Nemotron 3 Super: 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) | 99.25% | 97.76% | 97.76% | 2.91s | 120s | 54 tps◆ (best) | 262K | $0.085 / $0.400◆ (best) | |
DigitalOceandigitalocean | Healthy | 100%◆ (best) | 99.78% | 99.34%◆ (best) | 99.34%◆ (best) | 820ms◆ (best) | 7.13s◆ (best) | 18 tps | 1.0M | $0.300 / $0.650 |
| No data | — | — | 78.98% | 78.98% | — | — | — | 8K | $0.300 / $0.900 |
- DeepInfra100%◆ (best)Healthy24h 99.25%
- 7d
- 97.76%
- 30d
- 97.76%
- p50
- 2.91s
- p99
- 120s
- Throughput
- 54 tps◆ (best)
- Context
- 262K
- $/Mtok
- $0.085 / $0.400◆ (best)
deepinfra/bf16bf16 - DigitalOcean100%◆ (best)Healthy24h 99.78%
- 7d
- 99.34%◆ (best)
- 30d
- 99.34%◆ (best)
- p50
- 820ms◆ (best)
- p99
- 7.13s◆ (best)
- Throughput
- 18 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $0.650
digitalocean - No data24h —
- 7d
- 78.98%
- 30d
- 78.98%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 8K
- $/Mtok
- $0.300 / $0.900
nebius/fp4fp4
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.
Throughput
Median tokens per second.