Quickstart

Step 1: Create an account

Register an account with AGTCloud; if you already have one, sign in directly.

Step 2: Get an API key

1. Open API Keys.
2. Select Create API Key.
3. Copy the API key and store it securely.

Step 3: Check your balance

API calls consume account balance. Before sending a request, open Billing and top-up and confirm that your account has available credit. Available top-up methods and crediting results are shown in the console.

Step 4: Send your first API requests

The examples use the current site's API address and configured example models. Confirm model access in the Model marketplace before calling an endpoint.

Chat with an LLM

The Chat Completions-compatible API can be called with the OpenAI SDK or an HTTP request.

from openai import OpenAI

client = OpenAI(
    api_key="your-api-key",
    base_url="https://api.agtcloud.cn/v1",
)

response = client.chat.completions.create(
    model="deepseek-v4-flash",
    messages=[
        {"role": "user", "content": "What can you help me build?"}
    ],
)

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

The generated text is returned in choices[0].message.content. See Chat Completions for request and response details.

Generate an image

curl 'https://api.agtcloud.cn/v1/images/generations' \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer your-api-key' \
  --data '{
    "model": "qwen-image",
    "prompt": "A futuristic city floating above a sea of clouds"
  }'

Generate a video

curl 'https://api.agtcloud.cn/v1/video/generations' \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer your-api-key' \
  --data '{
    "model": "doubao-seedance-2-5-260628",
    "prompt": "A spacecraft flying through a blue nebula"
  }'

After the request succeeds, save the returned task_id, then query the task status and result:

curl 'https://api.agtcloud.cn/v1/video/generations/your-task-id' \
  -H 'Authorization: Bearer your-api-key'

See Create video and Retrieve video for complete fields and task states.

To test a request in your browser, open the Playground.

Step 5: Explore models

Browse the Model marketplace and confirm each model's supported protocol, parameters, and account access before using it.