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.

deepseek

deepseek-v4.1-flash

Unstable

Rank 16 of 16 Last probed (22 min ago)

deepseek-ai/deepseek-v4.1-flash answered 41.6% of probes on the NVIDIA NIM free API in the last 30 days, with a median time to first token of 187.0 s and 2.0 tok/s. It ranks 16 of 16 tracked models.

41.6% Uptime 295/709 probes
27/ 100 Score 0 round wins
187.0 s First token p95 306.3 s
189.1 s Full reply median
8.90 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
41.6% 77.3%
36 pts below median
First token
187.0 s 16.6 s
11× worse than median
Full reply
189.1 s 22.6 s
8.4× worse than median
Throughput
2.0 tok/s 18.0 tok/s
9.0× worse than median

deepseek-v4.1-flash median of answering models

Error breakdown

414 failed of 709 probes, last 30 days.

FailureProbesShare of failures
Timed out230 55.6%
Network error148 35.7%
Empty answer24 5.8%
Not served (404)12 2.9%

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/s12.5 tok/s25.0 tok/s37.5 tok/s50.0 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
Not served (404)n/an/an/a
Not served (404)n/an/an/a
Not served (404)n/an/an/a
Not served (404)n/an/an/a
Not served (404)n/an/an/a
Not served (404)n/an/an/a
Not served (404)n/an/an/a
Not served (404)n/an/an/a
Not served (404)n/an/an/a
Not served (404)n/an/an/a
Not served (404)n/an/an/a
Not served (404)n/an/an/a
Timed outn/an/an/a
Timed outn/an/an/a
Timed outn/an/an/a
Timed outn/an/an/a
OK289.3 s291.6 s1.3 tok/s
Timed outn/an/an/a
Timed outn/an/an/a
Empty answern/an/an/a

Call deepseek-v4.1-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": "deepseek-ai/deepseek-v4.1-flash",
    "messages": [{"role": "user", "content": "Hello"}],
    "max_tokens": 256,
    "stream": true
  }'

Other models answering

Top of the leaderboard right now.