Phi-3.5-vision instruct (128k) vs DeepSeek-R1
Both have similar output pricing, while Phi-3.5-vision instruct (128k) offers a larger context window. Choose Phi-3.5-vision instruct (128k) or DeepSeek-R1 based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Phi-3.5-vision instruct (128k) | DeepSeek-R1 |
|---|---|---|
| Provider | GitHub Models | GitHub Models |
| Input / 1M tokens | $0.00 | $0.00 |
| Output / 1M tokens | $0.00 | $0.00 |
| Context window | 128K | 66K |
| Parameters | — | 671B |
| Open weights | Yes | Yes |
| Released | Aug 2024 | Jan 2025 |
FAQ
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.