## The Multi-Provider Problem You want to use DeepSeek R1 for reasoning, Kimi for long-context tasks, and JiMeng for image generation. Here's what that normally requires: - **DeepSeek**: Chinese phone number, Alipay/WeChat payment - **Kimi (Moonshot)**: Separate account, Chinese ID verification - **Doubao (ByteDance)**: Volcengine account, Chinese business entity - **Qwen (Alibaba)**: Alibaba Cloud account, regional restrictions - **JiMeng**: ByteDance platform access, Chinese payment method That's five accounts, five API keys, five billing systems, and five sets of documentation — most requiring Chinese identity verification. ## The Solution: One API Key AI API Marketplace provides a single, OpenAI-compatible endpoint for all of these models. One signup, one API key, one credit balance. ```python from openai import OpenAI client = OpenAI( api_key="YOUR_API_KEY", base_url="https://api.aigcto.cc/v1" ) # DeepSeek R1 for reasoning reasoning = client.chat.completions.create( model="deepseek-r1", messages=[{"role": "user", "content": "Prove that sqrt(2) is irrational"}] ) # DeepSeek Chat for quick tasks chat = client.chat.completions.create( model="deepseek-chat", messages=[{"role": "user", "content": "Summarize this article..."}] ) # JiMeng for image generation image = client.images.generate( model="jimeng-image", prompt="A mountain landscape at dawn, oil painting style", size="1024x1024" ) ``` Same client, same API key, different models. Switch between them by changing a single string. ## Model Comparison | Model | Best For | Speed | Cost | |---|---|---|---| | **DeepSeek R1** | Complex reasoning, math, code | Medium | Low | | **DeepSeek Chat** | General chat, summarization | Fast | Very low | | **Kimi** | Long documents, 200K+ context | Medium | Low | | **Doubao** | Chinese NLP, balanced tasks | Fast | Low | | **Qwen** | Multilingual, Chinese-specific | Fast | Low | | **JiMeng** | Image generation | Medium | Per image | ## Quick Start ### 1. Sign Up Create an account at [aimarket.aigcto.cc/register](https://aimarket.aigcto.cc/register). Takes 30 seconds — email only, no credit card. ### 2. Add Credits Top up your balance. 1,000 credits = $1 USD. No minimums, no expiration. ### 3. Generate an API Key Go to Dashboard > API Keys and create a new key. ### 4. Start Calling ```bash curl https://api.aigcto.cc/v1/chat/completions \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "deepseek-r1", "messages": [{"role": "user", "content": "Hello!"}], "stream": true }' ``` Streaming works out of the box — same SSE format as OpenAI. ### 5. Use Any OpenAI-Compatible Library Since the API is fully OpenAI-compatible, you can use: - **Python**: `openai` SDK - **Node.js**: `openai` npm package - **LangChain**: Set the base URL and model name - **Any HTTP client**: Standard REST calls ## Why Unified Access Matters **For prototyping.** Test multiple models against the same prompt without juggling credentials. **For production.** One billing system, one rate limit policy, one dashboard for monitoring usage across all models. **For cost optimization.** Route simple queries to cheaper models (DeepSeek Chat) and complex tasks to stronger ones (DeepSeek R1) — all through the same API. **For global teams.** Team members outside China can access Chinese AI models without any of the registration friction. [Get your API key](https://aimarket.aigcto.cc/register) and start using every model from one place.