpenAI(
    base_url="https://www.itapi.ai/v1",
    api_key="it_your_api_key_here"
)

stream = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Tell me a short story."}],
    stream=True
)

for chunk in stream:
    content = chunk.choices[0].delta.content
    if content:
        print(content, end="", flush=True)
print()  # final newline

Node.js — Streaming

import OpenAI from 'openai'

const client = new OpenAI({
  baseURL: 'https://www.itapi.ai/v1',
  apiKey: 'it_your_api_key_here'
})

const stream = await client.chat.completions.create({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'Tell me a short story.' }],
  stream: true
})

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || '')
}
console.log()

cURL — Streaming

curl https://www.itapi.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer it_your_api_key_here" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {"role": "user", "content": "Tell me a short story."}
    ],
    "stream": true
  }'

API Reference

POST/v1/chat/completions

Creates a model response for a given chat conversation. Follows the OpenAI Chat Completions specification.

Parameter	Type	Required	Description
model	string	Yes	Model ID to use. Examples: gpt-4o, gpt-4o-mini, claude-3-5-sonnet-20241022, claude-3-opus-20240229, deepseek-chat, gemini-2.0-flash. See the Models page for the full list.
messages	array	Yes	Array of message objects, each with role (system \| user \| assistant \| function \| tool) and content (string or array of content parts).
stream	boolean	No	When true, responses are streamed as Server-Sent Events (SSE). Defaults to false.
temperature	number	No	Sampling temperature between 0 and 2. Higher values produce more random outputs. Default varies by model.
max_tokens	integer	No	Maximum number of tokens to generate in the completion. Useful for controlling cost and response length.
top_p	number	No	Nucleus sampling parameter between 0 and 1. Only tokens with cumulative probability ≥ top_p are considered. Default is 1.
frequency_penalty	number	No	Penalizes repeated tokens. Values range from -2.0 to 2.0. Positive values reduce repetition.
presence_penalty	number	No	Penalizes tokens that have already appeared. Values range from -2.0 to 2.0. Positive values encourage new topics.
stop	string \| array	No	Up to 4 sequences where the API will stop generating further tokens.
n	integer	No	Number of completion choices to generate for each input message. Default is 1.
seed	integer	No	If specified, the system attempts to produce deterministic results. Useful for testing and reproducibility.
user	string	No	Unique identifier for your end-user. Helps with monitoring and abuse detection.
tools	array	No	List of tool/function definitions the model may call. Follows the OpenAI function-calling schema.
tool_choice	string \| object	No	Controls how the model calls tools. Can be 'none', 'auto', 'required', or a specific tool object.
response_format	object	No	Specifies the output format. Use { type: 'json_object' } for JSON mode (must include 'json' in your prompt).
logprobs	boolean	No	Whether to return log probabilities of the output tokens. Default is false.
top_logprobs	integer	No	Number of most likely tokens to return at each position when logprobs is true. Integer between 0 and 20.

Request Body

{
  "model": "gpt-4o",
  "messages": [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Hello!"}
  ],
  "temperature": 0.7,
  "max_tokens": 1024,
  "top_p": 1,
  "stream": false
}

Response

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1700000000,
  "model": "gpt-4o",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 9,
    "total_tokens": 34
  }
}

Rate Limits

Tier	Requests / Minute	Tokens / Minute
Free	10	20,000
Starter	60	100,000
Pro	300	500,000
Enterprise	Custom	Custom

Rate-limit headers (x-ratelimit-*) are included in every response. Need higher limits? Contact us.

Error Codes

Errors follow the OpenAI error format with an error object containing message, type, and code fields.

HTTP Status	Code	Description
400	invalid_request_error	Malformed request body, missing required fields, or invalid parameter values.
401	authentication_error	Invalid or missing API key. Check your Authorization header and ensure the key is active.
402	insufficient_quota	Your account has run out of credits or hit your usage limit. Top up from the dashboard.
429	rate_limit_exceeded	Too many requests. Wait before retrying — check the Retry-After header for the backoff time.
500	api_error	Unexpected server error. Itapi.ai engineers are automatically notified. Retry with exponential backoff.
503	server_overloaded	The service is temporarily overloaded. Retry after a short delay.