Currently listed through these providers:
Model details
GLM 4.6V FlashX
GLM 4.6V FlashX is a visual foundation model that unifies multimodal perception with actionable output capabilities. It stands out as the first visual model to embed function-calling directly into its core architecture, creating a seamless pipeline from interpreting images and video to triggering executable workflows. The design prioritizes stability and reliability for real-world business deployments, with a training-time context window expanded to 128k tokens for deep analysis across large datasets. This combination of visual understanding with native tool integration positions it as a versatile foundation for intelligent agents operating in complex enterprise environments.
This model represents a significant iteration in the GLM series, building upon the model's lineage to deliver state-of-the-art visual understanding accuracy at its parameter scale. The ability to toggle reasoning modes offers flexibility between high-speed performance and thorough complex workflow execution, adapting to varied task demands. With its emphasis on practical agentic applications, the model excels in scenarios requiring precise visual interpretation translated into concrete tool-based actions, making it particularly well-suited for developers building autonomous systems that need to process visual input from business environments and execute decisions reliably.
Quick Info
Powered by- Provider
- ZenMux
- Model key
- z-ai/glm-4.6v-flash
- Release date
- Dec 8, 2025
- Last updated
- Dec 8, 2025
- Input modalities
- Output modalities
- Capabilities
Cost
- Input token cost
- $0.0218
- Output token cost
- $0.2184
Limits
- Output tokens
- 128,000 tokens
- Context window
- 200,000 tokens
Transparent token rates
Compare GLM 4.6V FlashX pricing
Rates are shown per one million tokens. Combined means one million input plus one million output tokens.