gpt-4.1-nano vs text-embedding-3-small
text-embedding-3-small is cheaper on output tokens, while gpt-4.1-nano offers a larger context window. Choose gpt-4.1-nano or text-embedding-3-small based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | gpt-4.1-nano | text-embedding-3-small |
|---|---|---|
| Provider | SAP AI Core | SAP AI Core |
| Input / 1M tokens | $0.08 | $0.02 |
| Output / 1M tokens | $0.26 | $0.00 |
| Context window | 1M | 8K |
| Parameters | — | — |
| Open weights | No | No |
| Released | Apr 2025 | Jan 2024 |
FAQ
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.