LLMgoogle

Google: Gemini 3 Flash Preview (batch)

Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...

Anyone in the Project can @-mention Google: Gemini 3 Flash Preview (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 Flash Preview (batch) delivers Google's latest multimodal reasoning at batch-optimized pricing — $0.25 input makes it viable for high-volume document processing, video analysis, and audio transcription workflows. The 1M token context window handles feature-length videos or entire codebases in one pass. Trade-off: batch mode means no streaming and potential latency (minutes to hours depending on queue depth). Reach for this when cost and context matter more than real-time response.

Best for

Batch video analysis across large catalogs
Cost-sensitive document processing pipelines
Audio transcription at scale
Multimodal data labeling workflows
Long-context code repository analysis

Strengths

The 1M token context window absorbs entire feature films, multi-hour podcasts, or 50+ PDF reports without chunking. Multimodal support spans text, image, audio, video, and file uploads — rare breadth at this price point. Batch pricing ($0.25/$1.50 per Mtok) undercuts real-time Gemini variants by 50-75%, making it economical for overnight processing jobs or background enrichment tasks. Google's infrastructure typically delivers strong vision and audio understanding relative to text-only competitors.

Trade-offs

Batch processing introduces unpredictable latency — jobs may complete in minutes or queue for hours during peak demand, making this unsuitable for user-facing applications. No streaming means you wait for the full response or nothing. Preview status signals potential API changes and limited production SLAs. Without public benchmarks, you're flying blind on reasoning quality relative to Claude 3.7 Sonnet or GPT-4.5 — expect to run your own evals before committing production traffic.

Specifications

Provider: google
Category: llm
Context length: 1,048,576 tokens
Max output: 65,536 tokens
Modalities: text, image, file, audio, video
License: proprietary
Released: 2025-12-17

Pricing

Input: $0.25/Mtok
Output: $1.50/Mtok
Model ID: google/gemini-3-flash-preview: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

$11.00

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

Summarize Video Transcript

Watch this video and provide a structured summary with: (1) main topics discussed, (2) key decisions made, (3) action items with owners, and (4) unresolved questions. Format as markdown with clear sections.

Open in a Project →

Analyze Codebase Structure

Review all files in this repository and describe: (1) the overall architecture pattern (MVC, microservices, etc.), (2) main modules and their responsibilities, (3) external dependencies, and (4) potential technical debt or anti-patterns you observe.

Open in a Project →

Extract Data from Documents

Extract all invoice line items from these documents into a JSON array. Each entry should include: vendor, date, item description, quantity, unit price, and total. Flag any missing or ambiguous fields.

Open in a Project →

Transcribe and Tag Audio

Transcribe this audio file and then tag it with: (1) primary topics discussed (max 5), (2) speaker sentiment (positive/neutral/negative), (3) any product or brand mentions, and (4) a one-sentence summary.

Open in a Project →

Compare Visual Assets

Compare these product images and report: (1) visual inconsistencies (lighting, angle, background), (2) missing or extra elements relative to the first image, and (3) recommendations to standardize the set for e-commerce display.

Open in a Project →

Compare with

Compare Google: Gemini 3 Flash Preview (batch) with…

More language models

See all language models →