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.
Google Vertex currently ranks first at 137.0 tok/s via google-vertex.
| Rank | Provider / route | Output speed | Speed measurements | Endpoint details |
|---|---|---|---|---|
| #1 | Provider / route Google Vertex google-vertex | Output speed137.0 tok/s | Speed measurements
| Endpoint details
|
| #2 | Provider / route Cerebras cerebras/fp16 | Output speed96.0 tok/s | Speed measurements
| Endpoint details
|
| #3 | Provider / route DeepInfra deepinfra/fp4 | Output speed37.0 tok/s | Speed measurements
| Endpoint details
|
| #4 | Provider / route Z.ai z-ai/fp4 | Output speed31.0 tok/s | Speed measurements
| Endpoint details
|
| #5 | Provider / route Venice venice/fp4 | Output speed27.0 tok/s | Speed measurements
| Endpoint details
|
| #6 | Provider / route NovitaAI novita/fp8 | Output speed22.0 tok/s | Speed measurements
| Endpoint details
|
| #7 | Provider / route StreamLake streamlake/fp8 | Output speed20.0 tok/s | Speed measurements
| Endpoint details
|
| #8 | Provider / route Phala phala | Output speed15.0 tok/s | Speed measurements
| Endpoint details
|
| #9 | Provider / route AtlasCloud atlas-cloud/fp8 | Output speed10.0 tok/s | Speed measurements
| Endpoint details
|
Endpoint data fetched .
GLM 4.7 endpoint guide
9 of 9 GLM 4.7 endpoints currently have the published data required for this ranking. Google Vertex leads at 137.0 tok/s via google-vertex. 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.
Cerebras currently ranks second at 96.0 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.
GLM 4.7 has 9 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.
