Which provider is fastest for a given model? Which is most reliable? We transact text, images and video across every provider — so we can measure it. These leaderboards are computed from real API request traffic, not vendor marketing.
7-day window · as of Thu, 19 Nov 2026 08:40:25 UTC
Every measured provider across all models it served in the last 7 days. Success counts HTTP 5xx as failures; client errors (4xx) and rate limits are excluded, so one bad caller can't sink a score.
For each model, the provider currently serving it fastest. Open a model for the full provider comparison and its latency, uptime and price history.
Output tokens per second per cent of typical request price — measured throughput against what you actually pay. Chat models with measured performance.
| Model | Tokens/sec | Price | Value (tok/s per ¢) |
|---|---|---|---|
| DeepSeek V4 Flash | 130.4 | $0.0010 | 1330.6 |
| Step 3.7 Flash | 217.8 | $0.0022 | 1013 |
| MiMo V2.5 | 72.3 | $0.0010 | 737.8 |
| Gemini 2.5 Flash | 126.9 | $0.0040 | 317.3 |
| GPT-4.1 Mini | 111.7 | $0.0036 | 310.3 |
| GPT-5 Mini | 85.7 | $0.0033 | 263.7 |
| Gemini 3 Flash | 39.3 | $0.0055 | 71.5 |
| DeepSeek V4 Pro | 70.9 | $0.012 | 58.2 |
| Gemini 3.5 Flash | 95 | $0.017 | 57.6 |
| Gemini 3.7 Flash | 37 | $0.0075 | 49.3 |
Measured from live API traffic. GET /api/v1/health · Status