How do I call Zhipu GLM 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 Zhipu GLM 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.

Zhipu GLM models: APIs and prices

4 models·Filter in the catalogue

GLM models, a Chinese flagship family. XiaoZhan AIhub offers 4 Zhipu GLM 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.

Text generation4

GLM-5.3glm-5.3
Zhipu GLM-5.3: 1M context, with a thinking chain.
Input 0.336Credits/K0.48Credits·Output 1.176Credits/K1.68Credits
GLM-5.3-1022glm-5.3-1022
Zhipu GLM-5.3 (1022 line): 1M context, with a thinking chain that cannot be turned off, tool calling and text-only input, billed at Zhipu's list price. OpenAI Chat, Responses and Anthropic Messages protocols.
Input 0.48Credits/K·Output 1.68Credits/K
GLM-5.3-Flashglm-5.3-flash
Zhipu GLM-5.3-Flash: the first natively multimodal model of the GLM-5 series, 1M context and up to 128K output, with image, video and file input and a thinking chain.
Input 0.0336Credits/K0.048Credits·Output 0.1176Credits/K0.168Credits
GLM-5.3-Flash-1022glm-5.3-flash-1022
Zhipu GLM-5.3-Flash (1022 line): natively multimodal, 1M context, with a thinking chain that cannot be turned off, image input and tool calling, billed at Zhipu's standard list price. OpenAI Chat, Responses and Anthropic Messages protocols.
Input 0.048Credits/K·Output 0.168Credits/K

FAQ

How do I call Zhipu GLM 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 Zhipu GLM 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.