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.
Alibaba Cloud Int. currently ranks first at 153.0 tok/s via alibaba.
| Rank | Provider / route | Output speed | Speed measurements | Endpoint details |
|---|---|---|---|---|
| #1 | Provider / route Alibaba Cloud Int. alibaba | Output speed153.0 tok/s | Speed measurements
| Endpoint details
|
| #2 | Provider / route Weights & Biases wandb/fp8 | Output speed150.0 tok/s | Speed measurements
| Endpoint details
|
| #3 | Provider / route DeepInfra deepinfra/fp8 | Output speed99.0 tok/s | Speed measurements
| Endpoint details
|
| #4 | Provider / route Parasail parasail/fp8 | Output speed82.0 tok/s | Speed measurements
| Endpoint details
|
| #5 | Provider / route Venice venice | Output speed70.0 tok/s | Speed measurements
| Endpoint details
|
| #6 | Provider / route AkashML akashml/fp8 | Output speed60.5 tok/s | Speed measurements
| Endpoint details
|
| #7 | Provider / route NextBit nextbit/fp8 | Output speed36.0 tok/s | Speed measurements
| Endpoint details
|
| #8 | Provider / route SiliconFlow siliconflow/fp8 | Output speed18.0 tok/s | Speed measurements
| Endpoint details
|
| #9 | Provider / route AtlasCloud atlas-cloud/fp8 | Output speed17.0 tok/s | Speed measurements
| Endpoint details
|
Endpoint data fetched .
Qwen3.5-35B-A3B endpoint guide
9 of 9 Qwen3.5-35B-A3B endpoints currently have the published data required for this ranking. Alibaba Cloud Int. leads at 153.0 tok/s via alibaba. 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.
Weights & Biases currently ranks second at 150.0 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.
Qwen3.5-35B-A3B has 9 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.
