Nemotron 3 Ultra: 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% | 99.91% | 99.91% | 99.86% | 1.19s | 4.54s | 88 tps | 262K | $0.500 / $2.20◆ (best) | |
| No data | — | 99.99% | 99.97%◆ (best) | 99.87%◆ (best) | 265ms◆ (best) | 777ms◆ (best) | 129 tps◆ (best) | 203K | $0.600 / $2.40 | |
Togethertogether | No data | — | — | — | — | — | — | — | 512K | $0.600 / $3.60 |
| No data | — | 99.78% | 98.02% | 97.83% | 1.06s | 3.96s | 99 tps | 256K | $0.625 / $3.13 |
- DeepInfra100%Healthy24h 99.91%
- 7d
- 99.91%
- 30d
- 99.86%
- p50
- 1.19s
- p99
- 4.54s
- Throughput
- 88 tps
- Context
- 262K
- $/Mtok
- $0.500 / $2.20◆ (best)
deepinfra/fp4fp4 - No data24h 99.99%
- 7d
- 99.97%◆ (best)
- 30d
- 99.87%◆ (best)
- p50
- 265ms◆ (best)
- p99
- 777ms◆ (best)
- Throughput
- 129 tps◆ (best)
- Context
- 203K
- $/Mtok
- $0.600 / $2.40
baseten/fp4fp4 - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 512K
- $/Mtok
- $0.600 / $3.60
together - No data24h 99.78%
- 7d
- 98.02%
- 30d
- 97.83%
- p50
- 1.06s
- p99
- 3.96s
- Throughput
- 99 tps
- Context
- 256K
- $/Mtok
- $0.625 / $3.13
venice/fp8fp8
Measured 1m 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.