Native API Calls (SDK Examples)

Replace {baseUrl} with your platform API root, without a trailing / or /v1, and sk-your-api-key with your model API key. Select models supported by your token's group.

Python (OpenAI SDK)

pip install openai

from openai import OpenAI

client = OpenAI(
    api_key="sk-your-api-key",
    base_url="{baseUrl}/v1",
)

resp = client.chat.completions.create(
    model="gpt-5.2",
    messages=[
        {"role": "system", "content": "You are a concise assistant."},
        {"role": "user", "content": "Explain intelligent routing in one sentence."},
    ],
)
print(resp.choices[0].message.content)

Streaming

stream = client.chat.completions.create(
    model="gpt-5.2",
    messages=[{"role": "user", "content": "Write a four-line poem about a tree."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

Node.js (openai package)

npm install openai

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "sk-your-api-key",
  baseURL: "{baseUrl}/v1",
});

const resp = await client.chat.completions.create({
  model: "gpt-5.2",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(resp.choices[0].message.content);

Anthropic SDK

pip install anthropic

from anthropic import Anthropic

client = Anthropic(
    api_key="sk-your-api-key",
    base_url="{baseUrl}",  # Do not append /v1
)

msg = client.messages.create(
    model="claude-sonnet-4-5-20250929",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello"}],
)
print(msg.content[0].text)

Google GenAI SDK (native Gemini)

pip install google-genai

from google import genai

client = genai.Client(
    api_key="sk-your-api-key",
    http_options={"base_url": "{baseUrl}"},
)

resp = client.models.generate_content(
    model="gemini-2.5-pro",
    contents="Hello",
)
print(resp.text)

Image and video generation

For the OpenAI-compatible image endpoint, create an OpenAI client:

from openai import OpenAI

client = OpenAI(api_key="sk-your-api-key", base_url="{baseUrl}/v1")
resp = client.images.generate(
    model="gemini-3-pro-image",
    prompt="A red fox standing in the snow, photorealistic",
    size="1024x1024",
)
print(resp.data[0].url)

Video generation uses asynchronous tasks: submit a request, save the returned task_id, and poll for results. The platform provides shared video generation and task-query endpoints as well as provider-specific endpoints for Kling, Sora, Jimeng, and Volcengine. See the video generation API for parameters.

MiniMax H3/H3-Max, H3 2K upgrades, and Context-IR use native asynchronous /v2 endpoints. See the MiniMax H3 integration guide. The returned task_id is a platform task ID; read task.content.url for video or task.content.prompt for Context-IR.

Endpoint reference

Endpoint	Method	Purpose
/v1/models	GET	List available models
/v1/chat/completions	POST	Chat completions
/v1/responses	POST	Responses API
/v1/messages	POST	Native Anthropic messages
/v1/embeddings	POST	Text embeddings
/v1/audio/speech	POST	Text to speech
/v2/video_generation	POST	MiniMax H3/H3-Max video generation
/v2/video_regeneration	POST	H3 2K upgrade
/v2/h3_context_ir	POST	Context-IR prompt generation
/v2/query/video_generation/{task_id}	GET	Query MiniMax H3 tasks
/v1beta/models	GET	Native Gemini model list
/api/user/self	GET	Account information; requires a management access token
/api/log/self	GET	Request logs; requires a management access token