Nemotron 3.5 Super VL: 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) | 92.93% | 83.23% | 83.23% | 601ms | 2.04s◆ (best) | 396 tps◆ (best) | 1.0M | $0.150 / $0.750 | |
| Healthy | 100%◆ (best) | 95.31% | 96.77% | 96.77% | 310ms◆ (best) | 7.13s | 108 tps | 262K | $0.100 / $0.400◆ (best) | |
| Healthy | 100%◆ (best) | 99.74% | 100%◆ (best) | 100%◆ (best) | 570ms | 2.54s | 349 tps | 262K | $0.200 / $1.00 | |
Togethertogether | Healthy | 100%◆ (best) | 98.93% | 100%◆ (best) | 100%◆ (best) | 592ms | 12.8s | 211 tps | 262K | $0.150 / $0.500 |
| Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 100%◆ (best) | 694ms | 3.16s | 256 tps | 262K | $0.250 / $1.25 |
- CoreWeave100%◆ (best)Healthy24h 92.93%
- 7d
- 83.23%
- 30d
- 83.23%
- p50
- 601ms
- p99
- 2.04s◆ (best)
- Throughput
- 396 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $0.150 / $0.750
coreweave/nvfp4nvfp4 - Crusoe100%◆ (best)Healthy24h 95.31%
- 7d
- 96.77%
- 30d
- 96.77%
- p50
- 310ms◆ (best)
- p99
- 7.13s
- Throughput
- 108 tps
- Context
- 262K
- $/Mtok
- $0.100 / $0.400◆ (best)
crusoe/bf16bf16 - DeepInfra100%◆ (best)Healthy24h 99.74%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 570ms
- p99
- 2.54s
- Throughput
- 349 tps
- Context
- 262K
- $/Mtok
- $0.200 / $1.00
deepinfra/fp4fp4 - Together100%◆ (best)Healthy24h 98.93%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 592ms
- p99
- 12.8s
- Throughput
- 211 tps
- Context
- 262K
- $/Mtok
- $0.150 / $0.500
together - Venice100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 694ms
- p99
- 3.16s
- Throughput
- 256 tps
- Context
- 262K
- $/Mtok
- $0.250 / $1.25
venice/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.
Throughput
Median tokens per second.