AI API PLATFORM · CONTROLLED DEVELOPMENT
Developer-friendly AI API access
Developer-friendly AI API access, transparent token pricing and usage tracking. DeepSeek text is available in controlled development; broader provider, model and modality support is a future direction.
Start with a small text request
Use a funded account and a server-side API key. Install the Python openai package. The operator must confirm the HTTPS API base URL before use; this preview has no announced production endpoint.
import os
from openai import OpenAI
# Set AI_GATEWAY_BASE_URL to the operator-confirmed HTTPS API URL ending in /v1.
# No public production API domain has been announced yet.
client = OpenAI(
api_key=os.environ["AI_GATEWAY_API_KEY"],
base_url=os.environ["AI_GATEWAY_BASE_URL"],
max_retries=0,
)
response = client.chat.completions.create(
model="deepseek-flash",
messages=[{"role": "user", "content": "Hello, world!"}],
max_tokens=32,
stream=False,
)
print(response.choices[0].message.content)
print(response.usage)
Simple integration. Clear usage.
Familiar API patterns
Use chat completions with system, user and assistant text messages. Only the documented subset is supported.
Transparent token-based pricing
Separate input cache hits, input cache misses and output tokens. Review peak and off-peak sales rates before calling.
Your account, your records
Create and revoke customer-bound API keys, review Usage and Billing, and contact support from your signed-in portal.
Planned / Not available yet
Our direction is a multi-provider, multi-model AI API platform, eventually extending beyond text to image, audio and video. These capabilities are not implemented or available yet. No additional provider support, delivery date, pricing or API compatibility is promised.
Know the rate before you call
Customer sales prices in CNY per 1,000,000 tokens. Your account balance remains CNY. There is no subscription or automatic payment feature.
View pricing details →Output tokens · per 1M
- Peak
- CNY 10.40
- Off-peak
- CNY 5.20