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) | 100% | 99.90% | 99.90% | 312ms◆ (best) | 848ms◆ (best) | 206 tps◆ (best) | 262K | $0.050 / $0.200◆ (best) | |
| Healthy | 100%◆ (best) | 99.96% | 99.95%◆ (best) | 99.95%◆ (best) | 811ms | 11.9s | 97 tps | 262K | $0.050 / $0.200◆ (best) | |
| Degraded | 98.53% | 97.47% | 96.82% | 96.82% | 3.90s | 51.2s | 74 tps | 262K | $0.050 / $0.200◆ (best) |
- Crusoe100%◆ (best)Healthy24h 100%
- 7d
- 99.90%
- 30d
- 99.90%
- p50
- 312ms◆ (best)
- p99
- 848ms◆ (best)
- Throughput
- 206 tps◆ (best)
- Context
- 262K
- $/Mtok
- $0.050 / $0.200◆ (best)
crusoe/fp8fp8 - Novita100%◆ (best)Healthy24h 99.96%
- 7d
- 99.95%◆ (best)
- 30d
- 99.95%◆ (best)
- p50
- 811ms
- p99
- 11.9s
- Throughput
- 97 tps
- Context
- 262K
- $/Mtok
- $0.050 / $0.200◆ (best)
novita/fp4fp4 - DeepInfra98.53%Degraded24h 97.47%
- 7d
- 96.82%
- 30d
- 96.82%
- p50
- 3.90s
- p99
- 51.2s
- Throughput
- 74 tps
- 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.