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% | 99.89% | 99.91% | 99.86% | 2.54s | 13.7s | 39 tps | 262K | $0.500 / $2.20◆ (best) | |
| No data | — | 99.99% | 99.97%◆ (best) | 99.87%◆ (best) | 284ms◆ (best) | 1.28s◆ (best) | 133 tps◆ (best) | 203K | $0.600 / $2.40 | |
Togethertogether | No data | — | — | — | — | — | — | — | 512K | $0.600 / $3.60 |
| No data | — | 99.79% | 98.01% | 97.83% | 1.47s | 13.2s | 39 tps | 256K | $0.625 / $3.13 |
- DeepInfra100%Healthy24h 99.89%
- 7d
- 99.91%
- 30d
- 99.86%
- p50
- 2.54s
- p99
- 13.7s
- Throughput
- 39 tps
- Context
- 262K
- $/Mtok
- $0.500 / $2.20◆ (best)
deepinfra/fp4fp4 - No data24h 99.99%
- 7d
- 99.97%◆ (best)
- 30d
- 99.87%◆ (best)
- p50
- 284ms◆ (best)
- p99
- 1.28s◆ (best)
- Throughput
- 133 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 99.79%
- 7d
- 98.01%
- 30d
- 97.83%
- p50
- 1.47s
- p99
- 13.2s
- Throughput
- 39 tps
- Context
- 256K
- $/Mtok
- $0.625 / $3.13
venice/fp8fp8
Measured 3m 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.