How to Get a GLM API Key for Free (Where It Is Free, 2026)

How to Get a GLM API Key for Free

Updated 27 October 2026.

In short: Z.ai's GLM API is paid per token; the "Limited-time Free" label on its pricing page is for cached-input storage, not the models. GLM-5.3 and GLM-5.3-Flash are free on NVIDIA's API catalog after phone verification, and GLM-5.3-Flash is free inside the OpenCode app.

The Z.ai GLM API: paid per token

Z.ai's pricing page lists every GLM model with a price:

Model	Input, per 1M tokens	Output, per 1M tokens
`GLM-5.3`	$1.40	$4.40
`GLM-5.3-Flash`	$0.15	$0.50
`GLM-4.7`	$0.60	$2.20

The column marked "Limited-time Free" is cached-input storage.

Where GLM models are free

Where	GLM model	Free allowance	What it needs
NVIDIA (build.nvidia.com)	`z-ai/glm-5.3`, `z-ai/glm-5.3-flash`	Up to 40 requests a minute, no daily limit stated	Phone verification, not offered in every country
OpenCode	`glm-5.3-flash-free`	Free inside the OpenCode app	Nothing; it only works in OpenCode, not as an API key
Easy GonkaAI API	`zai-org/GLM-5.3-Flash`	10 million tokens once, for a new account	A free account; no card, no phone check
Perplexity Agent API	`perplexity/glm-5.3`, `perplexity/glm-5.3-flash`	A one-time $10 signup credit for some new accounts, 60 days	A Perplexity API account; no card

OpenCode's docs say its free models work only inside OpenCode, not from other apps. The full list of free AI APIs, with each limit and source, is on how to get AI API keys for free.

Use a free GLM model in an app made for OpenAI

In the app, enter the service's key, its base URL and its GLM model name:

Service	Base URL	Model name
NVIDIA	`https://integrate.api.nvidia.com/v1`	`z-ai/glm-5.3`
Easy GonkaAI API	`https://hskyauefqcgbvgvxkluj.supabase.co/functions/v1/gonka`	`zai-org/GLM-5.3-Flash`

To put several free keys behind one address on your own computer, the open-source OmniRoute gateway switches to the next key when one runs out.

Words to know

API key: the password an app uses to call a model. See what is an API key.
GLM: the model family from Z.ai (Zhipu AI); GLM-5.3-Flash is its fast, low-cost model.
Base URL: the address an app sends its requests to.
Token: a piece of a word; the unit models read and write. See tokens and context windows.

Frequently asked questions

Is the GLM API free?+

No. Z.ai bills GLM models per token: GLM-5.3 costs $1.40 per million input tokens and $4.40 per million output tokens. Only cached-input storage is marked Limited-time Free.

Where can I use GLM for free?+

GLM-5.3 and GLM-5.3-Flash are in NVIDIA's free API catalog (z-ai/glm-5.3, z-ai/glm-5.3-flash) after phone verification. GLM-5.3-Flash is also free inside the OpenCode app, with no API key.

What is the NVIDIA base URL for GLM?+

https://integrate.api.nvidia.com/v1 with the model name z-ai/glm-5.3 and an NVIDIA API key.