Nemotron 3.5 Lightning
nvidia/nemotron-3.5-lightningInputOutput
Compare its 6 providersIncident RSSCompare with Nemotron 3.5 Content Safety, Nemotron 3 Nano 30B A3B, Nemotron 3 Ultra
CompareNemotron 3.5 Lightning
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 100% | 99.99% | 99.95% | 177ms | 559ms | 260 tps | 262K | $0.070 / $0.200 | |
| Healthy | 100% | 99.68% | 99.87% | 99.54% | 1.11s | 5.39s | 33 tps | 262K | $0.039 / $0.180 | |
| Healthy | 100% | 99.99% | 99.92% | 99.83% | 426ms | 2.11s | 250 tps | 262K | $0.060 / $0.160 | |
Io Netio-net | Healthy | 100% | 99.55% | 97.54% | 97.94% | 453ms | 3.06s | 107 tps | 262K | $0.059 / $0.170 |
Phalaphala | Healthy | 100% | 99.64% | 98.67% | 99.07% | 377ms | 4.40s | 169 tps | 262K | $0.070 / $0.200 |
| No data | — | — | — | — | — | — | — | 1.0M | $0.100 / $0.250 |
- CoreWeave100%Healthy24h 100%
- 7d
- 99.99%
- 30d
- 99.95%
- p50
- 177ms
- p99
- 559ms
- Throughput
- 260 tps
- Context
- 262K
- $/Mtok
- $0.070 / $0.200
coreweave/bf16bf16 - Darkbloom100%Healthy24h 99.68%
- 7d
- 99.87%
- 30d
- 99.54%
- p50
- 1.11s
- p99
- 5.39s
- Throughput
- 33 tps
- Context
- 262K
- $/Mtok
- $0.039 / $0.180
darkbloom/int4int4 - DeepInfra100%Healthy24h 99.99%
- 7d
- 99.92%
- 30d
- 99.83%
- p50
- 426ms
- p99
- 2.11s
- Throughput
- 250 tps
- Context
- 262K
- $/Mtok
- $0.060 / $0.160
deepinfra/bf16bf16 - Io Net100%Healthy24h 99.55%
- 7d
- 97.54%
- 30d
- 97.94%
- p50
- 453ms
- p99
- 3.06s
- Throughput
- 107 tps
- Context
- 262K
- $/Mtok
- $0.059 / $0.170
io-net - Phala100%Healthy24h 99.64%
- 7d
- 98.67%
- 30d
- 99.07%
- p50
- 377ms
- p99
- 4.40s
- Throughput
- 169 tps
- Context
- 262K
- $/Mtok
- $0.070 / $0.200
phala - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.100 / $0.250
venice/fp4fp4
Measured 5m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
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.
Daily availability
One row per endpoint · one dot per day · last 90 days.
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 6 endpoints · 47 days with data, 22 endpoint-days below 90%.
Price changes
- Nemotron 3.5 LightningIo Netio-net$0.063 → $0.059 / $0.180 → $0.170cache read $0.032 → $0.0302026-09-29 06:21 UTC
- Nemotron 3.5 LightningDeepInfradeepinfra/bf16$0.080 → $0.060 / $0.200 → $0.160cache read $0.040 → $0.0302026-09-28 23:01 UTC
- Nemotron 3.5 LightningDarkbloomdarkbloom/int4$0.039 / $0.180cache read — → $0.0192026-09-28 20:56 UTC
- Nemotron 3.5 LightningIo Netio-net$0.067 → $0.063 / $0.190 → $0.180cache read $0.033 → $0.0322026-09-27 06:46 UTC
- Nemotron 3.5 LightningDarkbloomdarkbloom/int4$0.065 → $0.039 / $0.1802026-09-27 05:01 UTC
- Nemotron 3.5 LightningIo Netio-net$0.070 → $0.067 / $0.200 → $0.190cache read $0.035 → $0.0332026-09-26 06:10 UTC
- Nemotron 3.5 LightningIo Netio-net$0.070 / $0.200cache read — → $0.0352026-09-25 15:55 UTC
- Nemotron 3.5 LightningDarkbloomdarkbloom/int4$0.040 → $0.065 / $0.1802026-09-20 18:40 UTC
- Nemotron 3.5 LightningDarkbloomdarkbloom/int4$0.065 → $0.040 / $0.1802026-09-20 18:35 UTC
- Nemotron 3.5 LightningDarkbloomdarkbloom/int4$0.040 → $0.065 / $0.1802026-09-20 18:20 UTC
- Nemotron 3.5 LightningDarkbloomdarkbloom/int4$0.065 → $0.040 / $0.1802026-09-19 02:50 UTC
- Nemotron 3.5 LightningPhalaphala$0.080 → $0.070 / $0.2002026-09-17 00:56 UTC
- Nemotron 3.5 LightningCoreWeavecoreweave/bf16$0.100 → $0.070 / $0.250 → $0.200cache read $0.050 → $0.0402026-09-14 16:10 UTC