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-m3.1-flash
Servingminimaxai/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.
Model vs. median
Against the median of models that answered, last 24 hours.
minimax-m3.1-flash median of answering models
Error breakdown
2 failed of 12 probes, last 24 hours.
| Failure | Probes | Share of failures |
|---|---|---|
| Server error (5xx) | 2 | 100% |
Time to first token
Each probe. Lower is better.
Throughput
Tokens per second after the first token, each probe. Higher is better.
Availability heatmap
Last 7 days by UTC hour.
all answered some failed none answered not probed
Run history
Last 20 probes.
| Time | Result | First token | Full reply | Speed |
|---|---|---|---|---|
| OK | 18.4 s | 23.6 s | 38.8 tok/s | |
| OK | 36.4 s | 43.0 s | 30.1 tok/s | |
| OK | 46.1 s | 50.7 s | 43.9 tok/s | |
| Server error (5xx) | n/a | n/a | n/a | |
| OK | 23.8 s | 31.5 s | 26.0 tok/s | |
| OK | 64.8 s | 71.7 s | 29.1 tok/s | |
| OK | 620 ms | 12.6 s | 16.7 tok/s | |
| Server error (5xx) | n/a | n/a | n/a | |
| OK | 9.31 s | 24.8 s | 12.9 tok/s | |
| OK | 1.48 s | 8.90 s | 27.0 tok/s | |
| OK | 476 ms | 7.26 s | 29.5 tok/s | |
| OK | 831 ms | 6.18 s | 37.4 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.
- 96 nvidia nemotron-3.5-lightning-30b-a3b 190 ms first token · 163 tok/s compare
- 95 nvidia nemotron-3.5-bolt-e4b 118 ms first token · 83.8 tok/s compare
- 94 nvidia nemotron-3-nano-omni-30b-a3b-reasoning 179 ms first token · 90.5 tok/s compare
- 93 nvidia nemotron-3.5-super-vl-120b-a12b 334 ms first token · 126 tok/s compare
- 90 poolside laguna-xs-2.1 171 ms first token · 31.0 tok/s compare
- 89 nvidia nemotron-3-ultra-550b-a55b 414 ms first token · 40.1 tok/s compare