Start typing to search.
Ranks providers by estimated time to return 500 tokens, combining the wait for the first token with output speed.
ModelRun currently ranks first at 3.92 s via modelrun/fp4.
| Rank | Provider / route | Estimated response time | Speed measurements | Endpoint details |
|---|---|---|---|---|
| #1 | Provider / route ModelRun modelrun/fp4 | Estimated response time3.92 s | Speed measurements
| Endpoint details
|
| #2 | Provider / route SambaNova sambanova | Estimated response time7.16 s | Speed measurements
| Endpoint details
|
| #3 | Provider / route Weights & Biases wandb/bf16 | Estimated response time12.85 s | Speed measurements
| Endpoint details
|
| #4 | Provider / route Cerebras cerebras/fp16 | Estimated response time14.09 s | Speed measurements
| Endpoint details
|
| #5 | Provider / route Together together | Estimated response time15.30 s | Speed measurements
| Endpoint details
|
| #6 | Provider / route Together together | Estimated response time15.30 s | Speed measurements
| Endpoint details
|
| #7 | Provider / route Venice venice/bf16 | Estimated response time17.23 s | Speed measurements
| Endpoint details
|
| #8 | Provider / route DeepInfra deepinfra/turbo | Estimated response time18.53 s | Speed measurements
| Endpoint details
|
| #9 | Provider / route DeepInfra deepinfra/fp8 | Estimated response time22.56 s | Speed measurements
| Endpoint details
|
| #10 | Provider / route Parasail parasail/fp8 | Estimated response time23.70 s | Speed measurements
| Endpoint details
|
| #11 | Provider / route NovitaAI novita/bf16 | Estimated response time40.04 s | Speed measurements
| Endpoint details
|
| #12 | Provider / route Chutes chutes/fp4 | Estimated response time41.41 s | Speed measurements
| Endpoint details
|
| #13 | Provider / route Phala phala | Estimated response time53.76 s | Speed measurements
| Endpoint details
|
| #14 | Provider / route SiliconFlow siliconflow/fp8 | Estimated response time78.26 s | Speed measurements
| Endpoint details
|
Endpoint data fetched .
Gemma 4 31B endpoint guide
14 of 14 Gemma 4 31B endpoints currently have the published data required for this ranking. ModelRun leads at 3.92 s via modelrun/fp4. 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.
SambaNova currently ranks second at 7.16 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.
Gemma 4 31B has 14 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.
