Documentation

Welcome to the CTIM AI documentation. This guide will help you get started quickly and make full use of our AI infrastructure services.

About CTIM AI

Learn about our basic information and service details.

Overview

CTIM AI is a unified API gateway that provides access to all major AI models through a single OpenAI-compatible endpoint. Switch between models by changing one parameter — no code changes needed.

API Address

Supported Models

• Model List — Full list of available models and providers
• Model Pricing — Transparent per-token pricing for all models

Getting Started

Detailed user guides and operation steps to start making API calls.

Quick Start

1. 1Contact us via Telegram or email to get your API key — typically within 2 hours.
2. 2Set base URL to https://api.ctimsoft.net/ai and replace your API key.
3. 3Start making requests — the OpenAI SDK works out of the box.

OpenAI SDK Usage

Change the base_url, everything else stays the same.

from openai import OpenAI

client = OpenAI(
    api_key="API_KEY",
    base_url="https://api.ctimsoft.net/ai"
)

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

curl -X POST https://api.ctimsoft.net/ai/chat/completions \
  -H "Authorization: Bearer API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Anthropic SDK Usage

Use our gateway with the Anthropic Messages API — just change the base URL.

import anthropic

client = anthropic.Anthropic(
    api_key="API_KEY",
    base_url="https://api.ctimsoft.net/ai"
)

message = client.messages.create(
    model="claude-sonnet-4-20250514",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello"}]
)
print(message.content[0].text)

Response Format

CTIM AI gateway is fully compatible with the OpenAI API — response structures are identical. Here's what you'll get back:

Success Response (200)

Standard chat completion response:

{
  "id": "chatcmpl-9XyZ...b",
  "object": "chat.completion",
  "created": 1720000000,
  "model": "gpt-4o",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?",
        "refusal": null
      },
      "logprobs": null,
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 8,
    "completion_tokens": 12,
    "total_tokens": 20,
    "prompt_tokens_details": { "cached_tokens": 0 },
    "completion_tokens_details": { "reasoning_tokens": 0 }
  },
  "service_tier": "default",
  "system_fingerprint": "fp_ctim"
}

Response Fields

Streaming Response

When stream: true is set, the response is delivered as Server-Sent Events (SSE). Each line starts with data: followed by a JSON chunk:

data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","created":1720000000,"model":"gpt-4o","choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null}]}

data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","created":1720000000,"model":"gpt-4o","choices":[{"index":0,"delta":{"content":"Hello"},"finish_reason":null}]}

data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","created":1720000000,"model":"gpt-4o","choices":[{"index":0,"delta":{"content":"!"},"finish_reason":null}]}

data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","created":1720000000,"model":"gpt-4o","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}

data: [DONE]

Each chunk contains a delta field with incremental content. The final chunk has finish_reason set and empty delta.content.

Error Response

All errors follow the OpenAI error format:

{
  "error": {
    "message": "Invalid API key provided",
    "type": "invalid_request_error",
    "param": "api_key",
    "code": "invalid_api_key"
  }
}

Common HTTP Status Codes

Platform Operations

Manage your API keys, monitor usage, and configure access controls.

API Key Management

Each API key can be configured with:

• Model-level access control (allow/deny specific models)
• Rate limits (requests per minute, tokens per day)
• Usage alerts (notify when balance drops below threshold)
• IP whitelist (restrict access to specific IP ranges)

Rate Limits & Quotas

Default rate limits apply per API key. Contact us for custom limits or enterprise plans.

Quick Navigation

Recommended path for new users:

Frequently Asked Questions

Account Related

• How do I get an API key?
• What payment methods do you support?

API Usage

• Can I use the OpenAI SDK?
• Can I use the Anthropic SDK?
• What are the rate limits?

Billing

• How is pricing calculated?
• How do I top up my balance?
• Do you offer invoicing?

Technical Support

If you encounter problems during use, you can get help through the following methods:

• Telegram — Fastest response, 24/7
• Email — For detailed inquiries and enterprise requests