# Google: gemini-3.5-flash

- Model ID: `gemini-3.5-flash`
- Provider: Google
- Web version: https://www.moleapi.com/en/models/google/gemini-3.5-flash
- Content status: verified

## Model introduction

Gemini 3.5 Flash is Google's multimodal model. It accepts text, images, video, audio, and PDF input and produces text output.

## Model capabilities

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

### Verified specifications

- Input / output: Text, image, video, audio, PDF / Text
- Context window: 1,048,576 tokens
- Maximum output: 65,536 tokens
- Verified capabilities: Function calling; structured outputs; code execution; file search

### Independent capability evaluation

- Reasoning, high effort
- Intelligence: 50 (#20/186)
- Output speed: 169.7 tok/s (#25/186)
- Time to first token: 20.22s
- Source: https://artificialanalysis.ai/models/gemini-3-5-flash/

Combines a strong composite score with very fast output for multimodal work that values both intelligence and throughput.

## Model pricing and access

Pricing is supplied dynamically by the MoleAPI console API.

### Standard (default, x1)

- Input: $1.5 / 1M tokens
- Output: $9 / 1M tokens
- Cache read: $0.15 / 1M tokens

### Discount (discount, x0.8)

- Input: $1.2 / 1M tokens
- Output: $7.2 / 1M tokens
- Cache read: $0.12 / 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-3.5-flash

Gemini 3.5 Flash is Google's multimodal model. It accepts text, images, video, audio, and PDF input and produces text output.

### Best for

Applications that need long documents or several media types in one request, together with tool calling, code execution, or structured output.

### Core strengths

- Native text, image, video, audio, and PDF input in one model.
- Independent testing shows a strong composite score with very fast output at high reasoning effort.
- Supports function calling, structured output, code execution, search, and a 1M context window.

### Limitations

- High reasoning effort decodes quickly but can still add a long thinking delay before the first answer.
- Output pricing is higher than earlier Flash models, so batch workloads should measure real token use.

### Selection and production evaluation

Start a gemini-3.5-flash evaluation by mapping its official positioning to real work: Applications that need long documents or several media types in one request, together with tool calling, code execution, or structured output. The first pass should exercise both its main strength, "Native text, image, video, audio, and PDF input in one model.", and its known limitation, "High reasoning effort decodes quickly but can still add a long thinking delay before the first answer.", instead of relying on a single subjective general-chat comparison.

For access, MoleAPI currently lists openai, openai-response, anthropic, gemini protocols and the Standard, Discount billing groups for this Google model; the default price summary is Input $1.5 / 1M tokens · Output $9 / 1M tokens. Pricing, protocols, and groups come from the live catalog, so production planning should still price representative requests using real context length, output size, and cache-hit assumptions.

The capability snapshot uses the exact model ID under the "Reasoning, high effort" public evaluation profile. A launch decision should add your own task accuracy, structured-output validity, tool-call success, and timeout rates while pinning the model ID, prompt, and sample set so version or effort changes do not hide regressions.

The model material on this page was last checked on 2026-07-23. When upstream model cards, context limits, or tool support change, update the cited bilingual facts before changing the recommendation; live MoleAPI price changes remain separate and update from the catalog automatically.

### Sources

- [Google Gemini 3.5 Flash model documentation](https://ai.google.dev/gemini-api/docs/models/gemini-3.5-flash) — Google
- Last verified: 2026-07-23

## 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-3.5-flash","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-3.5-flash", 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-3.5-flash", input: "Explain this problem step by step." });
console.log(response.output_text);
```

## More related models

- [gemini-3.1-pro](https://www.moleapi.com/en/models/google/gemini-3.1-pro) — 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-3.5-flash priced?

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

### How can I access gemini-3.5-flash?

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

### How do I switch an existing project to gemini-3.5-flash?

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

### Where do the gemini-3.5-flash details come from?

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