Every LLM API below is scored by running the same fixed public-domain prompt battery through it and measuring total latency and output throughput ourselves, shown next to the vendor's published per-token price. The speed numbers are first-party measurements — and sponsors cannot edit them.
Method: fixed prompt battery from MMLU (MIT) + Project Gutenberg (public domain) · client-side timing · latency = median of 5 runs, throughput = mean tokens/sec · v1-illustrative
⚠ The latency and throughput numbers below are ILLUSTRATIVE samples. The method is real and reproducible — replace these with measured numbers after running the battery with real API accounts. Pricing reflects published list rates and may change. No real accounts, keys, or money were used.
Featured placement puts your API at the top of the index with your logo and pitch — in front of developers actively choosing an LLM provider.
Claim or feature your listing →Placement is for sale. Your measured latency and throughput are not — every featured model shows the same unedited benchmark numbers.