Nemotron 3 Nano 30B A3B: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100%◆ (best) | 99.98% | 99.98%◆ (best) | 99.79% | 300ms◆ (best) | 1.87s | 225 tps◆ (best) | 262K | $0.050 / $0.200◆ (best) | |
| Healthy | 100%◆ (best) | 99.89% | 99.32% | 98.82% | 380ms | 1.39s◆ (best) | 152 tps | 262K | $0.060 / $0.240 | |
| Degraded | 99.00% | 99.57% | 99.65% | 99.82%◆ (best) | 518ms | 11.7s | 222 tps | 262K | $0.050 / $0.200◆ (best) | |
| No data | — | 82.86% | 92.09% | 97.91% | — | — | — | 262K | $0.050 / $0.200◆ (best) |
- Crusoe100%◆ (best)Healthy24h 99.98%
- 7d
- 99.98%◆ (best)
- 30d
- 99.79%
- p50
- 300ms◆ (best)
- p99
- 1.87s
- Throughput
- 225 tps◆ (best)
- Context
- 262K
- $/Mtok
- $0.050 / $0.200◆ (best)
crusoe/fp8fp8 - Nebius100%◆ (best)Healthy24h 99.89%
- 7d
- 99.32%
- 30d
- 98.82%
- p50
- 380ms
- p99
- 1.39s◆ (best)
- Throughput
- 152 tps
- Context
- 262K
- $/Mtok
- $0.060 / $0.240
nebius/fp8fp8 - Novita99.00%Degraded24h 99.57%
- 7d
- 99.65%
- 30d
- 99.82%◆ (best)
- p50
- 518ms
- p99
- 11.7s
- Throughput
- 222 tps
- Context
- 262K
- $/Mtok
- $0.050 / $0.200◆ (best)
novita/fp4fp4 - No data24h 82.86%
- 7d
- 92.09%
- 30d
- 97.91%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.050 / $0.200◆ (best)
deepinfra/fp4fp4
Measured 5m ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.
Price vs latency
One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag
History
Availability
Axis starts at 90% so small differences stay visible; it expands to 0 when an endpoint falls below.
Time to first token
Logarithmic axis — the fleet spans two orders of magnitude. P50 is OpenRouter's rolling 30-minute window, averaged over the hour.
Throughput
Median tokens per second.