---
title: "Gemini 3.5"
route_path: "/model/gemini-3.5-flash"
canonical_url: "https://www.pipellm.ai/model/gemini-3.5-flash"
markdown_path: "/llms/models/gemini-3.5-flash.md"
markdown_url: "https://www.pipellm.ai/llms/models/gemini-3.5-flash.md"
content_type: "model-detail-page"
description: "Machine-readable detail page for Gemini 3.5."
generated_at: "2026-10-08T02:59:36.991Z"
---
Canonical page: https://www.pipellm.ai/model/gemini-3.5-flash
Markdown mirror: https://www.pipellm.ai/llms/models/gemini-3.5-flash.md
Content type: model-detail-page
Generated at: 2026-10-08T02:59:36.991Z
# Gemini 3.5
## Query Intents
- Understand pricing, provider availability, context window, and capabilities for Gemini 3.5.
- Compare Gemini 3.5 against other models available through PipeLLM.
- Find the canonical model identifier to use in SDK or API requests.
## Overview
Gemini 3.5 Flash is Google's brand-new generation core AI model, launched in May 2026, featuring ultimate processing speed, powerful code writing capabilities, and the execution power of an autonomous AI Agent (AI Agent). Although positioned as the lightweight "Flash" series, its performance has surpassed the previous generation's flagship model in many benchmark tests, achieving a significant leap towards "mobile executor" while maintaining a high cost-performance ratio.
## Model Metadata
- Display name: Gemini 3.5
- Model ID: gemini-3.5-flash
- Provider family: Google
- Release date: 2026-05-19T12:00:00.000Z
- Context window: 1048576K
- Max output: 65536K
- Input modalities: text, image
- Output modalities: text
- Tool use support: Yes
- Computer use support: Yes
- Cache control support: Yes
## API Integration
Supported call formats through PipeLLM converter routes:
- [OpenAI](https://docs.pipellm.ai/converter/openai-format): `/openai/v1/chat/completions`
- [Responses](https://docs.pipellm.ai/converter/responses-format): `/responses/v1/responses`
- [Anthropic](https://docs.pipellm.ai/converter/anthropic-format): `/anthropic/v1/messages`
- [Gemini](https://docs.pipellm.ai/converter/gemini-format): `/gemini/v1beta/models/{model}:generateContent`

Responses conversion is stateless: use store=false and replay complete output items, including reasoning.encrypted_content, for tool continuations. See the Responses documentation for supported fields and Gemini 3 signature limitations.
## Official Pricing (per 1M tokens)
| Metric | <=200K Context | >200K Context |
| --- | --- | --- |
| Input Price | $1.5 | — |
| Output Price | $9 | — |
| Cache Read | $0 | — |
| Image Input | $0 | — |
| Image Output | $0 | — |

## Provider Availability
| Provider | Region | Context Window | Max Output | Input Price | Output Price | Cache Read | Cache Write |
| --- | --- | --- | --- | --- | --- | --- | --- |
| GCP Vertex | — | 1048576K | 65536K | $1.5 | $9 | $0 | — |
| Vertex | — | 1048.576K | 65.536K | $1.5 | $9 | — | — |

## Documentation
Send an authenticated POST request to https://api.pipellm.ai/v1/chat/completions with model set to gemini-3.5-flash.