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.
Wafer currently ranks first at 81.0 tok/s via wafer/fp8.
| Rank | Provider / route | Output speed | Speed measurements | Endpoint details |
|---|---|---|---|---|
| #1 | Provider / route Wafer wafer/fp8 | Output speed81.0 tok/s | Speed measurements
| Endpoint details
|
| #2 | Provider / route Cloudflare cloudflare | Output speed58.0 tok/s | Speed measurements
| Endpoint details
|
| #3 | Provider / route Google Vertex google-vertex/global | Output speed52.0 tok/s | Speed measurements
| Endpoint details
|
| #4 | Provider / route DekaLLM dekallm/bf16 | Output speed41.0 tok/s | Speed measurements
| Endpoint details
|
| #5 | Provider / route DeepInfra deepinfra/fp8 | Output speed32.0 tok/s | Speed measurements
| Endpoint details
|
| #6 | Provider / route NovitaAI novita/bf16 | Output speed31.0 tok/s | Speed measurements
| Endpoint details
|
| #7 | Provider / route SiliconFlow siliconflow/fp8 | Output speed24.0 tok/s | Speed measurements
| Endpoint details
|
| #8 | Provider / route Parasail parasail/bf16 | Output speed18.0 tok/s | Speed measurements
| Endpoint details
|
| #9 | Provider / route Venice venice/bf16 | Output speed15.0 tok/s | Speed measurements
| Endpoint details
|
| #10 | Provider / route NextBit nextbit/bf16 | Output speed14.0 tok/s | Speed measurements
| Endpoint details
|
Endpoint data fetched .
Gemma 4 26B A4B endpoint guide
10 of 10 Gemma 4 26B A4B endpoints currently have the published data required for this ranking. Wafer leads at 81.0 tok/s via wafer/fp8. 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.
Cloudflare currently ranks second at 58.0 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 26B A4B has 10 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.
