Schematron V2 Turbo: 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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
InferenceNetinference-net | No data | — | — | — | 99.97%◆ (best) | — | — | — | 128K | $0.030 / $0.150◆ (best) |
| No data | — | 100% | 92.45% | 98.52% | 1.78s | 5.01s◆ (best) | 132 tps◆ (best) | 128K | $0.030 / $0.150◆ (best) | |
| No data | — | 100% | 96.33%◆ (best) | 97.82% | 1.58s◆ (best) | 5.16s | 131 tps | 128K | $0.030 / $0.150◆ (best) |
- No data24h —
- 7d
- —
- 30d
- 99.97%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 128K
- $/Mtok
- $0.030 / $0.150◆ (best)
inference-net - No data24h 100%
- 7d
- 92.45%
- 30d
- 98.52%
- p50
- 1.78s
- p99
- 5.01s◆ (best)
- Throughput
- 132 tps◆ (best)
- Context
- 128K
- $/Mtok
- $0.030 / $0.150◆ (best)
inference-net/bf16bf16 - No data24h 100%
- 7d
- 96.33%◆ (best)
- 30d
- 97.82%
- p50
- 1.58s◆ (best)
- p99
- 5.16s
- Throughput
- 131 tps
- Context
- 128K
- $/Mtok
- $0.030 / $0.150◆ (best)
inference-net/usbf16
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.