Category

API

App

ZHIPU
Date
Price

glm-5.1

GLM-5.1 is the next-generation flagship model launched by Zhipu AI, specifically designed to tackle “long-term, complex engineering tasks.”
Model
LLM
Model capability: thinkingModel capability: function_call
Input:
$0.86/1M tokensstarting from
Output:
$3.5/1M tokensstarting from

glm-5v-turbo

GLM-5V-Turbo is Zhipu’s first multimodal coding foundation model, designed specifically for visual programming tasks. It can natively process multimodal inputs such as images, videos, and text, and excels at long-term planning, complex programming, and action execution. It is deeply integrated with agent workflows, enabling seamless collaboration with agents like Claude Code and OpenClaw to complete the full closed-loop process of “understanding the environment → planning actions → executing tasks.”
Model
LLM
Model capability: audioModel capability: imageModel capability: videoModel capability: thinkingModel capability: function_call
Input:
$0.72/1M tokensstarting from
Output:
$3.2/1M tokensstarting from

glm-5-turbo

GLM-5-Turbo is a foundation model deeply optimized for the OpenClaw scenario.
Model
LLM
Model capability: thinkingModel capability: function_call
Input:
$0.72/1M tokensstarting from
Output:
$3.2/1M tokensstarting from

glm-5

Zhipu AI has launched a new-generation flagship foundation large model, specifically designed for complex system engineering and long-term agent tasks, offering a real programming experience that closely rivals Claude Opus 4.5.
Model
LLM
Model capability: thinkingModel capability: function_call
Input:
$0.6/1M tokensstarting from
Output:
$2.6/1M tokensstarting from

glm-4.7-flashx

The lightweight, high-speed version of GLM-4.7—a language model that balances performance and cost-effectiveness.
Model
LLM
Model capability: thinkingModel capability: function_call
Input:
$0.0715/1M tokens
Output:
$0.429/1M tokens

glm-4.7

Zhipu’s flagship text model, covering complex task solving and efficient creation across multiple scenarios.
Model
LLM
Model capability: thinkingModel capability: function_call
Input:
$0.286/1M tokensstarting from
Output:
$1.142/1M tokensstarting from

glm-4.6v

Zhipu High-Performance Visual Understanding Model
Model
LLM
Model capability: imageModel capability: function_call
Input:
$0.145/1M tokensstarting from
Output:
$0.43/1M tokensstarting from

glm-for-coding

Use in three folds in Claude Code
Model
LLM
Model capability: thinkingModel capability: function_call
Input:
$0.086/1M tokensstarting from
Output:
$0.343/1M tokensstarting from

glm-4.6

Zhipu AI’s flagship language model supports complex agent tasks and high-precision code generation.
Model
LLM
Model capability: thinkingModel capability: function_call
Input:
$0.286/1M tokensstarting from
Output:
$1.142/1M tokensstarting from

glm-4.5v

Multimodal Visual Reasoning Model Based on the MOE Architecture
Model
LLM
Model capability: imageModel capability: function_call
Input:
$0.29/1M tokensstarting from
Output:
$0.86/1M tokensstarting from

glm-4.5-airx

GLM-4.5 series: lightweight, high-performance, ultra-fast response models
Model
LLM
Model capability: function_call
Input:
$0.572/1M tokensstarting from
Output:
$1.714/1M tokensstarting from

glm-4.5-air

GLM-4.5 series: high-cost-performance, lightweight, and high-performance model
Model
LLM
Model capability: function_call
Input:
$0.1143/1M tokensstarting from
Output:
$0.286/1M tokensstarting from

glm-4.5-x

GLM-4.5 series high-performance, strong inference, ultra-fast response model
Model
LLM
Model capability: function_call
Input:
$1.143/1M tokensstarting from
Output:
$2.29/1M tokensstarting from

glm-4.5

The 355-billion-parameter MoE large model launched by Zhipu integrates inference, programming, and tool-call capabilities natively.
Model
LLM
Model capability: function_call
Input:
$0.286/1M tokensstarting from
Output:
$1.143/1M tokensstarting from

glm-4-flash-250414

The language model launched by Zhipu AI focuses on real-time web retrieval, long-context processing, and multilingual support.
Model
LLM
Model capability: function_call
Input:
$0.0014/1M tokens
Output:
$0.0014/1M tokens

glm-4-air-250414

The high-performance language model launched by Zhipu AI is primarily positioned as an agent task execution and complex logic processing engine, demonstrating outstanding performance in atomic capabilities such as tool invocation, code generation, and instruction adherence.
Model
LLM
Model capability: function_call
Input:
$0.07/1M tokens
Output:
$0.07/1M tokens