GLM-4.5-Flash
The older free (rate-limited) Flash model that popularized no-cost GLM access. It is still a usable open-weight option for simple tasks, though newer Flash models surpass it.
At a glance
Released
Sep 2, 2025
Provider
Zhipu AI
Context window
128,000 tokens
Max output
8,000 tokens
Modalities
Text → text
Knowledge cutoff
April 2025
API model ID
glm-4.5-flashLicense
Open weights (MIT)
Pricing
Free
Free to call on chat.z.ai (rate-limited). The open weights can also be self-hosted at no per-token cost. Compare it in the calculator →
Best use cases
Simple automation
Handles basic rewriting and tagging at zero cost.
Fallback tier
A free backstop for low-stakes requests.
Edge self-hosting
Small enough to run on modest local hardware under MIT.
Strengths & limitations
Strengths
- Free to call (rate-limited)
- Lightweight
- Open weights
Limitations
- Oldest cutoff of the Flash line
- Very short max output
How to test it
- No-code: open chat.z.ai and pick GLM-4.5-Flash from the model switcher — no API key needed.
- Playground: sign in to the Z.ai API console and run prompts in the workbench, then copy the generated code.
- API: create a key in the Z.ai API console and call the API (example below).
curl https://api.z.ai/api/paas/v4/chat/completions \
# OpenAI-compatible endpoint
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "glm-4.5-flash",
"messages": [{"role": "user", "content": "Explain tokenization in one paragraph."}]
}'