# xiaozhanAI

xiaozhanAI flagship chat model. 1.05M context, connected directly to the official OpenAI API, on the official Fast tier by default. Web search, image generation, tool calling and image input, with adjustable reasoning effort; very long prompts are priced in a separate tier. It can also write code in a cloud sandbox to produce Word, Excel, PowerPoint and PDF files: use it directly in AI Chat on this site, or over the API with the shell / code_interpreter tools of /v1/responses and /v1/containers to fetch the files.

- Model ID (the request body's `model` field): `xiaozhanAI`
- Category: Text chat
- Page: https://qd.zsopc.com/en/models/xiaozhanAI
- Endpoint: `https://qd.zsopc.com/v1/chat/completions`
- Context window: 1,050,000 tokens
- Default output limit per request: 128,000 tokens
- Capabilities: Image input · Tool calling · Thinking mode · Web search · JSON mode · Image generation
- Compatible protocols: OpenAI Chat Completions · OpenAI Responses
- Released: 2026-10-11
- Last updated: 2026-11-17

## Pricing

- Input: 121.32 credits (≈ ¥2.02 / ≈ $0.3) per 1M tokens
- Output: 606.6 credits (≈ ¥10.11 / ≈ $1.5) per 1M tokens
- Cached input: 12.13 credits (≈ ¥0.202 / ≈ $0.03) per 1M tokens
- Cache write: 151.65 credits (≈ ¥2.53 / ≈ $0.375) per 1M tokens
- Long-context tier (prompt ≥ 272,000 tokens): input 242.64 credits (≈ ¥4.04 / ≈ $0.6), output 909.9 credits (≈ ¥15.17 / ≈ $2.25)
- Per server-side tool call (web search etc.): 8.09 credits (≈ ¥0.135 / ≈ $0.02)
- Per output image: 170.66 credits (≈ ¥2.84 / ≈ $0.422)

Credits are the platform's only unit: 60 credits = ¥1 (machine-readable: `GET https://qd.zsopc.com/api/v1/config/currency`).
Each call first holds the most it could cost, then settles on actual usage and refunds the difference.

## Example call

```bash
curl https://qd.zsopc.com/v1/chat/completions \
  -H "Authorization: Bearer $PLATFORM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"xiaozhanAI","messages":[{"role":"user","content":"Hello"}]}'
```

## FAQ

### How do I call xiaozhanAI?

Set the model field of the request body to xiaozhanAI, send it to https://qd.zsopc.com/v1/chat/completions, and put your key (it starts with sk-gpushare-) in the Authorization: Bearer header. The official OpenAI, Anthropic and Google Gemini SDKs all work directly; just point base_url at this gateway.

### How much does the xiaozhanAI API cost?

Input: 121.32 credits (≈ ¥2.02 / ≈ $0.3) per 1M tokens; Output: 606.6 credits (≈ ¥10.11 / ≈ $1.5) per 1M tokens; Cached input: 12.13 credits (≈ ¥0.202 / ≈ $0.03) per 1M tokens; Cache write: 151.65 credits (≈ ¥2.53 / ≈ $0.375) per 1M tokens; Long-context tier (prompt ≥ 272,000 tokens): input 242.64 credits (≈ ¥4.04 / ≈ $0.6), output 909.9 credits (≈ ¥15.17 / ≈ $2.25); Per server-side tool call (web search etc.): 8.09 credits (≈ ¥0.135 / ≈ $0.02); Per output image: 170.66 credits (≈ ¥2.84 / ≈ $0.422). Prices are in credits: 60 credits = ¥1. Each call first holds the most it could cost, then settles on actual usage and refunds the difference.

### How large is xiaozhanAI's context window?

1,050,000 tokens, with a default output limit of 128,000 tokens per request.

### What can xiaozhanAI do?

Image input, Tool calling, Thinking mode, Web search, JSON mode, Image generation. Compatible protocols: OpenAI Chat Completions, OpenAI Responses.

## Related

- All models and live prices: https://qd.zsopc.com/en/models
- Quickstart: https://qd.zsopc.com/en/docs/quickstart
- FAQ: https://qd.zsopc.com/en/docs/faq
- OpenAPI: https://qd.zsopc.com/openapi.json
