o4-mini (Fast) vs o3-deep-research
o4-mini (Fast) is cheaper on output tokens. Choose o4-mini (Fast) or o3-deep-research based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | o4-mini (Fast) | o3-deep-research |
|---|---|---|
| Provider | Vercel AI Gateway | Vercel AI Gateway |
| Input / 1M tokens | $2.00 | $10.00 |
| Output / 1M tokens | $8.00 | $40.00 |
| Context window | 200K | 200K |
| Parameters | — | — |
| Open weights | No | No |
| Released | Apr 2025 | Jun 2025 |
FAQ
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.