Start typing to search.
Ranks providers by estimated time to return 500 tokens, combining the wait for the first token with output speed.
Google Vertex currently ranks first at 11.21 s via google-vertex/us-east5.
| Rank | Provider / route | Estimated response time | Speed measurements | Endpoint details |
|---|---|---|---|---|
| #1 | Provider / route Google Vertex google-vertex/us-east5 | Estimated response time11.21 s | Speed measurements
| Endpoint details
|
| #2 | Provider / route DeepInfra deepinfra/fp8 | Estimated response time17.04 s | Speed measurements
| Endpoint details
|
| #3 | Provider / route Groq groq | Estimated response time18.68 s | Speed measurements
| Endpoint details
|
| #4 | Provider / route NovitaAI novita/bf16 | Estimated response time39.05 s | Speed measurements
| Endpoint details
|
Endpoint data fetched .
Llama 4 Scout endpoint guide
4 of 4 Llama 4 Scout endpoints currently have the published data required for this ranking. Google Vertex leads at 11.21 s via google-vertex/us-east5. The table keeps unranked routes visible so missing measurements do not look like missing provider availability.
The fastest ranking estimates a 500-token answer by adding the recent median first-token wait to 500 divided by median output throughput. It represents an example complete response, not a guarantee for every prompt or request size.
DeepInfra currently ranks second at 17.04 s. Compare that gap with input and output price, response-start time, output speed, 30-minute uptime, context length, and the exact route before deciding whether first place is meaningful for your workload.
Llama 4 Scout has 4 published provider options, and performance data is matched to each exact OpenRouter routing tag. Different quantization, context, regional deployment, or provider configuration can change price and behavior even when the underlying model name is identical.
