Nex-N2-Pro: 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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| No data | — | 99.84% | 99.98% | 99.96%◆ (best) | 1.10s | 6.88s | 36 tps | 262K | $0.250 / $1.00◆ (best) | |
SiliconFlowsiliconflow | No data | — | 99.46% | 100%◆ (best) | 99.82% | 780ms◆ (best) | 869ms◆ (best) | 56 tps◆ (best) | 262K | $0.500 / $2.50 |
- No data24h 99.84%
- 7d
- 99.98%
- 30d
- 99.96%◆ (best)
- p50
- 1.10s
- p99
- 6.88s
- Throughput
- 36 tps
- Context
- 262K
- $/Mtok
- $0.250 / $1.00◆ (best)
nex-agi/fp8fp8 - No data24h 99.46%
- 7d
- 100%◆ (best)
- 30d
- 99.82%
- p50
- 780ms◆ (best)
- p99
- 869ms◆ (best)
- Throughput
- 56 tps◆ (best)
- Context
- 262K
- $/Mtok
- $0.500 / $2.50
siliconflow
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.