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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100%◆ (best) | 99.90% | 99.54% | 99.54% | 628ms | 4.95s | 24 tps | 328K | $0.100 / $0.300◆ (best) | |
Googlegoogle-vertex/us-east5 | Healthy | 100%◆ (best) | 99.95% | 99.94%◆ (best) | 99.94%◆ (best) | 1.23s | 3.04s | 30 tps | 1.3M | $0.250 / $0.700 |
| Healthy | 100%◆ (best) | 98.09% | 98.51% | 98.51% | 972ms | 2.62s | 16 tps | 131K | $0.180 / $0.590 | |
Groqgroq | Healthy | 99.73% | 99.62% | 99.68% | 99.68% | 456ms◆ (best) | 2.07s◆ (best) | 63 tps◆ (best) | 131K | $0.110 / $0.340 |
- DeepInfra100%◆ (best)Healthy24h 99.90%
- 7d
- 99.54%
- 30d
- 99.54%
- p50
- 628ms
- p99
- 4.95s
- Throughput
- 24 tps
- Context
- 328K
- $/Mtok
- $0.100 / $0.300◆ (best)
deepinfra/fp8fp8 - Google100%◆ (best)Healthy24h 99.95%
- 7d
- 99.94%◆ (best)
- 30d
- 99.94%◆ (best)
- p50
- 1.23s
- p99
- 3.04s
- Throughput
- 30 tps
- Context
- 1.3M
- $/Mtok
- $0.250 / $0.700
google-vertex/us-east5 - Novita100%◆ (best)Healthy24h 98.09%
- 7d
- 98.51%
- 30d
- 98.51%
- p50
- 972ms
- p99
- 2.62s
- Throughput
- 16 tps
- Context
- 131K
- $/Mtok
- $0.180 / $0.590
novita/bf16bf16 - Groq99.73%Healthy24h 99.62%
- 7d
- 99.68%
- 30d
- 99.68%
- p50
- 456ms◆ (best)
- p99
- 2.07s◆ (best)
- Throughput
- 63 tps◆ (best)
- Context
- 131K
- $/Mtok
- $0.110 / $0.340
groq
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, averaged over the hour.
Throughput
Median tokens per second.