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.
| Rank | Provider / route | Output speed | Speed measurements | Endpoint details |
|---|---|---|---|---|
| #1 | Provider / routetogether | Output speed49.0 tok/s | Speed measurements
| Endpoint details
|
Endpoint data fetched .
Inkling endpoint guide
1 of 1 Inkling endpoint currently have the published data required for this ranking. Together leads at 49.0 tok/s via together. 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.
Only 1 route currently qualifies, so the rank alone provides limited choice. Review every visible endpoint for price, speed, uptime, context length, and route-specific configuration.
Inkling has 1 published provider option, 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.
