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.
OpenAI currently ranks first at 87.5 tok/s via openai.
| Rank | Provider / route | Output speed | Speed measurements | Endpoint details |
|---|---|---|---|---|
| #1 | Provider / route OpenAI openai | Output speed87.5 tok/s | Speed measurements
| Endpoint details
|
Endpoint data fetched .
GPT-4o-mini Search Preview endpoint guide
1 of 1 GPT-4o-mini Search Preview endpoint currently have the published data required for this ranking. OpenAI leads at 87.5 tok/s via openai. 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.
GPT-4o-mini Search Preview 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.
