Free GLM-4-Flash API
A genuinely always-free chat model from a frontier lab.
GLM-4-Flash is one of the few frontier-lab chat models that is permanently free, with a free vision variant (GLM-4V-Flash). A reliable always-on fallback to keep alongside Gemini Flash.
Quickstart — GLM-4-Flash on Zhipu AI (GLM)
from openai import OpenAI
client = OpenAI(
base_url="https://open.bigmodel.cn/api/paas/v4",
api_key="YOUR_FREE_KEY" # from Zhipu AI (GLM)
)
resp = client.chat.completions.create(
model="glm-4-flash", # GLM-4-Flash on Zhipu AI (GLM)
messages=[{"role": "user", "content": "Hello!"}]
)
print(resp.choices[0].message.content)Providers offering GLM-4-Flash free
Create your own key on any of these. Click through for setup, limits and code.
Free GLM-4-Flash API — FAQ
Is GLM-4-Flash free to use via API?+
Yes. 1 providers in our directory host GLM-4-Flash with free access, starting with Zhipu AI (GLM). You create your own free key on the provider’s site.
Which provider is best for a free GLM-4-Flash API key?+
Zhipu AI (GLM) — Free GLM-4 Flash — a capable always-free chat model. See the full comparison below to match limits and speed to your needs.
How do I call GLM-4-Flash with the OpenAI SDK?+
Set your base URL to your chosen provider’s endpoint (shown on each provider page), use your free key, and pass a GLM-4-Flash model id such as "glm-4-flash".