LLMgoogle

Google: Gemini 3.5 Flash Lite (batch)

Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.

Anyone in the Project can @-mention Google: Gemini 3.5 Flash Lite (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 Lite (batch) targets high-volume, cost-sensitive workloads where speed matters less than price. At $0.15/Mtok input, it undercuts most competitors by 50-80%, making it viable for large-scale classification, tagging, or extraction jobs. The batch-only interface means no real-time use, and quality likely trails standard Flash models. Reach for this when you're processing millions of tokens and can tolerate 24-48 hour turnaround.

Best for

Bulk document classification at scale
High-volume data extraction pipelines
Cost-sensitive content moderation
Batch tagging of image libraries
Large corpus summarization jobs

Strengths

The pricing structure makes this the cheapest multimodal option in Google's lineup, suitable for workloads where per-token cost dominates total expense. The 1M token context window handles book-length documents or hundreds of images in a single request. Multimodal support across text, image, video, and audio means you can process mixed-media datasets without switching models. Batch processing allows you to queue thousands of requests and let them run overnight.

Trade-offs

Batch-only delivery eliminates real-time use cases entirely — expect hours of latency, not seconds. The 'Lite' designation suggests reduced capability versus standard Gemini 3.5 Flash, though Google hasn't published comparative benchmarks. Output pricing at $1.25/Mtok is 8x the input rate, penalizing verbose responses. No public benchmark data means you're flying blind on reasoning quality, factual accuracy, and instruction-following relative to peers like GPT-4o-mini or Claude Haiku.

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: 2026-07-21

Pricing

Input: $0.15/Mtok
Output: $1.25/Mtok
Model ID: google/gemini-3.5-flash-lite: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

$8.45

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

Extract Invoice Fields

Extract the following fields from this invoice: vendor name, invoice date, invoice number, total amount, and all line items with descriptions and prices. Return as JSON.

Open in a Project →

Classify Support Tickets

Classify this support ticket into one of these categories: billing, technical, account, feature request, or other. Provide only the category name and a one-sentence reason.

Open in a Project →

Tag Product Images

Generate 5-8 descriptive tags for this product image. Focus on color, style, material, and key features. Return as a comma-separated list.

Open in a Project →

Summarize Research Papers

Summarize this research paper in 150 words. Include the main hypothesis, methodology, key findings, and implications. Use plain language.

Open in a Project →

Moderate User Content

Review this content for policy violations: hate speech, graphic violence, sexual content, or spam. Return 'safe' or list specific violations with brief explanations.

Open in a Project →

Compare with

Compare Google: Gemini 3.5 Flash Lite (batch) with…

More language models

See all language models →