Start typing to search.
Ranks providers by estimated time to return 500 tokens, combining the wait for the first token with output speed.
Friendli currently ranks first at 5.65 s via friendli.
| Rank | Provider / route | Estimated response time | Speed measurements | Endpoint details |
|---|---|---|---|---|
| #1 | Provider / route Friendli friendli | Estimated response time5.65 s | Speed measurements
| Endpoint details
|
| #2 | Provider / route Baseten baseten/fp4 | Estimated response time6.58 s | Speed measurements
| Endpoint details
|
| #3 | Provider / route Fireworks fireworks | Estimated response time9.57 s | Speed measurements
| Endpoint details
|
| #4 | Provider / route DeepInfra deepinfra/fp4 | Estimated response time9.85 s | Speed measurements
| Endpoint details
|
| #5 | Provider / route GMICloud gmicloud/fp8 | Estimated response time11.03 s | Speed measurements
| Endpoint details
|
| #6 | Provider / route Phala phala | Estimated response time13.69 s | Speed measurements
| Endpoint details
|
| #7 | Provider / route Venice venice/fp8 | Estimated response time13.71 s | Speed measurements
| Endpoint details
|
| #8 | Provider / route Chutes chutes/fp8 | Estimated response time13.87 s | Speed measurements
| Endpoint details
|
| #9 | Provider / route Baidu Qianfan baidu/fp8 | Estimated response time14.22 s | Speed measurements
| Endpoint details
|
| #10 | Provider / route Parasail parasail/fp8 | Estimated response time14.49 s | Speed measurements
| Endpoint details
|
| #11 | Provider / route Wafer wafer/fp4 | Estimated response time15.65 s | Speed measurements
| Endpoint details
|
| #12 | Provider / route SiliconFlow siliconflow/fp8 | Estimated response time16.52 s | Speed measurements
| Endpoint details
|
| #13 | Provider / route Nebius nebius/fp8 | Estimated response time16.70 s | Speed measurements
| Endpoint details
|
| #14 | Provider / route NovitaAI novita/fp8 | Estimated response time17.26 s | Speed measurements
| Endpoint details
|
| #15 | Provider / route Z.ai z-ai/fp8 | Estimated response time19.09 s | Speed measurements
| Endpoint details
|
| #16 | Provider / route AtlasCloud atlas-cloud/fp8 | Estimated response time19.42 s | Speed measurements
| Endpoint details
|
| #17 | Provider / route StreamLake streamlake/fp8 | Estimated response time22.58 s | Speed measurements
| Endpoint details
|
| #18 | Provider / route DigitalOcean digitalocean | Estimated response time28.79 s | Speed measurements
| Endpoint details
|
Endpoint data fetched .
GLM 5.1 endpoint guide
18 of 18 GLM 5.1 endpoints currently have the published data required for this ranking. Friendli leads at 5.65 s via friendli. The table keeps unranked routes visible so missing measurements do not look like missing provider availability.
The fastest ranking estimates a 500-token answer by adding the recent median first-token wait to 500 divided by median output throughput. It represents an example complete response, not a guarantee for every prompt or request size.
Baseten currently ranks second at 6.58 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.
GLM 5.1 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.
