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) | 99.93% | 99.93%◆ (best) | 99.91%◆ (best) | 632ms◆ (best) | 2.67s | 27 tps◆ (best) | 328K | $0.100 / $0.300◆ (best) | |
| Healthy | 100%◆ (best) | 99.94% | 99.92% | 99.78% | 791ms | 2.60s◆ (best) | 26 tps | 131K | $0.180 / $0.590 | |
Googlegoogle-vertex/us-east5 | No data | — | — | — | 98.92% | — | — | — | 1.3M | $0.250 / $0.700 |
Groqgroq | No data | — | — | — | — | — | — | — | 131K | $0.110 / $0.340 |
- DeepInfra100%◆ (best)Healthy24h 99.93%
- 7d
- 99.93%◆ (best)
- 30d
- 99.91%◆ (best)
- p50
- 632ms◆ (best)
- p99
- 2.67s
- Throughput
- 27 tps◆ (best)
- Context
- 328K
- $/Mtok
- $0.100 / $0.300◆ (best)
deepinfra/fp8fp8 - Novita100%◆ (best)Healthy24h 99.94%
- 7d
- 99.92%
- 30d
- 99.78%
- p50
- 791ms
- p99
- 2.60s◆ (best)
- Throughput
- 26 tps
- Context
- 131K
- $/Mtok
- $0.180 / $0.590
novita/bf16bf16 - No data24h —
- 7d
- —
- 30d
- 98.92%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.3M
- $/Mtok
- $0.250 / $0.700
google-vertex/us-east5 - Groq—No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.110 / $0.340
groq
Measured 2m 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.