DeepSeek V3 vs DeepSeek V4 Pro
| Spec | DeepSeek V3 | DeepSeek V4 Pro |
|---|---|---|
| Respan Index | 13.2 (#166) | 49.2 (#44) |
| Blended price per 1M | $0.175 | $0.585 |
| Context window | 128K | 1M |
| Input / output per 1M | $0.14 / $0.28 | $0.28 / $1.5 |
| Max output | 8K | 384K |
| Input | text | text |
| Released | 2024-12-26 | 2026-08-13 |
Respan Index by category
Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.
| Category | DeepSeek V3 | DeepSeek V4 Pro |
|---|---|---|
| Coding | 3.1 DeepSeek V3 | 29.8 DeepSeek V4 Pro |
| Agents | 5.6* DeepSeek V3 | 59.7 DeepSeek V4 Pro |
| Reasoning | 17.3 DeepSeek V3 | 52.8 DeepSeek V4 Pro |
| Knowledge & language | 7.8 DeepSeek V3 | 52.6 DeepSeek V4 Pro |
| Human preference | 39.4 DeepSeek V3 | 56.0 DeepSeek V4 Pro |
* Estimated: no published scores in that category. How the Respan Index works
Benchmarks both report
DeepSeek V4 Pro leads on 5 of the 5 benchmarks both report. Higher is better. Each score links to where it was published.
FAQ
Is DeepSeek V3 better than DeepSeek V4 Pro?
DeepSeek V4 Pro scores 49.2 on the Respan Index (#44), ahead of DeepSeek V3 at 13.2 (#166). DeepSeek V4 Pro leads on 5 of the 5 benchmarks both report.
Which is cheaper, DeepSeek V3 or DeepSeek V4 Pro?
DeepSeek V3 lists at $0.14 input and $0.28 output per 1M tokens; DeepSeek V4 Pro at $0.28 and $1.5. DeepSeek V3 is 3.3x cheaper per token at list price.
Which has the larger context window?
DeepSeek V3 accepts 128K tokens and DeepSeek V4 Pro 1M tokens.
Compare other models
- vsDeepSeek V3.1 vs DeepSeek V3
- vsClaude Sonnet 5.5 vs DeepSeek V4 Pro
- vsGemini 3.8 Flash vs DeepSeek V4 Pro
- vsDeepSeek V3 vs gpt-oss-20b
- vsDeepSeek V3 vs Llama 4 Scout
- vsDeepSeek V3 vs Qwen3 30B-A3B Instruct 2507
- vsDeepSeek V4 Pro vs GPT-5.4
- vsDeepSeek V4 Pro vs GPT-6 Luna
- vsDeepSeek V4 Pro vs Claude Opus 4.7