Start typing to search.
Ranks providers by how quickly the first generated token appears. Providers without enough recent data remain visible after ranked rows.
ModelRun currently ranks first at 0.28 s via modelrun/fp4.
| Rank | Provider / route | Time to first token | Speed measurements | Endpoint details |
|---|---|---|---|---|
| #1 | Provider / route ModelRun modelrun/fp4 | Time to first token0.28 s | Speed measurements
| Endpoint details
|
| #2 | Provider / route Weights & Biases wandb/fp4 | Time to first token0.33 s | Speed measurements
| Endpoint details
|
| #3 | Provider / route Together together | Time to first token0.55 s | Speed measurements
| Endpoint details
|
| #4 | Provider / route Cloudflare cloudflare | Time to first token0.59 s | Speed measurements
| Endpoint details
|
| #5 | Provider / route DigitalOcean digitalocean | Time to first token0.69 s | Speed measurements
| Endpoint details
|
| #6 | Provider / route DeepInfra deepinfra/fp4 | Time to first token0.72 s | Speed measurements
| Endpoint details
|
| #7 | Provider / route Parasail parasail/int4 | Time to first token0.75 s | Speed measurements
| Endpoint details
|
| #8 | Provider / route Fireworks fireworks | Time to first token0.77 s | Speed measurements
| Endpoint details
|
| #9 | Provider / route Baidu Qianfan baidu/fp4 | Time to first token1.01 s | Speed measurements
| Endpoint details
|
| #10 | Provider / route Venice venice/int4 | Time to first token1.02 s | Speed measurements
| Endpoint details
|
| #11 | Provider / route Baseten baseten/fp4 | Time to first token1.07 s | Speed measurements
| Endpoint details
|
| #12 | Provider / route Phala phala | Time to first token1.62 s | Speed measurements
| Endpoint details
|
| #13 | Provider / route Moonshot AI moonshotai/int4 | Time to first token1.76 s | Speed measurements
| Endpoint details
|
| #14 | Provider / route SiliconFlow siliconflow/fp8 | Time to first token1.78 s | Speed measurements
| Endpoint details
|
| #15 | Provider / route StreamLake streamlake/fp8 | Time to first token1.98 s | Speed measurements
| Endpoint details
|
| #16 | Provider / route AtlasCloud atlas-cloud/int4 | Time to first token1.98 s | Speed measurements
| Endpoint details
|
| #17 | Provider / route NovitaAI novita | Time to first token2.25 s | Speed measurements
| Endpoint details
|
| #18 | Provider / route Inceptron inceptron/int4 | Time to first token2.48 s | Speed measurements
| Endpoint details
|
| #19 | Provider / route Decart decart/fp4 | Time to first token5.78 s | Speed measurements
| Endpoint details
|
| #20 | Provider / route Chutes chutes/int4 | Time to first token7.34 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 0.28 s via modelrun/fp4. The table keeps unranked routes visible so missing measurements do not look like missing provider availability.
The first-token ranking orders endpoints by the recent median time before output begins. This is useful for interactive applications, but it should be read alongside throughput because the first provider to start is not always the first to finish a long answer.
Weights & Biases currently ranks second at 0.33 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.
