---
last_updated: 2026-11-22
source_url: https://opper.ai/google/gemini-3-8-flash
title: "Gemini 3.8 Flash by Google"
description: "Gemini 3.8 Flash is Google's workhorse multimodal model for software engineering and agentic tasks, pairing 1M context with image, audio, video, and PDF input."
---

# Gemini 3.8 Flash

By [Google](https://opper.ai/google).

Released 2 Sep 2026, 6 days after [Gemini Omni 1.1 Flash](https://opper.ai/google/gemini-omni-1-1-flash) · [Announcement](https://ai.google.dev/gemini-api/docs/deprecations) · [All Google releases](https://opper.ai/model-releases/google)

Gemini 3.8 Flash launched on September 2, 2026, the third Flash release in about six weeks after 3.6 Flash in July and 3.7 Flash in August. Google calls it its most intelligent workhorse model and reports significant improvements over 3.7 Flash in software engineering, agent tasks, and hard multi-step reasoning. It keeps the 1,048,576 token context window and 65,536 token output ceiling, accepts text, images, audio, video, and PDFs, and returns text.

The model scores 54.9% on HLE-Verified and, per Google, outperforms most larger frontier models on DeepSWE v1.1, and on hard problems it shows more diligence, running extra reasoning steps and calling tools iteratively. Thinking depth is selectable at low, medium, and high, and the feature set covers function calling, structured output, search grounding, code execution, and a preview of computer use.

Gemini 3.8 Flash suits production agents, coding assistants, and multimodal pipelines that need near-frontier quality at high volume. A separate Gemini 3.8 Flash Cyber variant tuned for vulnerability discovery and patching exists but is limited to Google's Fairwind program for trusted defenders.

## Available routes

Gemini 3.8 Flash runs on 5 different routes through the Opper gateway. Prices are per 1M tokens. Zero data retention on Google Cloud is available on Enterprise. In the EU it is served by Google Cloud. [See every Gemini model hosted in the EU](https://opper.ai/models/eu/gemini). Some routes also sell flex and priority processing: the same model at another price, picked per request with service_tier. [How service tiers work](https://docs.opper.ai/build/gateway/service-tiers). Its routes and prices, live from the catalogue, are public JSON with no API key needed at https://api.opper.ai/v3/models?q=gemini-3.8-flash.

| Provider | Model id | Region | Zero data retention | Training | Input | Output | Cache read |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [Google Cloud](https://opper.ai/provider/google) | `gemini/gemini-3.8-flash` | US (United States) | Abuse monitoring | No | $0.75 (50% off until 31 Dec, list $1.50) | $3.75 (50% off until 31 Dec, list $7.50) | $0.07 (list $0.15) ($0.79 write, list $1.58) |
| [Google Cloud](https://opper.ai/provider/google), Flex | `gemini:flex/gemini-3.8-flash` | US (United States) | Abuse monitoring | No | $0.38 | $1.88 | $0.04 |
| [Google Cloud](https://opper.ai/provider/google), Priority | `gemini:priority/gemini-3.8-flash` | US (United States) | Abuse monitoring | No | $1.35 | $6.75 | $0.14 |
| [Google Cloud](https://opper.ai/provider/google) | `vertexai-zdr/gemini-3.8-flash` | Multi-region | Yes, on Enterprise | No | $0.75 (50% off until 31 Dec, list $1.50) | $3.75 (50% off until 31 Dec, list $7.50) | $0.07 (list $0.15) |
| [Google Cloud](https://opper.ai/provider/google) | `vertexai-zdr/gemini-3.8-flash-eu` | EU | Yes, on Enterprise | No | $0.82 (50% off until 31 Dec, list $1.65) | $4.13 (50% off until 31 Dec, list $8.25) | $0.08 (list $0.17) |
| [Google Cloud](https://opper.ai/provider/google) | `vertexai/gemini-3.8-flash` | Multi-region | Abuse monitoring | No | $0.75 (50% off until 31 Dec, list $1.50) | $3.75 (50% off until 31 Dec, list $7.50) | $0.07 (list $0.15) ($0.79 write, list $1.58) |
| [Google Cloud](https://opper.ai/provider/google), Flex | `vertexai:global:flex/gemini-3.8-flash` | Multi-region | Abuse monitoring | No | $0.38 | $1.88 | $0.04 |
| [Google Cloud](https://opper.ai/provider/google), Priority | `vertexai:global:priority/gemini-3.8-flash` | Multi-region | Abuse monitoring | No | $1.35 | $6.75 | $0.14 |
| [Google Cloud](https://opper.ai/provider/google) | `vertexai/gemini-3.8-flash-eu` | EU | Abuse monitoring | No | $0.82 (50% off until 31 Dec, list $1.65) | $4.13 (50% off until 31 Dec, list $8.25) | $0.08 (list $0.17) ($0.87 write, list $1.73) |
| [Google Cloud](https://opper.ai/provider/google), Priority | `vertexai:eu:priority/gemini-3.8-flash` | EU | Abuse monitoring | No | $1.49 | $7.42 | $0.15 |

