tokevenGemini · Fast / Budget · 1,000K context window
Gemini 3 Flash pricing for rag pipeline
$0.007500 per call at 6,000 input / 1,500 output tokens.
Per call
$0.007500
10K calls/mo
$75
Cache savings
75% off input
Batch savings
50% off all
Calculate your Gemini 3 Flash costs
Adjust token counts, volume, and discount toggles to model your rag pipeline spend. Pricing updated weekly.
Configure your usage
Estimated cost
Quick start
Call Gemini 3 Flash with the Google Generative AI SDK:
import google.generativeai as genai
model = genai.GenerativeModel("gemini-3-flash")
response = model.generate_content("Your prompt here")
# Cost: ~$0.007500 per call at standard rates
# Input: $0.50/MTok
# Output: $3.00/MTokHow Gemini 3 Flash compares on cost
Per-call cost for all models scoring 50+ on rag pipeline benchmarks. Hover for details.
Cheapest viable option: Claude Haiku 4.5 at $0.0135/call (-80% less, 86/100 quality).
Complete Gemini 3 Flash pricing breakdown
Standard token rates
| Direction | $/MTok | Tokens per call |
|---|---|---|
| Input | $0.50 | 6,000 |
| Output | $3.00 | 1,500 |
Prompt caching: 75% off input tokens
Caching drops input cost from $0.50 to $0.13/MTok. For repeated system prompts, that saves $0.002250 per call.
Batch API: 50% off all tokens
Submit requests asynchronously and receive 50% off all token costs. This works best for offline pipelines where latency requirements are flexible.
Monthly cost projections
| Monthly volume | Cost per call | Standard monthly | Cached monthly | You save with caching |
|---|---|---|---|---|
| 10,000 calls | $0.007500 | $75 | $52.5 | $22.5 |
| 50,000 calls | $0.007500 | $375 | $262.5 | $112.5 |
| 100,000 calls | $0.007500 | $750 | $525 | $225 |
| 500,000 calls | $0.007500 | $3,750 | $2,625 | $1,125 |
| 1,000,000 calls | $0.007500 | $7,500 | $5,250 | $2,250 |
Gemini 3 Flash quality benchmarks for rag pipeline
Gemini 3 Flash is a solid pick for rag pipeline
Scores 82/100 (rank #5 of 14). Good balance of quality and cost for rag pipeline.
Top-ranked: GPT 5.6 Terra (92/100) at $0.0375/call
Performance across all task types
Gemini 3 Flash scores by task type. RAG Pipeline highlighted.
| Task type | Confidence score | Rank out of 14 |
|---|---|---|
| Classification | 88/100 | #3 |
| Extraction | 86/100 | #3 |
| Summarization | 83/100 | #5 |
| Q&A(current page) | 82/100 | #5 |
| Code Generation | 65/100 | #7 |
| Code Review | 62/100 | #7 |
| Reasoning | 58/100 | #7 |
| Creative Writing | 52/100 | #8 |
Alternative models for rag pipeline
12 models score 80+ on rag pipeline benchmarks, sorted by input rate. Cheapest: Claude Haiku 4.5 (-80% less, 86/100 quality).
