Start typing to search.
Ranks providers by their recent typical output speed in tokens per second. Providers without enough recent data remain visible after ranked rows.
ModelRun currently ranks first at 149.0 tok/s via modelrun/fp4.
| Rank | Provider / route | Output speed | Speed measurements | Endpoint details |
|---|---|---|---|---|
| #1 | Provider / route ModelRun modelrun/fp4 | Output speed149.0 tok/s | Speed measurements
| Endpoint details
|
| #2 | Provider / route SambaNova sambanova | Output speed95.0 tok/s | Speed measurements
| Endpoint details
|
| #3 | Provider / route Weights & Biases wandb/bf16 | Output speed40.0 tok/s | Speed measurements
| Endpoint details
|
| #4 | Provider / route Cerebras cerebras/fp16 | Output speed36.0 tok/s | Speed measurements
| Endpoint details
|
| #5 | Provider / route Together together | Output speed35.0 tok/s | Speed measurements
| Endpoint details
|
| #6 | Provider / route Together together | Output speed35.0 tok/s | Speed measurements
| Endpoint details
|
| #7 | Provider / route Venice venice/bf16 | Output speed31.0 tok/s | Speed measurements
| Endpoint details
|
| #8 | Provider / route DeepInfra deepinfra/turbo | Output speed28.0 tok/s | Speed measurements
| Endpoint details
|
| #9 | Provider / route DeepInfra deepinfra/fp8 | Output speed23.0 tok/s | Speed measurements
| Endpoint details
|
| #10 | Provider / route Parasail parasail/fp8 | Output speed22.0 tok/s | Speed measurements
| Endpoint details
|
| #11 | Provider / route Chutes chutes/fp4 | Output speed13.0 tok/s | Speed measurements
| Endpoint details
|
| #12 | Provider / route NovitaAI novita/bf16 | Output speed13.0 tok/s | Speed measurements
| Endpoint details
|
| #13 | Provider / route Phala phala | Output speed10.0 tok/s | Speed measurements
| Endpoint details
|
| #14 | Provider / route SiliconFlow siliconflow/fp8 | Output speed7.0 tok/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 149.0 tok/s via modelrun/fp4. The table keeps unranked routes visible so missing measurements do not look like missing provider availability.
The output-speed ranking compares recent median generated tokens per second. It favors routes that complete long generations quickly, while first-token latency remains a separate measure of how responsive the endpoint feels at the beginning.
SambaNova currently ranks second at 95.0 tok/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.