## Key info

- Model id: `gemini-3.8-flash` (routes across Google Cloud)
- Input: Text, Image, Audio, Video, Files
- Output: Text
- Features: Tools, Structured output, PDF input
- Context window: 1M
- Max output: 66K
- Input price: $0.75 per 1M tokens ($0.07 cache read · $0.79 write) (50% off until 31 Dec, list $1.50)
- Output price: $3.75 per 1M tokens (50% off until 31 Dec, list $7.50)
- Released: 2 Sep 2026
- EU residency available on Google Cloud
- US residency available on Google Cloud
- Zero data retention with abuse monitoring
- Zero data retention on Enterprise
- No training by default

## Data handling per route

Each route hosting Gemini 3.8 Flash has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

### Google Cloud — United States

Zero data retention with abuse monitoring: prompts and outputs are kept for abuse monitoring only, for a window the provider does not state, and are not used for training. No training on customer data. US; SCCs.

- Zero data retention: With abuse monitoring, window not stated.
- Training: No training on customer data.
- Logging: Abuse monitoring
- Abuse monitoring: On by default, holds flagged content, 55 days, a person can view samples
- Transfer mechanism: SCCs

Verified by Opper on 2026-09-17.

### Google Cloud — Multi-region

Zero data retention: nothing is logged, held for abuse monitoring or used for training. Available under a signed Enterprise agreement. No training on customer data. GLOBAL; SCCs.

- Zero data retention: Yes, on Enterprise. Nothing is logged, held for abuse monitoring or used for training.
- Plan: Signed Enterprise agreement
- Training: No training on customer data.
- Logging: None
- Abuse monitoring: On by default, keeps nothing
- Caching: Content cached for replay
- Transfer mechanism: SCCs

Verified by Opper on 2026-09-02.

### Google Cloud — EU

Zero data retention: nothing is logged, held for abuse monitoring or used for training. Available under a signed Enterprise agreement. No training on customer data. EU.

- Zero data retention: Yes, on Enterprise. Nothing is logged, held for abuse monitoring or used for training.
- Plan: Signed Enterprise agreement
- Training: No training on customer data.
- Logging: None
- Abuse monitoring: On by default, keeps nothing
- Caching: Content cached for replay
- Transfer mechanism: Not applicable — data stays in EU

Verified by Opper on 2026-09-02.

### Google Cloud — Multi-region

Zero data retention with abuse monitoring: nothing is logged or used for training; content flagged by abuse monitoring is held for review. No training on customer data. GLOBAL; SCCs.

- Zero data retention: With abuse monitoring, flagged content held.
- Training: No training on customer data.
- Logging: None
- Abuse monitoring: On by default, holds flagged content, 90 days, a person can view samples
- Transfer mechanism: SCCs

Verified by Opper on 2026-10-26.

### Google Cloud — EU

Zero data retention with abuse monitoring: nothing is logged or used for training; content flagged by abuse monitoring is held for review. No training on customer data. EU.

- Zero data retention: With abuse monitoring, flagged content held.
- Training: No training on customer data.
- Logging: None
- Abuse monitoring: On by default, holds flagged content, 90 days, a person can view samples
- Transfer mechanism: Not applicable — data stays in EU

Verified by Opper on 2026-10-26.

## Best for

Where Gemini 3.8 Flash ranks among the models on Opper with a score for each use case (0 to 100).

- [Legal](https://opper.ai/models?use=legal): 41.7, #21 of 53 (Legal tasks and reasoning)
- [Finance](https://opper.ai/models?use=finance): 42.4, #24 of 53 (Finance and accounting)
- [Healthcare](https://opper.ai/models?use=healthcare): 38.3 (Healthcare and medical)
- [Coding](https://opper.ai/models?use=coding): 19.1 (FrontierCode 2.0 and Terminal-Bench 4.0)
- [Agents](https://opper.ai/models?use=agents): 40.3, #35 of 93 (Terminal-Bench 4.0 and AutomationBench)

## Benchmarks

Independent benchmark scores via [Artificial Analysis](https://artificialanalysis.ai) ([view on AA](https://artificialanalysis.ai/models/gemini-3-8-flash)). Indices and domain scores are out of 100, Omniscience runs from −100 to 100, Briefcase is an Elo rating, and the other evaluation scores are the share of tasks solved.

