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.
Amazon Bedrock currently ranks first at 79.0 tok/s via amazon-bedrock.
| Rank | Provider / route | Output speed | Speed measurements | Endpoint details |
|---|---|---|---|---|
| #1 | Provider / route Amazon Bedrock amazon-bedrock | Output speed79.0 tok/s | Speed measurements
| Endpoint details
|
| #2 | Provider / route Venice venice/fp8 | Output speed55.0 tok/s | Speed measurements
| Endpoint details
|
| #3 | Provider / route GMICloud gmicloud/fp8 | Output speed50.0 tok/s | Speed measurements
| Endpoint details
|
| #4 | Provider / route StreamLake streamlake/fp8 | Output speed44.0 tok/s | Speed measurements
| Endpoint details
|
| #5 | Provider / route NovitaAI novita/fp8 | Output speed40.0 tok/s | Speed measurements
| Endpoint details
|
| #6 | Provider / route Chutes chutes/fp8 | Output speed38.0 tok/s | Speed measurements
| Endpoint details
|
| #7 | Provider / route Parasail parasail/fp8 | Output speed38.0 tok/s | Speed measurements
| Endpoint details
|
| #8 | Provider / route Phala phala | Output speed35.0 tok/s | Speed measurements
| Endpoint details
|
| #9 | Provider / route SiliconFlow siliconflow/fp8 | Output speed34.0 tok/s | Speed measurements
| Endpoint details
|
| #10 | Provider / route Baidu Qianfan baidu/fp8 | Output speed32.0 tok/s | Speed measurements
| Endpoint details
|
| #11 | Provider / route Z.ai z-ai/fp8 | Output speed32.0 tok/s | Speed measurements
| Endpoint details
|
| #12 | Provider / route DeepInfra deepinfra/fp4 | Output speed29.0 tok/s | Speed measurements
| Endpoint details
|
| #13 | Provider / route AtlasCloud atlas-cloud/fp8 | Output speed26.0 tok/s | Speed measurements
| Endpoint details
|
| #14 | Provider / route DigitalOcean digitalocean | Output speed7.0 tok/s | Speed measurements
| Endpoint details
|
Endpoint data fetched .
GLM 5 endpoint guide
14 of 14 GLM 5 endpoints currently have the published data required for this ranking. Amazon Bedrock leads at 79.0 tok/s via amazon-bedrock. 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.
Venice currently ranks second at 55.0 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 5 has 14 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.
