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% | 318ms◆ (best) | 967ms◆ (best) | 148 tps | 262K | $0.050 / $0.200◆ (best) | |
| Healthy | 100%◆ (best) | 99.90% | 99.32% | 98.81% | 359ms | 1.14s | 254 tps◆ (best) | 262K | $0.060 / $0.240 | |
| Healthy | 100%◆ (best) | 99.67% | 99.65% | 99.82%◆ (best) | 450ms | 4.84s | 253 tps | 262K | $0.050 / $0.200◆ (best) | |
| No data | — | 82.28% | 92.15% | 97.92% | 9.31s | 63.4s | 27 tps | 262K | $0.050 / $0.200◆ (best) |
- Crusoe100%◆ (best)Healthy24h 99.98%
- 7d
- 99.98%◆ (best)
- 30d
- 99.79%
- p50
- 318ms◆ (best)
- p99
- 967ms◆ (best)
- Throughput
- 148 tps
- Context
- 262K
- $/Mtok
- $0.050 / $0.200◆ (best)
crusoe/fp8fp8 - Nebius100%◆ (best)Healthy24h 99.90%
- 7d
- 99.32%
- 30d
- 98.81%
- p50
- 359ms
- p99
- 1.14s
- Throughput
- 254 tps◆ (best)
- Context
- 262K
- $/Mtok
- $0.060 / $0.240
nebius/fp8fp8 - Novita100%◆ (best)Healthy24h 99.67%
- 7d
- 99.65%
- 30d
- 99.82%◆ (best)
- p50
- 450ms
- p99
- 4.84s
- Throughput
- 253 tps
- Context
- 262K
- $/Mtok
- $0.050 / $0.200◆ (best)
novita/fp4fp4 - No data24h 82.28%
- 7d
- 92.15%
- 30d
- 97.92%
- p50
- 9.31s
- p99
- 63.4s
- Throughput
- 27 tps
- Context
- 262K
- $/Mtok
- $0.050 / $0.200◆ (best)
deepinfra/fp4fp4
Measured 2m 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.
Throughput
Median tokens per second.