| Model | Provider | Input $/MTok | Output $/MTok | Quality | Per call | vs Gemini |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | Claude | $1.00 | $5.00 | 86/100 | $0.0135 | 80% more |
| GPT 5.6 Luna | GPT | $1.00 | $6.00 | 85/100 | $0.0150 | 100% more |
| Gemini 3.5 Flash | Gemini | $1.50 | $9.00 | 84/100 | $0.0225 | 200% more |
| Claude Sonnet 5 | Claude | $2.00 | $10.00 | 89/100 | $0.0270 | 260% more |
| Gemini 3.1 Pro | Gemini | $2.00 | $12.00 | 87/100 | $0.0300 | 300% more |
| GPT 5.4 | GPT | $2.50 | $15.00 | 91/100 | $0.0375 | 400% more |
| GPT 5.6 Terra | GPT | $2.50 | $15.00 | 92/100 | $0.0375 | 400% more |
| Claude Sonnet 4.6 | Claude | $3.00 | $15.00 | 88/100 | $0.0405 | 440% more |
| Claude Opus 4.8 | Claude | $5.00 | $25.00 | 85/100 | $0.0675 | 800% more |
| GPT 5.5 | GPT | $5.00 | $30.00 | 90/100 | $0.0750 | 900% more |
| GPT 5.6 Sol | GPT | $5.00 | $30.00 | 91/100 | $0.0750 | 900% more |
| Claude Fable 5 | Claude | $10.00 | $50.00 | 88/100 | $0.1350 | 1700% more |
About Gemini 3 Flash
Provider
Gemini
Tier
Fast / Budget
Context
1,000K tokens
Released
Mar 2026
Other models from Gemini
| Model | Tier | Input $/MTok | Output $/MTok | Context |
|---|---|---|---|---|
| Gemini 3.1 Pro | Mid-tier | $2.00 | $12.00 | 1,000K |
| Gemini 3.5 Flash | Fast / Budget | $1.50 | $9.00 | 1,000K |
| Gemini 3.5 Flash-Lite | Fast / Budget | $0.25 | $1.50 | 1,000K |
You can compare Gemini 3 Flash head-to-head against any other model on our model comparison pages, or track how pricing has changed over time on the pricing history tracker.
Gemini 3 Flash pricing for other use cases
See how Gemini 3 Flash costs change across different workload types.
Code Generation
$0.0130/call
Unit Test Generation
$0.0165/call
SQL Generation
$0.003750/call
API Generation
$0.0195/call
Code Refactoring
$0.0140/call
Code Review
$0.008500/call
PR Review
$0.0130/call
Security Review
$0.0105/call
Bug Detection
$0.008500/call
Document Summarization
$0.008000/call
PDF Summarization
$0.0120/call
Meeting Notes
$0.0100/call
Email Summarization
$0.003000/call
Chatbot
$0.004000/call
Customer Support Bot
$0.004500/call
FAQ Bot
$0.003150/call
Data Extraction
$0.005000/call
JSON Extraction
$0.003900/call
Invoice Parsing
$0.002800/call
Resume Parsing
$0.003650/call
Chain of Thought
$0.0165/call
Legal Analysis
$0.0170/call
Math Reasoning
$0.009750/call
Financial Analysis
$0.0160/call
Content Moderation
$0.000550/call
Sentiment Analysis
$0.000550/call
Categorization
$0.000850/call
Intent Detection
$0.000450/call
Copywriting
$0.006250/call
Blog Writing
$0.0245/call
Marketing Copy
$0.009400/call
Product Descriptions
$0.004750/call
Related pages
Frequently asked questions
How much does Gemini 3 Flash cost for rag pipeline per API call?
$0.007500 per call at 6,000 input / 1,500 output tokens.
Is Gemini 3 Flash the best model for rag pipeline?
Scores 82/100, rank #5 of 14 models. Top-ranked: GPT 5.6 Terra at 92/100.
What is the cheapest model for rag pipeline with good quality?
Claude Haiku 4.5 scores 86/100 quality at $1.00/$5.00 per MTok. That is -80% less than Gemini 3 Flash per call.
How can I reduce my Gemini 3 Flash costs for rag pipeline?
Three strategies: prompt caching (75% off input), batch API (50% off all tokens), prompt optimization. Combined: $0.007500 drops to about $0.000938 per call.
How does Gemini 3 Flash pricing compare to other Gemini models?
Gemini also offers: Gemini 3.1 Pro at $2.00/$12.00, Gemini 3.5 Flash at $1.50/$9.00, Gemini 3.5 Flash-Lite at $0.25/$1.50.
What context window does Gemini 3 Flash support?
1,000K tokens total. Typical rag pipeline calls use 6,000 plus 1,500 tokens, well within limits.
Track what you spend on AI
This calculator estimates costs based on published rates only. Connect your API usage to see where your money goes and which models drive your spend.