Model comparison
DeepSeek-V4.1-Flash vs Gemini 3.1 Pro
A spec-by-spec comparison of DeepSeek-V4.1-Flash and Gemini 3.1 Pro: pricing, context window, capabilities, and independently sourced benchmarks.
Head-to-head
- DeepSeek-V4.1-Flash costs 13x less per input token than Gemini 3.1 Pro ($0.15/MTok vs $2.00/MTok).
- DeepSeek-V4.1-Flash and Gemini 3.1 Pro share the same 1,000,000 tokens context window.
| Spec | DeepSeek-V4.1-Flash | Gemini 3.1 Pro |
|---|---|---|
| Provider | deepseek | |
| Family | DeepSeek V4 | Gemini 3 |
| Status | current | frontier |
| Release date | — | — |
| Knowledge cutoff | — | 2025-01 |
| Context window | 1,000,000 tokens | 1,000,000 tokens |
| Max output tokens | 384,000 tokens | 64,000 tokens |
| Input price | $0.15/MTok | $2.00/MTok |
| Output price | $0.60/MTok | $12.00/MTok |
| Cached input price | $0.00/MTok | $0.20/MTok |
| Vision | Yes | — |
| Tool use | Yes | — |
| Extended thinking | Yes | Yes |
| Streaming | — | — |
Benchmarks
Independently sourced scores
A dash means that model has no publicly sourced score for that benchmark, not a zero.
| Benchmark | DeepSeek-V4.1-Flash | Gemini 3.1 Pro |
|---|---|---|
| GPQA Diamond | — | 94.1% |
DeepSeek-V4.1-Flash
Strengths- Cheapest off-peak input ($0.15) and output ($0.60) per MTok of any model in this file.
- Cache-hit input at $0.003/MTok (off-peak) is the cheapest cached rate of any model in this file.
- Same 1M context and 384K max output as DeepSeek-V4-Pro-0813.
- Concurrency limit of 2,500 requests, five times DeepSeek-V4-Pro-0813.
- Vision (image input) is supported, unlike DeepSeek-V4-Pro-0813.
- Peak-hour pricing (01:00-04:00 and 06:00-10:00 UTC, Monday-Friday, excluding Chinese public holidays) doubles every rate: $0.30/MTok input, $1.20/MTok output, $0.006/MTok cached.
- API model name changed from deepseek-v4-flash to deepseek-flash; the old name is kept as a working legacy alias.
- FIM completion works in non-thinking mode only.
- DeepSeek states it reserves the right to adjust prices and recommends checking the page regularly.
Gemini 3.1 Pro
Strengths- Ties GPT-5.6 Sol at the top of the Artificial Analysis GPQA Diamond board at 94.1%.
- Cheapest model in this file to reach 94% on independently run GPQA Diamond.
- Still labelled Preview on Google’s model index; preview models are deprecated with at least two weeks’ notice.
- Input doubles to $4.00/MTok and output rises to $18.00/MTok above 200k tokens, a threshold one fifth of the way into its own 1M window.
- No free tier on the Gemini API; free access is limited to Google AI Studio.
- Knowledge cutoff of January 2025.
Not sure which one to use?
Flaibo is a daily AI orientation hub: a 12-week path and a prompt vault, with Free and Professional plans. Build the habit, not just the comparison.
Start your AI path