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.
Baseten currently ranks first at 79.0 tok/s via baseten/fp4.
| Rank | Provider / route | Output speed | Speed measurements | Endpoint details |
|---|---|---|---|---|
| #1 | Provider / route Baseten baseten/fp4 | Output speed79.0 tok/s | Speed measurements
| Endpoint details
|
| #2 | Provider / route Fireworks fireworks | Output speed60.0 tok/s | Speed measurements
| Endpoint details
|
| #3 | Provider / route GMICloud gmicloud/fp8 | Output speed54.0 tok/s | Speed measurements
| Endpoint details
|
| #4 | Provider / route DeepSeek deepseek | Output speed51.0 tok/s | Speed measurements
| Endpoint details
|
| #5 | Provider / route Together together | Output speed49.0 tok/s | Speed measurements
| Endpoint details
|
| #6 | Provider / route Baidu Qianfan baidu/fp8 | Output speed40.0 tok/s | Speed measurements
| Endpoint details
|
| #7 | Provider / route NovitaAI novita/fp8 | Output speed37.0 tok/s | Speed measurements
| Endpoint details
|
| #8 | Provider / route Alibaba Cloud Int. alibaba | Output speed36.0 tok/s | Speed measurements
| Endpoint details
|
| #9 | Provider / route SiliconFlow siliconflow/fp8 | Output speed30.0 tok/s | Speed measurements
| Endpoint details
|
| #10 | Provider / route DeepInfra deepinfra/fp4 | Output speed29.0 tok/s | Speed measurements
| Endpoint details
|
| #11 | Provider / route StreamLake streamlake/fp8 | Output speed26.0 tok/s | Speed measurements
| Endpoint details
|
| #12 | Provider / route DigitalOcean digitalocean | Output speed24.0 tok/s | Speed measurements
| Endpoint details
|
| #13 | Provider / route Venice venice | Output speed16.0 tok/s | Speed measurements
| Endpoint details
|
| #14 | Provider / route Weights & Biases wandb/fp8 | Output speed6.0 tok/s | Speed measurements
| Endpoint details
|
| #15 | Provider / route AtlasCloud atlas-cloud/fp4 | Output speed3.0 tok/s | Speed measurements
| Endpoint details
|
| — | Provider / route Parasail parasail/fp8 | Output speedInsufficient recent data | Speed measurements
| Endpoint details
|
Endpoint data fetched .
DeepSeek V4 Pro endpoint guide
15 of 16 DeepSeek V4 Pro endpoints currently have the published data required for this ranking. Baseten leads at 79.0 tok/s via baseten/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.
Fireworks currently ranks second at 60.0 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 V4 Pro has 16 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.
