AI model comparison
Compare pricing, context limits, supported inputs and deployment options to choose a model for your workflow.
Deep Research Max Preview from Google lists 1.05M context, 65.54K maximum output, $2.00 input per 1M tokens, $12.00 output per 1M tokens. Gemini 3.1 Pro Preview Custom Tools from Google lists 1.05M context, 65.54K maximum output, $2.00 input per 1M tokens, $12.00 output per 1M tokens. Compare the inputs, outputs and deployment options below to see which fits your workflow.
Deep Research Max Preview from Google: Maximum-comprehensiveness agentic researcher for multi-step investigation, synthesis, and cited reports.
Accepts
Produces
Gemini 3.1 Pro Preview Custom Tools from Google: Advanced Gemini model for complex reasoning, coding, and multimodal analysis.
Accepts
Produces
At a glance
Compare the available figures below, then try both models on the work you need to do.
Context capacity
Higher listed limit
Deep Research Max Preview:1.05M
Gemini 3.1 Pro Preview Custom Tools:1.05M
Same value
Maximum output
Higher listed limit
Deep Research Max Preview:65.54K
Gemini 3.1 Pro Preview Custom Tools:65.54K
Same value
Input price
Lower listed token rate
Deep Research Max Preview:$2.00
Gemini 3.1 Pro Preview Custom Tools:$2.00
Same value
Output price
Lower listed token rate
Deep Research Max Preview:$12.00
Gemini 3.1 Pro Preview Custom Tools:$12.00
Same value
Specifications
| Specification | Deep Research Max Preview | Gemini 3.1 Pro Preview Custom Tools |
|---|---|---|
| Provider | ||
| Listed pricing route | ||
| Model family | gemini-pro | gemini-pro |
| Accepted inputs | text, image, video, audio, pdf | text, image, video, audio, pdf |
| Produced outputs | text, image | text |
| Context window | 1.05M | 1.05M |
| Max output | 65.54K | 65.54K |
| Input price / 1M | $2.00 | $2.00 |
| Output price / 1M | $12.00 | $12.00 |
| Reasoning mode | Documented | Documented |
| Tool calling | Documented | Documented |
| Image input | Documented | Documented |
| Audio input | Documented | Documented |
| Structured output | Not documented | Documented |
| License | Proprietary | Proprietary |
Workload guidance
The recorded figures alone do not establish a clear choice. Test both on the same representative examples and judge the output against your acceptance criteria. Include tool failures, retries and the time to a completed task.
Explore each model’s features, API requirements and licence terms in the sources below.
Deep Research Max Preview
Profile updated Oct 13, 2026
Documentation and references ↗Documentation and references ↗Documentation and references ↗Gemini 3.1 Pro Preview Custom Tools
Profile updated Oct 13, 2026
Search by model or provider to explore another comparison.