How do I call Google models?

Create an API key on XiaoZhan AIhub, point your SDK's base_url at https://api.dflop.top/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.

Google models: APIs and prices

13 models·Filter in the catalogue

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.

Text generation6

Gemini 3.1 Progemini-3.1-pro-low
Google Gemini 3.1 Pro. 2M context, flagship reasoning and multimodal. Served over the OpenAI-compatible protocol.
Input 0.4044Credits/K0.8088Credits·Output 2.4264Credits/K4.8528Credits
Gemini 3.1 Pro Preview 1020gemini-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.
Input 0.4044Credits/K0.8088Credits·Output 2.4264Credits/K4.8528Credits
Gemini 3.8 Flashgemini-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.
Input 0.1517Credits/K0.3033Credits·Output 0.7583Credits/K1.5165Credits
Gemini 3.8 Flash-nxgemini-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.
Input 0.3033Credits/K·Output 1.5165Credits/K
Gemini 4 Argongemini-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.
Input 0.4044Credits/K0.8088Credits·Output 2.022Credits/K4.044Credits
Gemini 4 Argon-nxgemini-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.
Input 0.8088Credits/K·Output 4.044Credits/K

Image generation4

Nano Banananano-banana
Google Gemini 2.5 Flash Image (Nano Banana).
per image 18Credits
Nano Banana 2nano-banana-2
Google Gemini 3.1 Flash Image (Nano Banana 2). Text-to-image and image-to-image (reference-image editing).
per image 18Credits
Nano Banana 2.1nano-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.
per image 18Credits
Nano Banana Pronano-banana-pro
Google Gemini 3 Pro Image (Nano Banana Pro).
per image 18Credits

Video generation3

Veo 3.1tvod-veo-3.1
Google Veo video generation (asynchronous task).
per second 24.264Creditsfrom
Veo 3.1 Fasttvod-veo-3.1-fast
Google Veo video generation (asynchronous task).
per second 40.44Creditsfrom
Veo 3.1 Litetvod-veo-3.1-lite
Google Veo video generation (asynchronous task).
per second 20.22Creditsfrom

FAQ

How do I call Google models?: Create an API key on XiaoZhan AIhub, point your SDK's base_url at https://api.dflop.top/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.