LLMgoogle

Google: Gemini 3.5 Flash (batch)

Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...

Anyone in the Project can @-mention Google: Gemini 3.5 Flash (batch) with the team's shared context - pooled credits, one chat, one memory.

All models

Starter is free forever - 1 Project, 100 credits/month, 1 MCP. No card.

Verdict

Gemini 3.5 Flash (batch) is Google's asynchronous processing variant, trading immediate responses for dramatically lower costs—$0.75/Mtok input makes it one of the cheapest multimodal models available. The million-token context window handles entire codebases or long videos, but batch mode means 24-hour turnaround times. Reach for this when you're processing large volumes of multimodal content on a schedule, not when you need real-time answers.

Best for

Overnight processing of video archives
Bulk document analysis jobs
Cost-sensitive multimodal workflows
Large codebase summarization tasks
Scheduled content moderation pipelines

Strengths

The pricing structure makes this the most economical option for high-volume multimodal work—input costs are 85% lower than real-time Gemini variants. The 1M token context window ingests feature-length videos, entire repositories, or hundreds of PDFs in a single request. Native support for video, audio, images, and files means no preprocessing pipeline. Batch mode eliminates rate-limit concerns when processing thousands of items overnight.

Trade-offs

Batch processing introduces 24-hour latency—requests queue and return results asynchronously, making this unsuitable for interactive applications or user-facing features. Without published benchmarks, quality comparisons to Claude or GPT-4 remain unclear. Google's batch API requires different integration patterns than standard streaming endpoints, adding implementation complexity. The model may lag behind real-time variants in capability updates since batch infrastructure typically trails production releases.

Specifications

Provider: google
Category: llm
Context length: 1,048,576 tokens
Max output: 65,536 tokens
Modalities: text, image, video, file, audio
License: proprietary
Released: 2026-05-19

Pricing

Input: $0.75/Mtok
Output: $4.50/Mtok
Model ID: google/gemini-3.5-flash:batch

Per-token prices show what the model costs upstream. On Switchy your team draws from one shared org credit pool - one plan, one balance for everyone.

Team cost calculator

Seats5 peopleMessages / seat / day80Avg turn size2 ktokOutput share30 %

Estimated monthly spend

$33.00

17.6M tokens / month
5 seats · 80 msgs/day

Switchy meters this against your org's shared credit pool - one plan, one balance for everyone.

Providers

Provider-level routing data is not available yet for this model.

Performance

Performance snapshots are collected daily. Check back after the next ingestion run.

Benchmarks

Public benchmark scores are not available yet for this model. Check back after the next ingestion run.

Works well with

Top MCPs

Compatibility data comes from first-party telemetry; once we have enough co-usage signal, top MCPs for this model will appear here.

How Switchy teams use it

Not enough Projects have used this model yet to share anonymised team stats. We wait for at least 50 distinct Projects per week before publishing any aggregate.

Starter prompts

Video Content Extraction

Watch this video and extract: (1) all on-screen text that appears, (2) main topics discussed with timestamps, (3) any products or brands shown. Return as JSON with timestamp references.

Open in a Project →

Codebase Documentation

Review all files in this repository. Write a technical README covering: architecture decisions, main entry points, data flow between modules, and setup instructions for new developers. Focus on what's non-obvious from file names.

Open in a Project →

Bulk Image Categorization

Categorize these product images into: Electronics, Apparel, Home Goods, or Other. For each image provide the category and a 10-word description of what's shown. Return as a numbered list.

Open in a Project →

Multi-Document Synthesis

Read these 40 customer feedback PDFs. Identify the top 5 recurring complaints, the top 3 feature requests, and any safety concerns mentioned more than twice. Quote specific customer language for each finding.

Open in a Project →

Audio Transcription Analysis

Transcribe this audio file, then analyze the speaker's tone and identify: key decisions made, action items mentioned, and any points of disagreement. Separate transcription from analysis clearly.

Open in a Project →

Compare with

Compare Google: Gemini 3.5 Flash (batch) with…

More language models

See all language models →