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 100.0 tok/s via google-vertex.
| Rank | Provider / route | Output speed | Speed measurements | Endpoint details |
|---|---|---|---|---|
| #1 | Provider / route Google Vertex google-vertex | Output speed100.0 tok/s | Speed measurements
| Endpoint details
|
| #2 | Provider / route Google AI Studio google-ai-studio | Output speed98.0 tok/s | Speed measurements
| Endpoint details
|
| #3 | Provider / route Google Vertex google-vertex/eu | Output speed87.0 tok/s | Speed measurements
| Endpoint details
|
| — | Provider / route Google AI Studio google-ai-studio/flex | Output speedInsufficient recent data | Speed measurements
| Endpoint details
|
| — | Provider / route Google AI Studio google-ai-studio/priority | Output speedInsufficient recent data | Speed measurements
| Endpoint details
|
Endpoint data fetched .
Gemini 2.5 Flash Lite endpoint guide
3 of 5 Gemini 2.5 Flash Lite endpoints currently have the published data required for this ranking. Google Vertex leads at 100.0 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.
Google AI Studio currently ranks second at 98.0 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.
Gemini 2.5 Flash Lite has 5 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.
