# Google: gemini-3.1-pro

- Model ID: `gemini-3.1-pro`
- Provider: Google
- Web version: https://www.moleapi.com/en/models/google/gemini-3.1-pro
- Content status: verified

## Model introduction

Gemini 3.1 Pro is Google's flagship multimodal model for complex reasoning, code, and long-form generation, with 1M context and 64K output.

## Model capabilities

- OpenAI compatible
- Responses API
- Anthropic compatible
- Gemini compatible
- Vision
- Prompt cache
- Reasoning

### Verified specifications

- Official positioning: Flagship complex reasoning and multimodal model
- Context window: 1,000,000 tokens
- Maximum output: 64,000 tokens
- Input / output: Text, image, audio, video, PDF / Text

## Model pricing and access

Pricing is supplied dynamically by the MoleAPI console API.

### Standard (default, x1)

- Input: $2 / 1M tokens
- Output: $12 / 1M tokens
- Cache read: $0.2 / 1M tokens

### Discount (discount, x0.8)

- Input: $1.6 / 1M tokens
- Output: $9.6 / 1M tokens
- Cache read: $0.16 / 1M tokens

### Access protocols

| Protocol | Method | Endpoint |
| --- | --- | --- |
| openai | POST | /v1/chat/completions |
| openai-response | POST | /v1/responses |
| anthropic | POST | /v1/messages |
| gemini | POST | /v1beta/models/{model}:generateContent |

- Live pricing source: https://home.moleapi.com/api/pricing

## About gemini-3.1-pro

## Positioning and core capabilities

Gemini 3.1 Pro is Google’s February 2026 flagship Gemini 3-series model for complex tasks, built on Gemini 3 Pro and positioned for natively multimodal reasoning. [3] It accepts text, images, audio, and video inputs, including entire code repositories, and returns text. [3]

## Capabilities and specifications

Gemini 3.1 Pro combines multimodal input processing with a long context window for complex reasoning, coding, and analysis workloads. [3]

| Specification | Value |
|---|---|
| Input modalities | Text, images, audio, and video [3] |
| Output modality | Text [3] |
| Context window | 1,000,000 tokens [3] |
| Maximum output | 64,000 tokens [3] |
| Model foundation | Gemini 3 Pro [3] |

Google’s evaluation table reports a 77.1% score for Gemini 3.1 Pro Thinking (High) on ARC-AGI-2, compared with 31.1% for Gemini 3 Pro Thinking (High), and a 68.5% score on Terminal-Bench 2.0, compared with 56.9%. [3] Google also reports 80.6% on SWE-Bench Verified, an Elo score of 2,887 on LiveCodeBench Pro, and MRCR v2 results of 84.9% at 128K average context and 26.3% on the reported 1M pointwise setting. [3]

## Use cases

Google identifies Gemini 3.1 Pro for agentic performance, advanced coding, algorithm development, and long-context or multimodal understanding. [3]

Its input support can accommodate analysis that combines written material with visual, audio, or video content, while its repository support targets codebase-level development and software-engineering tasks. [3] Its reported benchmark results also cover abstract reasoning, terminal-based tasks, software issue resolution, coding, search, and long-context retrieval. [3]

## Material limitations

Gemini 3.1 Pro produces text outputs, including when processing multimodal inputs. [3] Its generated response is capped at 64,000 tokens, while the 1,000,000-token limit applies to context. [3]

## Sources

- [3] [Google DeepMind Gemini 3.1 Pro model card](https://deepmind.google/models/model-cards/gemini-3-1-pro/)


## Code examples

### cURL

```bash
curl https://api.moleapi.com/v1/responses \
  -H "Authorization: Bearer $MOLEAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gemini-3.1-pro","input":"Explain this problem step by step."}'
```

### Python

```python
from openai import OpenAI

client = OpenAI(base_url="https://api.moleapi.com/v1", api_key="YOUR_MOLEAPI_API_KEY")
response = client.responses.create(model="gemini-3.1-pro", input="Explain this problem step by step.")
print(response.output_text)
```

### TypeScript

```typescript
import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.moleapi.com/v1", apiKey: process.env.MOLEAPI_API_KEY });
const response = await client.responses.create({ model: "gemini-3.1-pro", input: "Explain this problem step by step." });
console.log(response.output_text);
```

## More related models

- [gemini-3.5-flash](https://www.moleapi.com/en/models/google/gemini-3.5-flash) — Google
- [gemini-3-flash](https://www.moleapi.com/en/models/google/gemini-3-flash) — Google
- [gemini-3.7-flash](https://www.moleapi.com/en/models/google/gemini-3.7-flash) — Google

## Frequently asked questions

### How is gemini-3.1-pro priced?

Prices are read from the MoleAPI console API and update with model prices, context tiers, and account groups.

### How can I access gemini-3.1-pro?

The catalog currently lists openai, openai-response, anthropic, gemini.

### How do I switch an existing project to gemini-3.1-pro?

Keep the MoleAPI API address and key, replace the model parameter, and check protocol-specific parameters.

### Where do the gemini-3.1-pro details come from?

Capabilities and limitations are checked against B.AI and the other cited pages; pricing and protocols come from the MoleAPI console.