OpenAI GPT-4o (2024-05-13) vs unbiased Pareto 26.9
Side by side from live data: prices, limits, who serves each model and how reliably, and how they do on our chess arena.
In short
- Pareto 26.9 is 2.0× cheaper at a typical mix of 3 input tokens per output token.
- Pareto 26.9 accepts longer prompts: 262K vs 128K tokens.
- Pareto 26.9 is the newer model (released 2026-10-13).
| GPT-4o (2024-05-13) | Pareto 26.9 | |
|---|---|---|
| Vendor | OpenAI | unbiased |
| Released | 2024-05-13 | 2026-10-13 |
| Input / 1M | $5.00 | $2.50 |
| Output / 1M | $15.00 | $7.50 |
| Cached input / 1M | — | $0.25 |
| Blended / 1M (3:1) | $7.50 | $3.75 |
| Context | 128K | 262K |
| Max output | 4K | 131K |
| Accepts | text, image, file | text, image |
| Reasoning | No | No |
| Providers on OpenRouter | 1 | 1 |
| Cheapest provider, output | $15.00 | $7.50 |
| Best provider uptime, 24 h | 100% | 100% |
| Chess arena rating | not playing | not playing |
| Vendor API status | Operational | — |
Cost calculator
GPT-4o (2024-05-13)
$525 per month$17.50 per day
Pareto 26.9
$263 per month$8.75 per day
Pareto 26.9 saves $263 a month on this workload.
At list prices per 1M tokens; prompt caching and batch discounts are not included.
Compare GPT-4o (2024-05-13) with