Ling 3.0 Flash VL: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
- DeepInfra100%◆ (best)Healthy24h 99.96%
- 7d
- 99.83%◆ (best)
- 30d
- 99.82%◆ (best)
- p50
- 535ms◆ (best)
- p99
- 5.28s◆ (best)
- Throughput
- 90 tps
- Context
- 131K
- $/Mtok
- $0.060 / $0.180
deepinfra/fp16fp16 - Novita99.66%Healthy24h 99.97%
- 7d
- 99.77%
- 30d
- 99.77%
- p50
- 889ms
- p99
- 8.23s
- Throughput
- 149 tps◆ (best)
- Context
- 262K
- $/Mtok
- $0.021 / $0.062◆ (best)
novita/bf16bf16
Measured 4m 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.