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.
Baidu Qianfan currently ranks first at 79.0 tok/s via baidu/fp8.
| Rank | Provider / route | Output speed | Speed measurements | Endpoint details |
|---|---|---|---|---|
| #1 | Provider / route Baidu Qianfan baidu/fp8 | Output speed79.0 tok/s | Speed measurements
| Endpoint details
|
| #2 | Provider / route Fireworks fireworks | Output speed73.0 tok/s | Speed measurements
| Endpoint details
|
| #3 | Provider / route DeepSeek deepseek | Output speed72.0 tok/s | Speed measurements
| Endpoint details
|
| #4 | Provider / route Alibaba Cloud Int. alibaba | Output speed46.0 tok/s | Speed measurements
| Endpoint details
|
| #5 | Provider / route SiliconFlow siliconflow/fp8 | Output speed41.0 tok/s | Speed measurements
| Endpoint details
|
| #6 | Provider / route StreamLake streamlake/fp8 | Output speed40.0 tok/s | Speed measurements
| Endpoint details
|
| #7 | Provider / route Morph morph | Output speed37.0 tok/s | Speed measurements
| Endpoint details
|
| #8 | Provider / route GMICloud gmicloud/fp8 | Output speed35.0 tok/s | Speed measurements
| Endpoint details
|
| #9 | Provider / route Parasail parasail/fp8 | Output speed35.0 tok/s | Speed measurements
| Endpoint details
|
| #10 | Provider / route Venice venice | Output speed34.0 tok/s | Speed measurements
| Endpoint details
|
| #11 | Provider / route NovitaAI novita/fp8 | Output speed34.0 tok/s | Speed measurements
| Endpoint details
|
| #12 | Provider / route DeepInfra deepinfra/fp4 | Output speed30.0 tok/s | Speed measurements
| Endpoint details
|
| #13 | Provider / route Weights & Biases wandb/fp8 | Output speed29.0 tok/s | Speed measurements
| Endpoint details
|
| #14 | Provider / route NextBit nextbit/fp8 | Output speed27.0 tok/s | Speed measurements
| Endpoint details
|
| #15 | Provider / route AkashML akashml/fp8 | Output speed12.0 tok/s | Speed measurements
| Endpoint details
|
| #16 | Provider / route io.net io-net/fp8 | Output speed11.0 tok/s | Speed measurements
| Endpoint details
|
| #17 | Provider / route AtlasCloud atlas-cloud/fp4 | Output speed7.0 tok/s | Speed measurements
| Endpoint details
|
| #18 | Provider / route DigitalOcean digitalocean | Output speed6.0 tok/s | Speed measurements
| Endpoint details
|
Endpoint data fetched .
DeepSeek V4 Flash endpoint guide
18 of 18 DeepSeek V4 Flash endpoints currently have the published data required for this ranking. Baidu Qianfan leads at 79.0 tok/s via baidu/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.
Fireworks currently ranks second at 73.0 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 Flash has 18 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.
