Zhipu GLM-5.3 flagship coding model, post-trained on the GLM-5.2 base with stronger agentic coding and emergent cybersecurity capabilities and a 1M context window.
LLM Gateway routes requests to the best providers that are able to handle your prompt size and parameters.
Zhipu GLM-5.3 flagship coding model, post-trained on the GLM-5.2 base with stronger agentic coding and emergent cybersecurity capabilities and a 1M context window. You can access it through LLM Gateway's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.
Pricing for GLM-5.3 on LLM Gateway starts at $0.90 per million input tokens and $3.00 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.
GLM-5.3 supports a context window of up to 1,048,576 tokens on its largest provider deployment.
GLM-5.3 is served by Tencent Cloud, Z AI, NovitaAI, Baidu, Alibaba Cloud, Fireworks AI, Inference.net, Mistral AI, Together AI, Cloudflare through LLM Gateway. Requests are automatically routed to the best available provider, with fallback when a provider has issues.
Yes. GLM-5.3 supports both tool (function) calling and strict JSON output schema (upstream-enforced) through LLM Gateway.
GLM-5.3 was released on August 14, 2026.