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.
Parasail currently ranks first at 78.0 tok/s via parasail/fp8.
| Rank | Provider / route | Output speed | Speed measurements | Endpoint details |
|---|---|---|---|---|
| #1 | Provider / route Parasail parasail/fp8 | Output speed78.0 tok/s | Speed measurements
| Endpoint details
|
| #2 | Provider / route DigitalOcean digitalocean | Output speed62.0 tok/s | Speed measurements
| Endpoint details
|
| #3 | Provider / route NovitaAI novita | Output speed60.0 tok/s | Speed measurements
| Endpoint details
|
| #4 | Provider / route Venice venice | Output speed54.0 tok/s | Speed measurements
| Endpoint details
|
| #5 | Provider / route Phala phala | Output speed51.0 tok/s | Speed measurements
| Endpoint details
|
| #6 | Provider / route Alibaba Cloud Int. alibaba | Output speed40.0 tok/s | Speed measurements
| Endpoint details
|
| #7 | Provider / route DeepInfra deepinfra/fp8 | Output speed27.0 tok/s | Speed measurements
| Endpoint details
|
| #8 | Provider / route AtlasCloud atlas-cloud/fp8 | Output speed23.0 tok/s | Speed measurements
| Endpoint details
|
| #9 | Provider / route StreamLake streamlake | Output speed19.0 tok/s | Speed measurements
| Endpoint details
|
| #10 | Provider / route Chutes chutes/fp8 | Output speed6.0 tok/s | Speed measurements
| Endpoint details
|
| #11 | Provider / route GMICloud gmicloud/fp8 | Output speed4.0 tok/s | Speed measurements
| Endpoint details
|
Endpoint data fetched .
Qwen3.5 397B A17B endpoint guide
11 of 11 Qwen3.5 397B A17B endpoints currently have the published data required for this ranking. Parasail leads at 78.0 tok/s via parasail/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.
DigitalOcean currently ranks second at 62.0 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.
Qwen3.5 397B A17B has 11 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.
