Skip to main content

Overview

Google’s Gemini models offer industry-leading context windows (up to 2 million tokens), exceptional multimodal capabilities, and strong performance across text, code, and reasoning tasks.

Available Models

Gemini 3.8 Flash

3 credits • Gemini’s newest Flash model, built for long-horizon engineering and autonomous agents.
  • 1M context window
  • Exceptional reasoning (reasoning model)
  • Speed: Fast • Cost: Medium
  • Vision: images supported

Gemini 3.7 Flash

2 credits • The newest Gemini Flash model, with a 1M-token context window and native multimodal input.
  • 1.05M context window
  • Exceptional reasoning (reasoning model)
  • Speed: Fast • Cost: Medium
  • Vision: images supported
  • Model id: gemini-3.7-flash

Gemini 3.6 Flash

2 credits • Balances speed with intelligence for strong performance on agentic and multimodal tasks.
  • 1M context window
  • Excellent reasoning (reasoning model)
  • Speed: Fast • Cost: Medium
  • Vision: images supported
  • Model id: gemini-3.6-flash

Gemini 3.5 Flash

3 credits • Most intelligent Gemini model for sustained frontier performance on agentic and coding tasks.
  • 1M context window
  • Exceptional reasoning (reasoning model)
  • Speed: Fast • Cost: Medium
  • Vision: images supported
  • Model id: gemini-3.5-flash

Gemini 3.5 Flash Lite

1 credit • The fastest, most cost-effective Gemini 3.5 model for high-throughput execution.
  • 1M context window
  • Good reasoning (reasoning model)
  • Speed: Very_fast • Cost: Very_low
  • Vision: images supported
  • Model id: gemini-3.5-flash-lite

Gemini 3.1 Flash Lite

1 credit • Frontier-class performance at a fraction of the cost, optimized for low latency and high-volume tasks.
  • 1M context window
  • Good reasoning (reasoning model)
  • Speed: Very_fast • Cost: Very_low
  • Vision: images supported
  • Model id: gemini-3.1-flash-lite

Gemini 3.1 Pro

3 credits • Reasoning-first Gemini model for complex agentic workflows and coding, with adaptive thinking.
  • 1M context window
  • Exceptional reasoning (reasoning model)
  • Speed: Medium • Cost: High
  • Vision: images supported
  • Model id: gemini-3.1-pro-preview

Gemini 3 Flash

1 credit • The latest Gemini 3 Flash model in preview, optimized for speed and efficiency while delivering strong reasoning and language capabilities.
  • 1M context window
  • Excellent reasoning (reasoning model)
  • Speed: Fast • Cost: Medium
  • Vision: images supported
  • Model id: gemini-3-flash-preview

Gemini 2.5 Flash

1 credit • A fast and capable model in the Gemini 2.5 series, balancing speed and reasoning performance for production use.
  • 1M context window
  • Excellent reasoning (reasoning model)
  • Speed: Fast • Cost: Medium
  • Vision: images supported
  • Model id: gemini-2.5-flash

Gemini 2.5 Flash Lite

1 credit • A lightweight, cost-efficient variant of Gemini 2.5 Flash, optimized for low latency and basic tasks.
  • 1M context window
  • Good reasoning (reasoning model)
  • Speed: Very_fast • Cost: Very_low
  • Vision: images supported
  • Model id: gemini-2.5-flash-lite

Setup

Using BoostGPT-Hosted API Keys

1

Select Gemini Model

In your BoostGPT dashboard, select any Gemini model when creating or configuring your bot.
2

Choose Your Model

  • Gemini 2.5 Flash: Best for most production use cases
  • Gemini 2.5 Pro: When you need massive 2M context
  • Gemini 2.5 Flash Lite: High-volume, cost-sensitive
  • Gemini 2.0 Flash Thinking: Complex reasoning tasks

Using Your Own Google AI API Key

1

Navigate to Integrations

Go to app.boostgpt.co and select Integrations
2

Select Google AI

Find and click on the Google provider
3

Add API Key

Get your API key from Google AI StudioEnter the API key and select which agents will use it
4

Save Configuration

Click save to apply your custom API key
Google AI offers a generous free tier for testing and development!

Model Selection Guide

Best for:
  • Production chatbots and customer support
  • General-purpose applications
  • Fast responses with strong reasoning
  • 1M context for long conversations
Sweet spot: Best balance of speed, cost, and capabilityCost: 2 credits per request
Best for:
  • Analyzing entire codebases
  • Processing very long documents (books, research papers)
  • Multi-turn conversations with full history
  • Maximum context retention (2M tokens)
Standout feature: Largest context window availableCost: 3 credits per request
Best for:
  • High-volume applications (thousands of requests)
  • Simple queries and responses
  • Cost-sensitive production
  • Quick classifications
Cost: 1 credit per request (most affordable)
Best for:
  • Mathematical problem solving
  • Code analysis and debugging
  • Multi-step logical reasoning
  • Scientific tasks
Note: Reasoning model with explicit thinkingCost: 3 credits per request
Best for:
  • Research and experimentation
  • Testing next-generation capabilities
  • Maximum context + latest features
Note: Preview model, may have breaking changesCost: 5 credits per request

Troubleshooting

Expected: Pro prioritizes accuracy over speedSolutions:
  • Use Flash for faster responses
  • Reduce input length when possible
  • Add loading indicators
Rare: 1M-2M context handles most casesSolutions:
  • Use Pro for maximum 2M context
  • Implement message pruning for extreme cases
  • Split very large documents
Cause: Long contexts consume many tokensSolutions:
  • Use Flash Lite for simple tasks (1 credit)
  • Implement context pruning
  • Set max_reply_tokens limits
  • Monitor token usage in dashboard

Next Steps

Model Comparison

Compare all providers

Reasoning Models

Learn about Flash Thinking

Bring Your Own Key

Use your Google AI API key

SDK Reference

Full API documentation