# Moonshot AI models: APIs and prices

Kimi models: long-context MoE. XiaoZhan AIhub offers 5 Moonshot AI models (Text generation). Call them with one API key through the OpenAI, Anthropic or Gemini SDK; prices are in credits (60 credits = ¥1) and every model page lists the full price.

- Page: https://qd.zsopc.com/en/vendors/moonshot
- Models: 5
- Last updated: 2026-11-17

## Text generation

### Kimi K2.5

Moonshot Kimi K2.5. 256K context, with prompt caching.

- Model ID: `kimi-k2.5`
- Page: https://qd.zsopc.com/en/models/kimi-k2.5 (Markdown: https://qd.zsopc.com/en/models/kimi-k2.5.md)
- Context window: 256,000 tokens
- Updated: 2026-11-17
- Price:
  - Input: 242.64 credits (≈ ¥4.04 / ≈ $0.6) per 1M tokens
  - Output: 1,011 credits (≈ ¥16.85 / ≈ $2.5) per 1M tokens
  - Cached input: 40.44 credits (≈ ¥0.674 / ≈ $0.1) per 1M tokens

### Kimi K2.6

Moonshot Kimi K2.6. 256K context.

- Model ID: `kimi-k2.6`
- Page: https://qd.zsopc.com/en/models/kimi-k2.6 (Markdown: https://qd.zsopc.com/en/models/kimi-k2.6.md)
- Context window: 256,000 tokens
- Updated: 2026-11-17
- Price:
  - Input: 242.64 credits (≈ ¥4.04 / ≈ $0.6) per 1M tokens
  - Output: 1,011 credits (≈ ¥16.85 / ≈ $2.5) per 1M tokens
  - Cached input: 40.44 credits (≈ ¥0.674 / ≈ $0.1) per 1M tokens

### Kimi K2.7 Code

Moonshot Kimi K2.7, the coding-specialised version. 256K context.

- Model ID: `kimi-k2.7-code`
- Page: https://qd.zsopc.com/en/models/kimi-k2.7-code (Markdown: https://qd.zsopc.com/en/models/kimi-k2.7-code.md)
- Context window: 256,000 tokens
- Updated: 2026-11-17
- Price:
  - Input: 242.64 credits (≈ ¥4.04 / ≈ $0.6) per 1M tokens
  - Output: 1,011 credits (≈ ¥16.85 / ≈ $2.5) per 1M tokens
  - Cached input: 40.44 credits (≈ ¥0.674 / ≈ $0.1) per 1M tokens

### Kimi K3

Moonshot Kimi K3. 256K context, with prompt caching.

- Model ID: `kimi-k3`
- Page: https://qd.zsopc.com/en/models/kimi-k3 (Markdown: https://qd.zsopc.com/en/models/kimi-k3.md)
- Context window: 256,000 tokens
- Updated: 2026-11-17
- Price:
  - Input: 1,200 credits (≈ ¥20 / ≈ $2.97) per 1M tokens
  - Output: 6,000 credits (≈ ¥100 / ≈ $14.84) per 1M tokens
  - Cached input: 120 credits (≈ ¥2 / ≈ $0.297) per 1M tokens
  - Cache write: 1,200 credits (≈ ¥20 / ≈ $2.97) per 1M tokens

### Kimi K3 1013

Moonshot Kimi K3 on a separate line. 256K context, with prompt caching.

- Model ID: `kimi-k3-1013`
- Page: https://qd.zsopc.com/en/models/kimi-k3-1013 (Markdown: https://qd.zsopc.com/en/models/kimi-k3-1013.md)
- Context window: 256,000 tokens
- Updated: 2026-11-17
- Price:
  - Input: 1,200 credits (≈ ¥20 / ≈ $2.97) per 1M tokens
  - Output: 6,000 credits (≈ ¥100 / ≈ $14.84) per 1M tokens
  - Cached input: 120 credits (≈ ¥2 / ≈ $0.297) per 1M tokens
  - Cache write: 1,200 credits (≈ ¥20 / ≈ $2.97) per 1M tokens

Prices are in credits, 60 credits = ¥1. The prices above are what is charged today (limited-time discounts included); ≈¥ / ≈$ use the platform's published rates.

## FAQ

### How do I call Moonshot AI models?

Create an API key on XiaoZhan AIhub, point your SDK's base_url at https://qd.zsopc.com/v1 and put the model ID from the list above in the model field. The OpenAI, Anthropic and Gemini SDKs all work.

### How are Moonshot AI models billed?

Each model is billed its own way: text models per input and output token, image models per image, video models per second or per token. Prices are in credits (60 credits = ¥1); each model page lists the full price.
