As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/gemini-3-5-flash/

# Gemini 3.5 Flash

Google DeepMind, Gemini 3.5 family. Status: deprecated. Type: reasoning model. Released: 2026-05-19. Training cutoff: not published.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Gemini API | `gemini-3.5-flash` | https://generativelanguage.googleapis.com/v1beta/models/gemini-3.5-flash:generateContent | https://ai.google.dev/gemini-api/docs/models/gemini-3.5-flash |
| Google Cloud Gemini Enterprise Agent Platform (Vertex AI) | `gemini-3.5-flash` |  | https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/3-5-flash |
| OpenRouter | `google/gemini-3.5-flash` |  |  |

## Pricing

- Input: $1.50 per 1M tokens
- Output: $9 per 1M tokens
- Unit as published: per 1M tokens (Standard tier)
- Source: https://ai.google.dev/gemini-api/docs/pricing
- Last checked: 2026-10-10

## Specs

- Input: text, image, audio, video, pdf
- Output: text
- Context window: 1,048,576 tokens
- Max output: 65,536 tokens
- Open weights: no
- Licence: proprietary

## What it has not seen

- No published training cutoff. Counted from its release (2026-05-19): at least 1,842 AI events since (422 major, 83 historic), as of 2026-11-13.
- Everything since April 2026: https://postcutoff.com/since/2026-04/

## What stands out

- Flash beats previous Pro on agents: Outperformed Gemini 3.1 Pro on Terminal-Bench 2.1 (76.2%), GDPval-AA (1656 Elo) and MCP Atlas (83.6%); 84.2% CharXiv Reasoning. Source: https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-5/
- High output speed: Google claims ~4x the output tokens/second of other frontier models at launch. Source: https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-5/

## Notes

Deprecated on 2026-10-08: all requests to gemini-3.5-flash are now automatically routed to gemini-3.6-flash (Gemini API changelog, https://ai.google.dev/gemini-api/docs/changelog). Use gemini-3.8-flash (or 3.6-flash). Launched at Google I/O 2026 as first Gemini 3.5 model. Model page lists gemini-3-flash-preview (Dec 2025) as its preview predecessor id; that preview is still served. Now more expensive than 3.6-3.8 Flash; use gemini-3.8-flash.

First model of the Gemini 3.5 generation (I/O, May 2026). Kept for compatibility; newer 3.6-3.8 Flash models are cheaper and stronger.

```bash
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-3.5-flash:generateContent" \
  -H "x-goog-api-key: $GEMINI_API_KEY" -H "Content-Type: application/json" \
  -d '{"contents":[{"parts":[{"text":"Hello"}]}]}'
```

Sources: [model page](https://ai.google.dev/gemini-api/docs/models/gemini-3.5-flash), [pricing](https://ai.google.dev/gemini-api/docs/pricing), [deprecations](https://ai.google.dev/gemini-api/docs/deprecations), [I/O blog](https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-5/).

Model page: https://postcutoff.com/m/gemini-3-5-flash/