# Google models: APIs and prices

Gemini models, natively multimodal with very long context. XiaoZhan AIhub offers 13 Google models (Text generation, Image generation, Video 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/google
- Models: 13
- Last updated: 2026-11-17

## Text generation

### Gemini 3.1 Pro

Google Gemini 3.1 Pro. 2M context, flagship reasoning and multimodal. Served over the OpenAI-compatible protocol.

- Model ID: `gemini-3.1-pro-low`
- Page: https://qd.zsopc.com/en/models/gemini-3.1-pro-low (Markdown: https://qd.zsopc.com/en/models/gemini-3.1-pro-low.md)
- Context window: 2,000,000 tokens
- Updated: 2026-11-17
- Price:
  - Input: 808.8 credits (≈ ¥13.48 / ≈ $2) per 1M tokens
  - Output: 4,853 credits (≈ ¥80.88 / ≈ $12) per 1M tokens
  - Cached input: 80.88 credits (≈ ¥1.35 / ≈ $0.2) per 1M tokens
  - Long-context tier (prompt ≥ 200,001 tokens): input 1,618 credits (≈ ¥26.96 / ≈ $4), output 7,279 credits (≈ ¥121.32 / ≈ $18)

### Gemini 3.1 Pro Preview 1020

Google Gemini 3.1 Pro Preview (1020 line). 1M context, thinking on by default, Google Search supported, billed at Google's list price; inputs over 200K tokens use the long-context tier. OpenAI-compatible and native Gemini protocols.

- Model ID: `gemini-3.1-pro-preview-1020`
- Page: https://qd.zsopc.com/en/models/gemini-3.1-pro-preview-1020 (Markdown: https://qd.zsopc.com/en/models/gemini-3.1-pro-preview-1020.md)
- Context window: 1,000,000 tokens
- Updated: 2026-11-17
- Price:
  - Input: 808.8 credits (≈ ¥13.48 / ≈ $2) per 1M tokens
  - Output: 4,853 credits (≈ ¥80.88 / ≈ $12) per 1M tokens
  - Cached input: 80.88 credits (≈ ¥1.35 / ≈ $0.2) per 1M tokens
  - Long-context tier (prompt ≥ 200,001 tokens): input 1,618 credits (≈ ¥26.96 / ≈ $4), output 7,279 credits (≈ ¥121.32 / ≈ $18)

### Gemini 3.8 Flash

Google Gemini 3.8 Flash. 1M context, the strongest Flash tier to date, for long-horizon coding and autonomous agents, thinking on by default. OpenAI-compatible and native Gemini protocols.

- Model ID: `gemini-3.8-flash`
- Page: https://qd.zsopc.com/en/models/gemini-3.8-flash (Markdown: https://qd.zsopc.com/en/models/gemini-3.8-flash.md)
- Context window: 1,000,000 tokens
- Updated: 2026-11-17
- Price:
  - Input: 303.3 credits (≈ ¥5.06 / ≈ $0.75) per 1M tokens
  - Output: 1,517 credits (≈ ¥25.28 / ≈ $3.75) per 1M tokens
  - Cached input: 30.33 credits (≈ ¥0.506 / ≈ $0.075) per 1M tokens

### Gemini 3.8 Flash-nx

Google Gemini 3.8 Flash (nx line). 1M context, the strongest Flash tier to date, for long-horizon coding and autonomous agents, thinking on by default, billed at Google's list price. OpenAI-compatible and native Gemini protocols.

- Model ID: `gemini-3.8-flash-nx`
- Page: https://qd.zsopc.com/en/models/gemini-3.8-flash-nx (Markdown: https://qd.zsopc.com/en/models/gemini-3.8-flash-nx.md)
- Context window: 1,000,000 tokens
- Updated: 2026-11-17
- Price:
  - Input: 303.3 credits (≈ ¥5.06 / ≈ $0.75) per 1M tokens
  - Output: 1,517 credits (≈ ¥25.28 / ≈ $3.75) per 1M tokens
  - Cached input: 30.33 credits (≈ ¥0.506 / ≈ $0.075) per 1M tokens

### Gemini 4 Argon

Google Gemini 4 Argon. 1M context, the Gemini 4 flagship reasoning model for complex coding, agents, maths and science; thinking levels low, medium (default) and high. OpenAI-compatible and native Gemini protocols.

