Best-value LLM APIs (speed per dollar)
As of 2026-09-19, the top model is deepseek/deepseek-v4-flash-free (175 tok/s @ $0.28/1M). See the full ranking below — click a model for details or run your own test.
- 🥇175 tok/s @ $0.28/1M
- 🥈141 tok/s @ $0.28/1M
- 🥉105 tok/s @ $0.28/1M
- 483 tok/s @ $0.28/1M
- 544 tok/s @ $0.28/1M
- 6170 tok/s @ $1.1/1M
- 785 tok/s @ $0.87/1M
- 8100 tok/s @ $1.2/1M
- 9250 tok/s @ $4.0/1M
- 10171 tok/s @ $4.0/1M
- 1159 tok/s @ $4.4/1M
- 1255 tok/s @ $4.4/1M
- 1336 tok/s @ $14/1M
📋 Embed this ranking on your site
Copy the code below (live data, auto-updating):
<iframe src="https://www.tokrace.com/embed/best/value?lang=en" width="400" height="360" style="border:0;border-radius:12px" loading="lazy" title="Best-value LLM APIs (speed per dollar)"></iframe>
· Speed is the median of anonymous benchmarks; prices follow official pages and cross-currency uses a fixed USD rate. Reference only.