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.
Venice currently ranks first at 77.0 tok/s via venice/fp8.
| Rank | Provider / route | Output speed | Speed measurements | Endpoint details |
|---|---|---|---|---|
| #1 | Provider / route Venice venice/fp8 | Output speed77.0 tok/s | Speed measurements
| Endpoint details
|
| #2 | Provider / route Weights & Biases wandb/bf16 | Output speed48.5 tok/s | Speed measurements
| Endpoint details
|
| #3 | Provider / route DeepInfra deepinfra/turbo | Output speed38.0 tok/s | Speed measurements
| Endpoint details
|
| #4 | Provider / route Google Vertex google-vertex/us-south1 | Output speed33.0 tok/s | Speed measurements
| Endpoint details
|
| #5 | Provider / route Alibaba Cloud Int. alibaba/opensource | Output speed33.0 tok/s | Speed measurements
| Endpoint details
|
| #6 | Provider / route NovitaAI novita/fp8 | Output speed22.0 tok/s | Speed measurements
| Endpoint details
|
Endpoint data fetched .
Qwen3 Coder 480B A35B endpoint guide
6 of 6 Qwen3 Coder 480B A35B endpoints currently have the published data required for this ranking. Venice leads at 77.0 tok/s via venice/fp8. 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 48.5 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.
Qwen3 Coder 480B A35B has 6 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.