- Model ID: `gemini-4-argon`
- Page: https://qd.zsopc.com/en/models/gemini-4-argon (Markdown: https://qd.zsopc.com/en/models/gemini-4-argon.md)
- Context window: 1,000,000 tokens
- Updated: 2026-11-17
- Price:
  - 50% OFF right now; these are the prices charged:
    - Input: 404.4 credits (≈ ¥6.74 / ≈ $1) per 1M tokens
    - Output: 2,022 credits (≈ ¥33.7 / ≈ $5) per 1M tokens
    - Cached input: 20.22 credits (≈ ¥0.337 / ≈ $0.05) per 1M tokens
  - List price (applies again when the offer ends):
    - Input: 808.8 credits (≈ ¥13.48 / ≈ $2) per 1M tokens
    - Output: 4,044 credits (≈ ¥67.4 / ≈ $10) per 1M tokens
    - Cached input: 40.44 credits (≈ ¥0.674 / ≈ $0.1) per 1M tokens

### Gemini 4 Argon-nx

Google Gemini 4 Argon (nx line). 1M context, the Gemini 4 flagship reasoning model for complex coding, agents, maths and science; thinking levels low, medium (default) and high; billed at Google's list price. OpenAI-compatible and native Gemini protocols.

- Model ID: `gemini-4-argon-nx`
- Page: https://qd.zsopc.com/en/models/gemini-4-argon-nx (Markdown: https://qd.zsopc.com/en/models/gemini-4-argon-nx.md)
- Context window: 1,000,000 tokens
- Updated: 2026-11-17
- Price:
  - Input: 808.8 credits (≈ ¥13.48 / ≈ $2) per 1M tokens
  - Output: 4,044 credits (≈ ¥67.4 / ≈ $10) per 1M tokens
  - Cached input: 40.44 credits (≈ ¥0.674 / ≈ $0.1) per 1M tokens

## Image generation

### Nano Banana

Google Gemini 2.5 Flash Image (Nano Banana).

- Model ID: `nano-banana`
- Page: https://qd.zsopc.com/en/models/nano-banana (Markdown: https://qd.zsopc.com/en/models/nano-banana.md)
- Updated: 2026-11-17
- Price:
  - Per output image: 18 credits (≈ ¥0.3 / ≈ $0.045)

### Nano Banana 2

Google Gemini 3.1 Flash Image (Nano Banana 2). Text-to-image and image-to-image (reference-image editing).

- Model ID: `nano-banana-2`
- Page: https://qd.zsopc.com/en/models/nano-banana-2 (Markdown: https://qd.zsopc.com/en/models/nano-banana-2.md)
- Updated: 2026-11-17
- Price:
  - Per output image: 18 credits (≈ ¥0.3 / ≈ $0.045)

### Nano Banana 2.1

Google Gemini Nano Banana 2.1, the upgrade of Nano Banana 2. Text-to-image and image-to-image (reference-image editing) at 1K, 2K or 4K.

- Model ID: `nano-banana-2.1`
- Page: https://qd.zsopc.com/en/models/nano-banana-2.1 (Markdown: https://qd.zsopc.com/en/models/nano-banana-2.1.md)
- Updated: 2026-11-17
- Price:
  - Per output image: 18 credits (≈ ¥0.3 / ≈ $0.045)

### Nano Banana Pro

Google Gemini 3 Pro Image (Nano Banana Pro).

- Model ID: `nano-banana-pro`
- Page: https://qd.zsopc.com/en/models/nano-banana-pro (Markdown: https://qd.zsopc.com/en/models/nano-banana-pro.md)
- Updated: 2026-11-17
- Price:
  - Per output image: 18 credits (≈ ¥0.3 / ≈ $0.045)

## Video generation

### Veo 3.1

Google Veo video generation (asynchronous task).

- Model ID: `tvod-veo-3.1`
- Page: https://qd.zsopc.com/en/models/tvod-veo-3.1 (Markdown: https://qd.zsopc.com/en/models/tvod-veo-3.1.md)
- Updated: 2026-11-17
- Price:
  - 720p, per second of output: 24.26 credits (≈ ¥0.404 / ≈ $0.06)
  - 1080p, per second of output: 40.44 credits (≈ ¥0.674 / ≈ $0.1)
  - 4k, per second of output: 121.32 credits (≈ ¥2.02 / ≈ $0.3)

### Veo 3.1 Fast

Google Veo video generation (asynchronous task).

- Model ID: `tvod-veo-3.1-fast`
- Page: https://qd.zsopc.com/en/models/tvod-veo-3.1-fast (Markdown: https://qd.zsopc.com/en/models/tvod-veo-3.1-fast.md)
- Updated: 2026-11-17
- Price:
  - 720p, per second of output: 40.44 credits (≈ ¥0.674 / ≈ $0.1)
  - 1080p, per second of output: 48.53 credits (≈ ¥0.809 / ≈ $0.12)

### Veo 3.1 Lite

Google Veo video generation (asynchronous task).

- Model ID: `tvod-veo-3.1-lite`
- Page: https://qd.zsopc.com/en/models/tvod-veo-3.1-lite (Markdown: https://qd.zsopc.com/en/models/tvod-veo-3.1-lite.md)
- Updated: 2026-11-17
- Price:
  - 720p, per second of output: 20.22 credits (≈ ¥0.337 / ≈ $0.05)
  - 1080p, per second of output: 32.35 credits (≈ ¥0.539 / ≈ $0.08)

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 Google 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 Google 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.
