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.

minimax

minimax-m3.1-flash

Serving

Rank 8 of 15 Last probed (9 min ago)

minimaxai/minimax-m3.1-flash answered 83.3% of probes on the NVIDIA NIM free API in the last 24 hours, with a median time to first token of 9.31 s and 29.1 tok/s. It ranks 8 of 15 tracked models.

83.3% Uptime 10/12 probes
68/ 100 Score 0 round wins
9.31 s First token p95 64.8 s
23.6 s Full reply median
6.18 s Best reply fastest in range
29.1tok/s Throughput median

Model vs. median

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

Uptime
83.3% 100%
17 pts below median
First token
9.31 s 414 ms
22× worse than median
Full reply
23.6 s 4.91 s
4.8× worse than median
Throughput
29.1 tok/s 31.0 tok/s
1.1× worse than median

minimax-m3.1-flash median of answering models

Error breakdown

2 failed of 12 probes, last 24 hours.

FailureProbesShare of failures
Server error (5xx)2 100%

Time to first token

Each probe. Lower is better.

0 ms25.0 s50.0 s75.0 s100.0 s11-17 10:4311-17 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/s11-17 10:4311-17 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
OK18.4 s23.6 s38.8 tok/s
OK36.4 s43.0 s30.1 tok/s
OK46.1 s50.7 s43.9 tok/s
Server error (5xx)n/an/an/a
OK23.8 s31.5 s26.0 tok/s
OK64.8 s71.7 s29.1 tok/s
OK620 ms12.6 s16.7 tok/s
Server error (5xx)n/an/an/a
OK9.31 s24.8 s12.9 tok/s
OK1.48 s8.90 s27.0 tok/s
OK476 ms7.26 s29.5 tok/s
OK831 ms6.18 s37.4 tok/s

Call minimax-m3.1-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": "minimaxai/minimax-m3.1-flash",
    "messages": [{"role": "user", "content": "Hello"}],
    "max_tokens": 256,
    "stream": true
  }'

Other models answering

Top of the leaderboard right now.