DeepSeek V4 Pro 0423 vs GPT-3.5 Turbo Instruct
DeepSeek V4 Pro 0423 is cheaper on output tokens, while DeepSeek V4 Pro 0423 offers a larger context window. Choose DeepSeek V4 Pro 0423 or GPT-3.5 Turbo Instruct based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | DeepSeek V4 Pro 0423 | GPT-3.5 Turbo Instruct |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Input / 1M tokens | $0.82 | $1.50 |
| Output / 1M tokens | $1.63 | $2.00 |
| Context window | 1M | 4K |
| Parameters | 1.6T | 20B |
| Open weights | Yes | No |
| Released | Apr 2026 | Sep 2023 |
| LMArena (Chatbot Arena) Elo score | 1451 | — |
| LMArena WebDev Elo score | 1582 | — |
| Epoch Capabilities Index score | 156 | — |
| GPQA Diamond score | 91.7 | — |
| LiveBench score | 71.6 | — |
FAQ
Is DeepSeek V4 Pro 0423 or GPT-3.5 Turbo Instruct cheaper?
DeepSeek V4 Pro 0423 is cheaper on output tokens ($1.63 vs $2.00 per 1M).
Which has the larger context window, DeepSeek V4 Pro 0423 or GPT-3.5 Turbo Instruct?
DeepSeek V4 Pro 0423 has the larger context window (1M tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.