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.
ModelRun currently ranks first at 152.0 tok/s via modelrun/fp4.
| Rank | Provider / route | Output speed | Speed measurements | Endpoint details |
|---|---|---|---|---|
| #1 | Provider / route ModelRun modelrun/fp4 | Output speed152.0 tok/s | Speed measurements
| Endpoint details
|
| #2 | Provider / route Weights & Biases wandb/fp4 | Output speed125.0 tok/s | Speed measurements
| Endpoint details
|
| #3 | Provider / route Baseten baseten/fp4 | Output speed120.0 tok/s | Speed measurements
| Endpoint details
|
| #4 | Provider / route Together together | Output speed100.0 tok/s | Speed measurements
| Endpoint details
|
| #5 | Provider / route DeepInfra deepinfra/fp4 | Output speed89.0 tok/s | Speed measurements
| Endpoint details
|
| #6 | Provider / route Venice venice/int4 | Output speed75.0 tok/s | Speed measurements
| Endpoint details
|
| #7 | Provider / route Parasail parasail/int4 | Output speed67.0 tok/s | Speed measurements
| Endpoint details
|
| #8 | Provider / route Decart decart/fp4 | Output speed53.0 tok/s | Speed measurements
| Endpoint details
|
| #9 | Provider / route DigitalOcean digitalocean | Output speed51.0 tok/s | Speed measurements
| Endpoint details
|
| #10 | Provider / route Fireworks fireworks | Output speed48.0 tok/s | Speed measurements
| Endpoint details
|
| #11 | Provider / route Cloudflare cloudflare | Output speed45.0 tok/s | Speed measurements
| Endpoint details
|
| #12 | Provider / route SiliconFlow siliconflow/fp8 | Output speed37.0 tok/s | Speed measurements
| Endpoint details
|
| #13 | Provider / route Baidu Qianfan baidu/fp4 | Output speed36.0 tok/s | Speed measurements
| Endpoint details
|
| #14 | Provider / route StreamLake streamlake/fp8 | Output speed28.0 tok/s | Speed measurements
| Endpoint details
|
| #15 | Provider / route NovitaAI novita | Output speed26.0 tok/s | Speed measurements
| Endpoint details
|
| #16 | Provider / route AtlasCloud atlas-cloud/int4 | Output speed24.0 tok/s | Speed measurements
| Endpoint details
|
| #17 | Provider / route Moonshot AI moonshotai/int4 | Output speed21.0 tok/s | Speed measurements
| Endpoint details
|
| #18 | Provider / route Phala phala | Output speed19.0 tok/s | Speed measurements
| Endpoint details
|
| #19 | Provider / route Inceptron inceptron/int4 | Output speed18.0 tok/s | Speed measurements
| Endpoint details
|
| #20 | Provider / route Chutes chutes/int4 | Output speed12.0 tok/s | Speed measurements
| Endpoint details
|
Endpoint data fetched .
Kimi K2.6 endpoint guide
20 of 20 Kimi K2.6 endpoints currently have the published data required for this ranking. ModelRun leads at 152.0 tok/s via modelrun/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.
Weights & Biases currently ranks second at 125.0 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.
Kimi K2.6 has 20 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.
