tokevenGemini · Mid-tier · 1,000K context window
Gemini 3.1 Pro pricing for rag pipeline
$0.0300 per call at 6,000 input / 1,500 output tokens.
Per call
$0.0300
10K calls/mo
$300
Cache savings
75% off input
Batch savings
50% off all
Calculate your Gemini 3.1 Pro 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 3.1 Pro with the Google Generative AI SDK:
import google.generativeai as genai
model = genai.GenerativeModel("gemini-3.1-pro")
response = model.generate_content("Your prompt here")
# Cost: ~$0.0300 per call at standard rates
# Input: $2.00/MTok
# Output: $12.00/MTokHow Gemini 3.1 Pro compares on cost
Per-call cost for all models scoring 50+ on rag pipeline benchmarks. Hover for details.
Cheapest viable option: Gemini 3 Flash at $0.007500/call (75% less, 82/100 quality).
Complete Gemini 3.1 Pro pricing breakdown
Standard token rates
| Direction | $/MTok | Tokens per call |
|---|---|---|
| Input | $2.00 | 6,000 |
| Output | $12.00 | 1,500 |
Prompt caching: 75% off input tokens
Caching drops input cost from $2.00 to $0.50/MTok. For repeated system prompts, that saves $0.009000 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 | $0.0300 | $300 | $210 | $90 |
| 50,000 calls | $0.0300 | $1,500 | $1,050 | $450 |
| 100,000 calls | $0.0300 | $3,000 | $2,100 | $900 |
| 500,000 calls | $0.0300 | $15,000 | $10,500 | $4,500 |
| 1,000,000 calls | $0.0300 | $30,000 | $21,000 | $9,000 |
Gemini 3.1 Pro quality benchmarks for rag pipeline
Gemini 3.1 Pro is a solid pick for rag pipeline
Scores 87/100 (rank #4 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 3.1 Pro scores by task type. RAG Pipeline highlighted.
| Task type | Confidence score | Rank out of 14 |
|---|---|---|
| Reasoning | 90/100 | #4 |
| Summarization | 87/100 | #4 |
| Q&A(current page) | 87/100 | #4 |
| Code Generation | 86/100 | #5 |
| Classification | 86/100 | #3 |
| Extraction | 85/100 | #4 |
| Code Review | 84/100 | #4 |
| Creative Writing | 84/100 | #4 |
Alternative models for rag pipeline
12 models score 80+ on rag pipeline benchmarks, sorted by input rate. Cheapest: Gemini 3 Flash (75% less, 82/100 quality).
| Model | Provider | Input $/MTok | Output $/MTok | Quality | Per call | vs Gemini |
|---|---|---|---|---|---|---|
| Gemini 3 Flash | Gemini | $0.50 | $3.00 | 82/100 | $0.007500 | 75% cheaper |
| Claude Haiku 4.5 | Claude | $1.00 | $5.00 | 86/100 | $0.0135 | 55% cheaper |
| GPT 5.6 Luna | GPT | $1.00 | $6.00 | 85/100 | $0.0150 | 50% cheaper |
| Gemini 3.5 Flash | Gemini | $1.50 | $9.00 | 84/100 | $0.0225 | 25% cheaper |
| Claude Sonnet 5 | Claude | $2.00 | $10.00 | 89/100 | $0.0270 | 10% cheaper |
| GPT 5.4 | GPT | $2.50 | $15.00 | 91/100 | $0.0375 | 25% more |
| GPT 5.6 Terra | GPT | $2.50 | $15.00 | 92/100 | $0.0375 | 25% more |
| Claude Sonnet 4.6 | Claude | $3.00 | $15.00 | 88/100 | $0.0405 | 35% more |
| Claude Opus 4.8 | Claude | $5.00 | $25.00 | 85/100 | $0.0675 | 125% more |
| GPT 5.5 | GPT | $5.00 | $30.00 | 90/100 | $0.0750 | 150% more |
| GPT 5.6 Sol | GPT | $5.00 | $30.00 | 91/100 | $0.0750 | 150% more |
| Claude Fable 5 | Claude | $10.00 | $50.00 | 88/100 | $0.1350 | 350% more |
About Gemini 3.1 Pro
Provider
Gemini
Tier
Mid-tier
Context
1,000K tokens
Released
Apr 2026
Other models from Gemini
| Model | Tier | Input $/MTok | Output $/MTok | Context |
|---|---|---|---|---|
| Gemini 3.5 Flash | Fast / Budget | $1.50 | $9.00 | 1,000K |
| Gemini 3 Flash | Fast / Budget | $0.50 | $3.00 | 1,000K |
| Gemini 3.5 Flash-Lite | Fast / Budget | $0.25 | $1.50 | 1,000K |
You can compare Gemini 3.1 Pro 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 3.1 Pro pricing for other use cases
See how Gemini 3.1 Pro costs change across different workload types.
Code Generation
$0.0520/call
Unit Test Generation
$0.0660/call
SQL Generation
$0.0150/call
API Generation
$0.0780/call
Code Refactoring
$0.0560/call
Code Review
$0.0340/call
PR Review
$0.0520/call
Security Review
$0.0420/call
Bug Detection
$0.0340/call
Document Summarization
$0.0320/call
PDF Summarization
$0.0480/call
Meeting Notes
$0.0400/call
Email Summarization
$0.0120/call
Chatbot
$0.0160/call
Customer Support Bot
$0.0180/call
FAQ Bot
$0.0126/call
Data Extraction
$0.0200/call
JSON Extraction
$0.0156/call
Invoice Parsing
$0.0112/call
Resume Parsing
$0.0146/call
Chain of Thought
$0.0660/call
Legal Analysis
$0.0680/call
Math Reasoning
$0.0390/call
Financial Analysis
$0.0640/call
Content Moderation
$0.002200/call
Sentiment Analysis
$0.002200/call
Categorization
$0.003400/call
Intent Detection
$0.001800/call
Copywriting
$0.0250/call
Blog Writing
$0.0980/call
Marketing Copy
$0.0376/call
Product Descriptions
$0.0190/call
Related pages
Frequently asked questions
How much does Gemini 3.1 Pro cost for rag pipeline per API call?
$0.0300 per call at 6,000 input / 1,500 output tokens.
Is Gemini 3.1 Pro the best model for rag pipeline?
Scores 87/100, rank #4 of 14 models. Top-ranked: GPT 5.6 Terra at 92/100.
What is the cheapest model for rag pipeline with good quality?
Gemini 3 Flash scores 82/100 quality at $0.50/$3.00 per MTok. That is 75% less than Gemini 3.1 Pro per call.
How can I reduce my Gemini 3.1 Pro costs for rag pipeline?
Three strategies: prompt caching (75% off input), batch API (50% off all tokens), prompt optimization. Combined: $0.0300 drops to about $0.003750 per call.
How does Gemini 3.1 Pro pricing compare to other Gemini models?
Gemini also offers: Gemini 3.5 Flash at $1.50/$9.00, Gemini 3 Flash at $0.50/$3.00, Gemini 3.5 Flash-Lite at $0.25/$1.50.
What context window does Gemini 3.1 Pro 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.