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) | 99.97% | 99.68% | 99.68% | 192ms◆ (best) | 1.97s◆ (best) | 45 tps◆ (best) | 262K | $0.080 / $0.200◆ (best) | |
| Down | 96.97% | 96.19% | 97.94% | 97.94% | 524ms | 68.7s | 41 tps | 262K | $0.100 / $0.250 | |
| No data | — | — | 99.99%◆ (best) | 99.99%◆ (best) | — | — | — | 1.0M | $0.100 / $0.250 |
- DeepInfra100%◆ (best)Healthy24h 99.97%
- 7d
- 99.68%
- 30d
- 99.68%
- p50
- 192ms◆ (best)
- p99
- 1.97s◆ (best)
- Throughput
- 45 tps◆ (best)
- Context
- 262K
- $/Mtok
- $0.080 / $0.200◆ (best)
deepinfra/bf16bf16 - CoreWeave96.97%Down24h 96.19%
- 7d
- 97.94%
- 30d
- 97.94%
- p50
- 524ms
- p99
- 68.7s
- Throughput
- 41 tps
- Context
- 262K
- $/Mtok
- $0.100 / $0.250
coreweave/bf16bf16 - No data24h —
- 7d
- 99.99%◆ (best)
- 30d
- 99.99%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.100 / $0.250
venice/fp4fp4
Measured 4m 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.