Ling-3.0-flash
inclusionai/ling-3.0-flash
Compare with Ling-2.6-flash, Ling-2.6-1T, Ring-2.6-1T
CompareLing-3.0-flash
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Novitanovita | Healthy | 100% | 100% | 711ms | 1.61s | 61 tps | 262K | $0.021 / $0.063 |
Novitanovita/fast | Healthy | 100% | 100% | 709ms | 1.52s | 62 tps | 262K | $0.042 / $0.126 |
DeepInfradeepinfra/bf16bf16 | Healthy | 99.57% | 99.68% | 2.25s | 29.4s | 25 tps | 131K | $0.060 / $0.180 |
- Novita100%Healthy24h 100%
- p50
- 711ms
- p99
- 1.61s
- Throughput
- 61 tps
- Context
- 262K
- $/Mtok
- $0.021 / $0.063
novita - Novita100%Healthy24h 100%
- p50
- 709ms
- p99
- 1.52s
- Throughput
- 62 tps
- Context
- 262K
- $/Mtok
- $0.042 / $0.126
novita/fast - DeepInfra99.57%Healthy24h 99.68%
- p50
- 2.25s
- p99
- 29.4s
- Throughput
- 25 tps
- Context
- 131K
- $/Mtok
- $0.060 / $0.180
deepinfra/bf16bf16
Measured 5m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
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 and p99 are OpenRouter's rolling 30-minute windows, averaged over the hour.
Throughput
Median tokens per second.