GLM 5.1
Access GLM 5.1 from Z.AI through one API with current catalog pricing and usage-based billing.
Complete attempts in the last 1d
Median tokens per second
p50 — · total p95 —
Awaiting observations
Available providers
router automatically selects a compatible provider. Compare current rates and observed health below. Image requests use only routes marked Text + images; cheaper text-only routes cannot serve them. Input support and current price eligibility are separate.
| Provider | Input support | Input / 1M | Output / 1M | Discount | Health | Observations |
|---|---|---|---|---|---|---|
| Provider 1 | Text only | $0.825 | $3.301 | 24% off | Observing | — |
At a glance
- Provider
- Z.AI
- Model ID
- glm-5.1
- Type
- Text generation
- Endpoints
- Chat · Responses · Messages
- Vision input
- Not supported
- Reasoning
- Not verified
- Streaming
- Supported
- Context window
- 202,000 tokens
- Maximum output
- 128,000 tokens
Send a request
curl https://your-router.workers.dev/v1/chat/completions \
-H "Authorization: Bearer rtr_k_YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "glm-5.1",
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
}'Popularity ranking
Community usage, without exposing customer usage totals.
Loading ranking…
Loading ranking…
Loading ranking…
Ranked by recorded input and output tokens on router. Rolling periods measure usage, not model quality.
Pricing history
Compare this model’s recorded discounts by hour.
Loading observation window… · UTC
Recorded catalog changes, grouped by UTC hour. Labels use timezone offsets on 2026-09-07. Empty hours remain unknown; these observations do not establish continuous availability or a cheapest time to schedule requests.
Lower the cost of your
next API request
Create an account, fund your wallet, and keep your current request format.