Switchy
Sign up
LLMgoogle

Google: Gemini 3.1 Pro Preview (batch)

Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...

Anyone in the Project can @-mention Google: Gemini 3.1 Pro 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 3.1 Pro Preview (batch) is Google's asynchronous processing variant, trading real-time response for dramatically lower cost—$1 input/$6 output per Mtok makes it one of the cheapest capable models available. The million-token context window handles book-length documents, and native multimodal support (audio, video, image, file) means you can throw mixed-media datasets at it without preprocessing. Best for high-volume jobs where you can wait minutes to hours: document classification pipelines, batch video analysis, or cost-sensitive research workflows that need long-context reasoning.

Best for

  • High-volume document classification pipelines
  • Batch video content analysis
  • Cost-sensitive long-context research tasks
  • Multimodal dataset processing at scale
  • Asynchronous content moderation workflows

Strengths

The pricing is the headline: at $1/$6 per Mtok, this undercuts most competitors by 3-10x for batch workloads. The 1M token context window rivals Claude's extended offerings, making it viable for full-book summarization or codebase analysis. Native multimodal support—audio, video, image, file—eliminates transcription or OCR preprocessing steps. Batch mode suits workflows where latency doesn't matter: overnight processing runs, scheduled content audits, or research pipelines that can queue requests.

Trade-offs

Batch processing introduces latency—expect minutes to hours, not seconds. No public benchmarks yet means you're flying blind on quality relative to GPT-4o or Claude Sonnet; internal testing is mandatory before production use. Google's API ecosystem lags OpenAI's in tooling maturity, so expect more integration friction. The 'preview' label signals this is pre-stable: features and pricing may shift. If you need real-time responses or proven benchmark performance, standard Gemini Pro or competitors are safer bets.

Specifications

Provider
google
Category
llm
Context length
1,048,576 tokens
Max output
65,536 tokens
Modalities
audio, file, image, text, video
License
proprietary
Released
2026-02-19

Pricing

Input
$1.00/Mtok
Output
$6.00/Mtok
Model ID
google/gemini-3.1-pro-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

Estimated monthly spend
$44.00
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

Batch Video Transcript Analysis

Analyze these video files for recurring themes, speaker sentiment, and key decision points. Provide a structured summary with timestamps for each major topic shift.
Open in a Project →

Multi-Document Policy Comparison

Compare these three policy documents (totaling 800K tokens) and identify contradictions, gaps in coverage, and areas where requirements conflict. Output a table with specific section references.
Open in a Project →

Cost-Optimized Code Review

Review this codebase for security vulnerabilities, deprecated patterns, and opportunities to reduce complexity. Prioritize findings by severity and provide file-level recommendations.
Open in a Project →

Multimodal Dataset Labeling

Label each item in this dataset (images, audio clips, text snippets) with category tags, confidence scores, and a brief justification. Flag any items that don't fit the provided taxonomy.
Open in a Project →

Overnight Content Moderation

Review these user submissions for policy violations: hate speech, misinformation, copyright concerns. For each flagged item, cite the specific policy clause and recommend action (remove, warn, allow with note).
Open in a Project →

Compare with

More language models

See all language models →

Data last verified 7 hours ago.Sources aggregated hourly to weekly. See docs/architecture/model-directory.md.