Skip to main content

Includes 694 hourly rounds up to 2026-11-16 from NIMStats by Mauro Druwel (source), measured with a different prompt and timeout. Our own probe adds a round every 30 minutes.

z

glm-5.3-flash

Down

Rank 15 of 15 Last probed (9 min ago)

z-ai/glm-5.3-flash did not answer any probe on the NVIDIA NIM free API in the last 24 hours.

0% Uptime 0/12 probes
0/ 100 Score 0 round wins
n/a First token p95 n/a
n/a Full reply median
n/a Best reply fastest in range
n/a Throughput median

Model vs. median

Against the median of models that answered, last 24 hours.

Uptime
0% 100%
at the median
First token
n/a 414 ms
Full reply
n/a 4.91 s
Throughput
n/a 31.0 tok/s

glm-5.3-flash median of answering models

Error breakdown

12 failed of 12 probes, last 24 hours.

FailureProbesShare of failures
Timed out12 100%

Time to first token

Each probe. Lower is better.

No probe was answered in this range, so there is no latency to plot.

Throughput

Tokens per second after the first token, each probe. Higher is better.

No answered probe in this range.

Availability heatmap

Last 7 days by UTC hour.

all answered some failed none answered not probed

Run history

Last 20 probes.

TimeResultFirst tokenFull replySpeed
Timed outn/an/an/a
Timed outn/an/an/a
Timed outn/an/an/a
Timed outn/an/an/a
Timed outn/an/an/a
Timed outn/an/an/a
Timed outn/an/an/a
Timed outn/an/an/a
Timed outn/an/an/a
Timed outn/an/an/a
Timed outn/an/an/a
Timed outn/an/an/a

Call glm-5.3-flash

The endpoint is OpenAI-compatible.

Create a free key at build.nvidia.com, then:

curl https://integrate.api.nvidia.com/v1/chat/completions \
  -H "Authorization: Bearer $NVIDIA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "z-ai/glm-5.3-flash",
    "messages": [{"role": "user", "content": "Hello"}],
    "max_tokens": 256,
    "stream": true
  }'

Other models answering

Top of the leaderboard right now.