GLM 5.3 Flash now available on AI Gateway

Z.ai’s GLM-5.3 Flash, a multimodal model supporting text and vision inputs, is now available on Vercel’s AI Gateway. The model features a 1M token context window and includes capabilities such as function calling, structured output, and streaming responses. Users can send messages with images via URLs or Base64 data URLs, and multiple images can be included in a single request.

To integrate GLM-5.3 Flash into coding agents, developers can run the command vercel ai-gateway coding-agents setup to connect agents like Claude Code, Codex, OpenCode, Cursor, and Pi. The model can then be selected within the agent for use. This integration simplifies the process of leveraging the model’s capabilities in automated workflows.

AI Gateway provides a unified API for model interactions, usage tracking, and cost management. It includes features such as configurable retries, failover mechanisms, and performance optimizations to enhance uptime beyond provider guarantees. The service also offers built-in custom reporting, Zero Data Retention support, budget controls for API keys, and routing rules.

AI Gateway mirrors provider pricing without additional markup and does not impose a platform fee on inference costs, including Bring Your Own Key (BYOK) requests. The service aggregates language models from multiple providers, allowing users to compare and select models based on their requirements.