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

Unstable

Rank 12 of 16 Last probed (22 min ago)

z-ai/glm-5.3-flash answered 74.6% of probes on the NVIDIA NIM free API in the last 30 days, with a median time to first token of 122.4 s and 2.0 tok/s. It ranks 12 of 16 tracked models.

74.6% Uptime 529/709 probes
47/ 100 Score 19 round wins
122.4 s First token p95 293.1 s
129.8 s Full reply median
3.05 s Best reply fastest in range
2.0tok/s Throughput median

Model vs. median

Against the median of models that answered, last 30 days.

Uptime
74.6% 77.3%
3 pts below median
First token
122.4 s 16.6 s
7.4× worse than median
Full reply
129.8 s 22.6 s
5.7× worse than median
Throughput
2.0 tok/s 18.0 tok/s
9.0× worse than median

glm-5.3-flash median of answering models

Error breakdown

180 failed of 709 probes, last 30 days.

FailureProbesShare of failures
Timed out108 60.0%
Network error67 37.2%
Not served (404)4 2.2%
Server error (5xx)1 0.6%

Time to first token

Each probe. Lower is better.

0 ms125.0 s250.0 s375.0 s500.0 s10-31 14:0011-17 16:13 UTC
answered no answer

Throughput

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

0.0 tok/s25.0 tok/s50.0 tok/s75.0 tok/s100 tok/s10-31 14:0011-17 16:13 UTC
answered no answer

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
OK294.0 s297.3 s0.8 tok/s
OK289.3 s296.0 s0.8 tok/s
Timed outn/an/an/a
OK290.5 s294.4 s0.8 tok/s
OK127.9 s129.9 s1.8 tok/s
OK165.9 s172.8 s1.4 tok/s
OK89.6 s97.7 s2.7 tok/s
OK251.8 s255.6 s0.9 tok/s

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.