gemini-3-pro-preview vs deepseek-r1
Side-by-side comparison of gemini-3-pro-preview and deepseek-r1: benchmarks, pricing, context window and capabilities. Both are accessible through Requesty's unified API. gemini-3-pro-preview outperforms deepseek-r1 on 9 of 9 shared benchmarks.
gemini-3-pro-preview
Input / 1M
$2.00
Output / 1M
$12.00
Context
1.0M
Model ID
google/gemini-3-pro-preview
deepseek-r1
Input / 1M
$4.00
Output / 1M
$4.00
Context
64K
Model ID
novita/deepseek/deepseek-r1
Benchmark comparison
Intelligence Indexreasoning
gemini-3-pro-preview32.4%
deepseek-r113.9%
Math Indexmath
gemini-3-pro-preview95.7%
deepseek-r176.0%
GPQA Diamondreasoning
gemini-3-pro-preview90.8%
deepseek-r181.3%
AIME 2025math
gemini-3-pro-preview95.7%
deepseek-r176.0%
LiveCodeBenchcoding
gemini-3-pro-preview91.7%
deepseek-r177.0%
Terminal-Bench Hardagentic
gemini-3-pro-preview41.7%
deepseek-r115.9%
τ²-Benchagentic
gemini-3-pro-preview87.1%
deepseek-r136.5%
MMLU Proknowledge
gemini-3-pro-preview89.8%
deepseek-r184.9%
Humanity's Last Examreasoning
gemini-3-pro-preview39.7%
deepseek-r115.8%
Scores sourced from official model cards, Artificial Analysis, and public leaderboards. Benchmarks measure specific skills and don't capture every aspect of model quality.
Pricing & specifications
| gemini-3-pro-preview | deepseek-r1 | |
|---|---|---|
| Input price / 1M | $2.00 | $4.00 |
| Output price / 1M | $12.00 | $4.00 |
| Context window | 1.0M tokens | 64K tokens |
| Max output | 66K tokens | N/A |
| Vision input | Yes | N/A |
| Tool calling | Yes | Yes |
| Reasoning | Yes | N/A |
| Prompt caching | Yes | N/A |
| Computer use | N/A | N/A |
| Provider | Google LLC (Gemini API) | Novita AI |
Questions people ask
Is gemini-3-pro-preview better than deepseek-r1?
gemini-3-pro-preview outperforms deepseek-r1 on 9 of 9 shared benchmarks. See the benchmark comparison above for specifics: gemini-3-pro-preview and deepseek-r1 have different strengths across reasoning, coding, math and multimodal tasks.
Which is cheaper, gemini-3-pro-preview or deepseek-r1?
deepseek-r1 is cheaper. gemini-3-pro-preview costs $2.00/$12.00 per 1M input/output tokens, while deepseek-r1 costs $4.00/$4.00.
Can I use gemini-3-pro-preview and deepseek-r1 through the same API?
Yes. Requesty provides a single OpenAI-compatible API that routes to both. Change just the "model" parameter to switch between "google/gemini-3-pro-preview" and "novita/deepseek/deepseek-r1", no other code changes needed.
What are the context windows?
gemini-3-pro-preview supports up to 1.0M tokens of context. deepseek-r1 supports up to 64K tokens. Longer context means you can feed larger documents or codebases in a single prompt, though quality often degrades past 128K for most models.
Switch between gemini-3-pro-preview and deepseek-r1 with one line of code
Requesty provides a single OpenAI-compatible API for 600+ models. Change the model parameter, not your code.