- Global rank: #30 of 520 LLMs on the [LLM leaderboard](https://opper.ai/llm-leaderboard)
- Tier: Strong
- Output speed: 109 tok/s
- Intelligence Index: 30.8

### Coding

- FrontierCode 2.0: 19%
- Terminal-Bench 4.0: 20%
- SciCode: 57%

### Agentic & knowledge work

- AutomationBench: 61%
- GDPval: 47%
- GDP.pdf: 23%
- Briefcase (Elo): 1205

### Science & reasoning

- Terminal-Bench Science: 11%
- CritPt (hard): 47%
- HLE Diamond: 33%
- Humanity's Last Exam: 48%
- GPQA Diamond: 95%
- Long-context reasoning: 84%

### Knowledge

- Omniscience: 23.7
- MMMU-Pro: 86%

### By domain

- Finance & accounting: 42.4
- Legal: 41.7
- Healthcare & medical: 38.3
- Engineering: 38.8
- Economics: 40.1
- Strategy & operations: 47.2

## Get started

Call Gemini 3.8 Flash through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.

Gemini 3.8 Flash is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

### Set it up with your agent

Paste this into a coding agent like Claude Code, Cursor or Codex and it will wire up Opper for you:

```text
Use curl to download, read and follow: https://skills.opper.ai Call Gemini 3.8 Flash
```

### Or call it directly

OpenAI:

```javascript
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.OPPER_API_KEY,
  baseURL: "https://api.opper.ai/v3/compat",
});

const completion = await client.chat.completions.create({
  model: "gemini-3.8-flash",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);
```

Anthropic:

```javascript
import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  apiKey: process.env.OPPER_API_KEY,
  baseURL: "https://api.opper.ai/v3/compat",
});

const message = await client.messages.create({
  model: "gemini-3.8-flash",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Hello" }],
});
console.log(message.content);
```

Gemini:

```javascript
import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({
  apiKey: process.env.OPPER_API_KEY,
  httpOptions: { baseUrl: "https://api.opper.ai/v3/compat" },
});

const response = await ai.models.generateContent({
  model: "gemini-3.8-flash",
  contents: "Hello",
});
console.log(response.text);
```

cURL:

```bash
curl https://api.opper.ai/v3/compat/chat/completions \
  -H "Authorization: Bearer $OPPER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.8-flash",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'
```

## Use Gemini 3.8 Flash in your apps

Pick your tool to see how to run it on Gemini 3.8 Flash through Opper.

- [Claude Code](https://opper.ai/apps/claude-code/gemini-3-8-flash)
- [Claude Cowork](https://opper.ai/apps/claude-cowork/gemini-3-8-flash)
- [Codex](https://opper.ai/apps/codex/gemini-3-8-flash)
- [DeepSeek Harness](https://opper.ai/apps/deepseek-harness/gemini-3-8-flash)
- [GitHub Copilot CLI](https://opper.ai/apps/github-copilot-cli/gemini-3-8-flash)
- [Aider](https://opper.ai/apps/aider/gemini-3-8-flash)
- [Goose](https://opper.ai/apps/goose/gemini-3-8-flash)
- [Droid](https://opper.ai/apps/droid/gemini-3-8-flash)
- [OpenCode](https://opper.ai/apps/opencode/gemini-3-8-flash)
- [Pi](https://opper.ai/apps/pi/gemini-3-8-flash)
- [OpenClaw](https://opper.ai/apps/openclaw/gemini-3-8-flash)
- [Hermes](https://opper.ai/apps/hermes/gemini-3-8-flash)
- [Copilot for Obsidian](https://opper.ai/apps/obsidian-copilot/gemini-3-8-flash)
- [OmniRoute](https://opper.ai/apps/omniroute/gemini-3-8-flash)
- [Cursor](https://opper.ai/apps/cursor/gemini-3-8-flash)
- [Cline](https://opper.ai/apps/cline/gemini-3-8-flash)
- [Continue](https://opper.ai/apps/continue/gemini-3-8-flash)
- [Kilo Code](https://opper.ai/apps/kilo-code/gemini-3-8-flash)
- [GitHub Copilot](https://opper.ai/apps/github-copilot/gemini-3-8-flash)
- [Zed](https://opper.ai/apps/zed/gemini-3-8-flash)
- [JetBrains AI Assistant](https://opper.ai/apps/jetbrains-ai-assistant/gemini-3-8-flash)
- [Voidleap Code](https://opper.ai/apps/voidleap-code/gemini-3-8-flash)
- [n8n](https://opper.ai/apps/n8n/gemini-3-8-flash)
- [LibreChat](https://opper.ai/apps/librechat/gemini-3-8-flash)
- [Open WebUI](https://opper.ai/apps/open-webui/gemini-3-8-flash)
- [See all apps](https://opper.ai/apps)

## Other models from Google

- [Gemini 4 Argon](https://opper.ai/google/gemini-4-argon)
- [Gemini 3.5 Flash-Lite](https://opper.ai/google/gemini-3-5-flash-lite)
- [Gemini 3.7 Flash](https://opper.ai/google/gemini-3-7-flash)
- [Gemini 3.6 Flash](https://opper.ai/google/gemini-3-6-flash)
- [Gemini 3.5 Flash](https://opper.ai/google/gemini-3-5-flash)
- [Gemini 3.1 Pro Preview](https://opper.ai/google/gemini-3-1-pro-preview)
