DeepSeek R1 Distill Qwen 1.5B vs Phi-3.5-vision instruct (128k)
Both have similar output pricing, while Phi-3.5-vision instruct (128k) offers a larger context window. Choose DeepSeek R1 Distill Qwen 1.5B or Phi-3.5-vision instruct (128k) based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | DeepSeek R1 Distill Qwen 1.5B | Phi-3.5-vision instruct (128k) |
|---|---|---|
| Provider | Alibaba (China) | GitHub Models |
| Input / 1M tokens | $0.00 | $0.00 |
| Output / 1M tokens | $0.00 | $0.00 |
| Context window | 33K | 128K |
| Parameters | — | — |
| Open weights | No | Yes |
| Released | Jan 2025 | Aug 2024 |
| GPQA Diamond score | 33.6 | — |
| LMArena Vision Elo score | — | 851 |
FAQ
Is DeepSeek R1 Distill Qwen 1.5B or Phi-3.5-vision instruct (128k) cheaper?
DeepSeek R1 Distill Qwen 1.5B and Phi-3.5-vision instruct (128k) have comparable output pricing.
Which has the larger context window, DeepSeek R1 Distill Qwen 1.5B or Phi-3.5-vision instruct (128k)?
Phi-3.5-vision instruct (128k) has the larger context window (128K tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.