Nemotron 3.5 Lightning: 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% | 100%◆ (best) | 99.95%◆ (best) | 151ms◆ (best) | 568ms◆ (best) | 366 tps◆ (best) | 262K | $0.070 / $0.200 | |
| Healthy | 100%◆ (best) | 99.45% | 99.77% | 99.57% | 653ms | 10.1s | 63 tps | 262K | $0.039 / $0.180◆ (best) | |
| Healthy | 100%◆ (best) | 99.99% | 99.99% | 99.89% | 204ms | 1.40s | 271 tps | 262K | $0.060 / $0.160 | |
Phalaphala | Healthy | 100%◆ (best) | 99.81% | 99.51% | 99.17% | 457ms | 1.72s | 152 tps | 262K | $0.070 / $0.200 |
Io Netio-net | Healthy | 99.92% | 99.69% | 98.04% | 98.49% | 886ms | 9.91s | 33 tps | 262K | $0.049 / $0.140 |
| No data | — | — | — | — | — | — | — | 1.0M | $0.100 / $0.250 |
- CoreWeave100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 99.95%◆ (best)
- p50
- 151ms◆ (best)
- p99
- 568ms◆ (best)
- Throughput
- 366 tps◆ (best)
- Context
- 262K
- $/Mtok
- $0.070 / $0.200
coreweave/bf16bf16 - Darkbloom100%◆ (best)Healthy24h 99.45%
- 7d
- 99.77%
- 30d
- 99.57%
- p50
- 653ms
- p99
- 10.1s
- Throughput
- 63 tps
- Context
- 262K
- $/Mtok
- $0.039 / $0.180◆ (best)
darkbloom/int4int4 - DeepInfra100%◆ (best)Healthy24h 99.99%
- 7d
- 99.99%
- 30d
- 99.89%
- p50
- 204ms
- p99
- 1.40s
- Throughput
- 271 tps
- Context
- 262K
- $/Mtok
- $0.060 / $0.160
deepinfra/bf16bf16 - Phala100%◆ (best)Healthy24h 99.81%
- 7d
- 99.51%
- 30d
- 99.17%
- p50
- 457ms
- p99
- 1.72s
- Throughput
- 152 tps
- Context
- 262K
- $/Mtok
- $0.070 / $0.200
phala - Io Net99.92%Healthy24h 99.69%
- 7d
- 98.04%
- 30d
- 98.49%
- p50
- 886ms
- p99
- 9.91s
- Throughput
- 33 tps
- Context
- 262K
- $/Mtok
- $0.049 / $0.140
io-net - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.100 / $0.250
venice/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, averaged over the hour.
Throughput
Median tokens per second.