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.
DigitalOcean currently ranks first at 52.0 tok/s via digitalocean.
| Rank | Provider / route | Output speed | Speed measurements | Endpoint details |
|---|---|---|---|---|
| #1 | Provider / route DigitalOcean digitalocean | Output speed52.0 tok/s | Speed measurements
| Endpoint details
|
| #2 | Provider / route Alibaba Cloud Int. alibaba | Output speed49.0 tok/s | Speed measurements
| Endpoint details
|
| #3 | Provider / route Friendli friendli | Output speed40.0 tok/s | Speed measurements
| Endpoint details
|
| #4 | Provider / route GMICloud gmicloud/fp8 | Output speed34.5 tok/s | Speed measurements
| Endpoint details
|
| #5 | Provider / route Baidu Qianfan baidu/fp8 | Output speed32.0 tok/s | Speed measurements
| Endpoint details
|
| #6 | Provider / route SiliconFlow siliconflow/fp8 | Output speed32.0 tok/s | Speed measurements
| Endpoint details
|
| #7 | Provider / route Google Vertex google-vertex | Output speed27.0 tok/s | Speed measurements
| Endpoint details
|
| #8 | Provider / route SambaNova sambanova | Output speed26.0 tok/s | Speed measurements
| Endpoint details
|
| #9 | Provider / route StreamLake streamlake/fp8 | Output speed23.0 tok/s | Speed measurements
| Endpoint details
|
| #10 | Provider / route NovitaAI novita/fp8 | Output speed23.0 tok/s | Speed measurements
| Endpoint details
|
| #11 | Provider / route DeepInfra deepinfra/fp4 | Output speed17.0 tok/s | Speed measurements
| Endpoint details
|
| #12 | Provider / route Venice venice | Output speed16.0 tok/s | Speed measurements
| Endpoint details
|
| #13 | Provider / route AtlasCloud atlas-cloud/fp8 | Output speed7.0 tok/s | Speed measurements
| Endpoint details
|
| #14 | Provider / route Phala phala | Output speed7.0 tok/s | Speed measurements
| Endpoint details
|
Endpoint data fetched .
DeepSeek V3.2 endpoint guide
14 of 14 DeepSeek V3.2 endpoints currently have the published data required for this ranking. DigitalOcean leads at 52.0 tok/s via digitalocean. 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.
Alibaba Cloud Int. currently ranks second at 49.0 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.
DeepSeek V3.2 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.
