LLMgoogle

Google: Gemini 3.6 Flash (batch)

Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...

Anyone in the Project can @-mention Google: Gemini 3.6 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 3.6 Flash Batch is Google's asynchronous processing variant, trading immediate response for dramatically lower cost — $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 instead of real-time streaming. Reach for this when you're processing large volumes of data overnight and cost matters more than latency.

Best for

Overnight batch processing of documents
Cost-sensitive video analysis at scale
Large codebase audits and reviews
High-volume image classification tasks
Asynchronous content moderation pipelines

Strengths

The $0.75/Mtok input pricing undercuts most competitors by 3-5x while maintaining full multimodal support across text, images, video, and audio. The 1M token context window lets you feed entire repositories or hour-long videos in a single request without chunking. Batch mode architecture allows Google to optimize inference scheduling, passing those savings directly to you. The Flash architecture maintains reasonable quality despite the aggressive cost optimization.

Trade-offs

Batch processing means 24-hour maximum turnaround — this model cannot handle real-time conversations or interactive workflows. Without public benchmarks, quality relative to Gemini 3.6 Flash standard remains unverified in our testing. You lose streaming responses and immediate feedback, making it unsuitable for user-facing applications. The cost savings only materialize at scale; small jobs under 100K tokens see minimal benefit over standard Flash pricing.

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: $0.38/Mtok
Output: $1.88/Mtok
Model ID: google/gemini-3.6-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

$14.52

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

Codebase Security Audit

Review this codebase for security vulnerabilities. Focus on SQL injection risks, authentication bypasses, and exposed secrets. For each finding, cite the specific file and line number, explain the risk, and suggest a fix.

Open in a Project →

Video Content Categorization

Watch this video and create a detailed content breakdown. List all major topics discussed with timestamps, identify any products or brands mentioned, and flag content that might require moderation review.

Open in a Project →

Document Translation Pipeline

Translate this document from English to Spanish. Preserve all formatting, including headers, bullet points, and tables. Maintain technical terminology accuracy and flag any ambiguous phrases that need human review.

Open in a Project →

Image Dataset Labeling

Analyze this image and provide structured labels in JSON format. Include: main objects present, scene type, dominant colors, text visible in image, and estimated time of day. Use consistent taxonomy across all images.

Open in a Project →

Research Paper Synthesis

Read these research papers and create a synthesis report. Identify common themes, contradictory findings, and gaps in the research. Organize by topic area and cite specific papers when referencing claims.

Open in a Project →

Compare with

Compare Google: Gemini 3.6 Flash (batch) with…

More language models

See all language models →