Skip to content
NewTry RouterPlus with free creditsTry playground →
RouterPlus
Book a demo

GLM API

Open in consoleI need inference

Pricing

ModelReleasedContextInput / 1MOutput / 1MProvidersWeights
GLM 5.3 Flashz-ai/glm-5.3-flashAugust 26, 20261.05M$0.10Inference.net$0.45Inference.net6Open
GLM 5.3z-ai/glm-5.3August 14, 20261.05M$0.5625DeepInfra$2.50DeepInfra8Open
GLM 5.2z-ai/glm-5.2June 16, 20261.05M$0.5625DeepInfra$1.80DeepInfra4Open
GLM 5.2 Fastz-ai/glm-5.2-fastJune 16, 20261M$2.60Inference.net$8.80Inference.net1Open
GLM 5z-ai/glm-5February 11, 2026205K$0.95Inference.net$2.55Inference.net1Open

Lowest listed price, USD per 1M tokens, as of October 27, 2026.

FAQ

Which GLM models can I use through RouterPlus?

GLM 5.3 Flash, GLM 5.3, GLM 5.2, GLM 5.2 Fast and GLM 5. Each one uses its catalog ID, such as "z-ai/glm-5.3-flash", with the OpenAI-compatible endpoint at https://api.routerplus.com/v1.

What is the cheapest GLM model on RouterPlus?

GLM 5.3 Flash, at $0.10 per million input tokens and $0.45 per million output tokens on Inference.net. Prices as of October 27, 2026.

Which GLM model has the most providers?

GLM 5.3, served by 8 providers: Morph, DeepInfra, Mistral AI, Nebius, Novita AI, Inference.net, RunInfra and Sail Research.

What is the newest GLM model?

GLM 5.3 Flash, released August 26, 2026, is the newest Z.ai model in the RouterPlus catalog.

Run GLM in production

Open in consoleI need inference