Model Selection & Plans

Choose the right plan for your use case based on rate limits, monthly quota, and available models.

Available Models

The BrainUs Query API supports the following models:

gemini-2.5-flash-lite

Fastest response times
Most cost-effective for high-volume queries
Ideal for simple queries and basic RAG operations
Available on all plans

gemini-2.5-flash

Enhanced performance for complex queries
Better reasoning capabilities
Available on Enterprise plan only
Recommended for production applications requiring higher quality

Plans & Pricing

Choose the plan that fits your needs:

Plan	Monthly Requests	Rate Limit	Models Available	Support	Price (LKR)
Free	300	10/min	gemini-2.5-flash-lite	Community	0
Starter	2,000	20/min	gemini-2.5-flash-lite	Community	999
Pro	10,000	60/min	gemini-2.5-flash-lite	Email	3,499
Enterprise	50,000	200/min	gemini-2.5-flash-lite, gemini-2.5-flash	Dedicated	14,999

All plans include access to the Query API with the same response format. Upgrade for more requests, faster rate limits, and access to premium models.

Plan Features

Prop

Type

Feature Breakdown

Feature	Free	Starter	Pro	Enterprise
Basic Query	✅	✅	✅	✅
Standard Response Time	✅	✅	✅	✅
Fast Response Time	❌	❌	✅	✅
Priority Support	❌	❌	❌	✅
Dedicated Support	❌	❌	❌	✅
gemini-2.5-flash Model	❌	❌	❌	✅
SLA Guarantee	❌	❌	❌	✅

Using Different Models

Default Model

By default, your plan's first allowed model is used:

curl -X POST https://api.brainus.lk/api/v1/dev/query \
  -H "X-API-Key: $BRAINUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "What is photosynthesis?",
    "store_id": "default"
  }'

This will use gemini-2.5-flash-lite for Free/Starter/Pro plans, or gemini-2.5-flash-lite for Enterprise.

Specify a Model (Enterprise Only)

Enterprise customers can specify which model to use:

curl -X POST https://api.brainus.lk/api/v1/dev/query \
  -H "X-API-Key: $BRAINUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "What is photosynthesis?",
    "store_id": "default",
    "model": "gemini-2.5-flash"
  }'

Valid values for your plan:

Free/Starter/Pro: gemini-2.5-flash-lite (only option)
Enterprise: gemini-2.5-flash-lite or gemini-2.5-flash

If you specify a model not available in your plan, the API will return a 403 error.

Rate Limits Per Plan

Plan	Requests/Minute	Requests/Day	Requests/Month
Free	10	300	300
Starter	20	2,000	2,000
Pro	60	10,000	10,000
Enterprise	200	50,000	50,000

When you exceed your rate limit, the API responds with HTTP 429 (Too Many Requests). See Rate Limits for handling strategies.

Choosing a Plan

Use Free when:

Testing the API
Learning and experimenting
Building prototypes

Use Starter when:

Small personal projects
Light production use
Budget-conscious applications

Use Pro when:

Production applications
Need faster response times
Regular API usage

Use Enterprise when:

Large-scale deployments
Need access to gemini-2.5-flash model
Require dedicated support
Need SLA guarantees

Upgrading Your Plan

To upgrade your plan:

Visit Developer Dashboard
Navigate to Plans & Billing
Select your desired plan
Complete the payment process

Your upgrade takes effect immediately. No need to update your API key.

Model Selection Strategy

Start with gemini-2.5-flash-lite - It's fast, cost-effective, and works well for most use cases
For complex queries - Upgrade to Enterprise plan for access to gemini-2.5-flash
For high volume - Upgrade to Pro or Enterprise for higher rate limits
For premium support - Enterprise plan includes dedicated support

Next Steps

Basic Usage - Get started with queries
Filters & Options - Learn about filtering
Rate Limits - Understand rate limit handling

On this page