GLM-5
The model that opened the GLM-5 generation, introducing the long-context core the later releases build on. It remains a budget-friendly open-weight baseline.
At a glance
Released
Dec 15, 2025
Provider
Zhipu AI
Context window
200,000 tokens
Max output
32,000 tokens
Modalities
Text → text
Knowledge cutoff
September 2025
API model ID
glm-5License
Open weights (MIT)
Pricing
Standard
Input$1 / 1M
Output$3.20 / 1M
A typical 1,500-token prompt with a 650-token answer costs ≈ $0.004 on the standard tier. Run your own prompt through the calculator →
Best use cases
Baseline deployments
A cheap, stable starting point for self-hosted GLM pipelines.
Bulk processing
Handles large volumes of straightforward text tasks economically.
Prototyping
A low-risk model for testing GLM integrations before upgrading.
Strengths & limitations
Strengths
- Lowest flagship-core price
- Open weights
- Long context
Limitations
- Oldest cutoff in the 5.x line
- Weaker reasoning than successors
How to test it
- No-code: open chat.z.ai and pick GLM-5 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-5",
"messages": [{"role": "user", "content": "Explain tokenization in one paragraph."}]
}'