Llama 4 Scout: 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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Googlegoogle-vertex/us-east5 | Healthy | 100%◆ (best) | 99.94% | 99.94%◆ (best) | 99.94%◆ (best) | 618ms | 2.70s | 28 tps | 1.3M | $0.250 / $0.700 |
Groqgroq | Healthy | 99.40% | 99.62% | 99.68% | 99.68% | 380ms◆ (best) | 1.58s◆ (best) | 66 tps◆ (best) | 131K | $0.110 / $0.340 |
| Down | 73.02% | 97.82% | 98.51% | 98.51% | 3.48s | 10.1s | 9.0 tps | 131K | $0.180 / $0.590 | |
| No data | — | 99.90% | 99.54% | 99.54% | 6.02s | 6.62s | 0.0 tps | 328K | $0.100 / $0.300◆ (best) |
- Google100%◆ (best)Healthy24h 99.94%
- 7d
- 99.94%◆ (best)
- 30d
- 99.94%◆ (best)
- p50
- 618ms
- p99
- 2.70s
- Throughput
- 28 tps
- Context
- 1.3M
- $/Mtok
- $0.250 / $0.700
google-vertex/us-east5 - Groq99.40%Healthy24h 99.62%
- 7d
- 99.68%
- 30d
- 99.68%
- p50
- 380ms◆ (best)
- p99
- 1.58s◆ (best)
- Throughput
- 66 tps◆ (best)
- Context
- 131K
- $/Mtok
- $0.110 / $0.340
groq - Novita73.02%Down24h 97.82%
- 7d
- 98.51%
- 30d
- 98.51%
- p50
- 3.48s
- p99
- 10.1s
- Throughput
- 9.0 tps
- Context
- 131K
- $/Mtok
- $0.180 / $0.590
novita/bf16bf16 - No data24h 99.90%
- 7d
- 99.54%
- 30d
- 99.54%
- p50
- 6.02s
- p99
- 6.62s
- Throughput
- 0.0 tps
- Context
- 328K
- $/Mtok
- $0.100 / $0.300◆ (best)
deepinfra/fp8fp8
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.