tokevenGemini · Fast / Budget · 1,000K context window
Gemini 3.5 Flash pricing for faq bot
$0.009450 per call at 1,500 input / 800 output tokens.
Per call
$0.009450
10K calls/mo
$94.5
Cache savings
90% off input
Batch savings
50% off all
Calculate your Gemini 3.5 Flash costs
Adjust token counts, volume, and discount toggles to model your faq bot spend. Prices verified daily against provider pricing pages.
Configure your usage
Estimated cost
Quick start
Call Gemini 3.5 Flash with the Google Generative AI SDK:
import google.generativeai as genai
model = genai.GenerativeModel("gemini-3.5-flash")
response = model.generate_content("Your prompt here")
# Cost: ~$0.009450 per call at standard rates
# Input: $1.50/MTok
# Output: $9.00/MTokHow Gemini 3.5 Flash compares on cost
Per-call cost for all models scoring 50+ on faq bot benchmarks. Hover for details.
Cheapest viable option: GPT 5.6 Luna at $0.001260/call (87% less, 85/100 quality).
What drives faq bot cost
The most bounded question-answering shape: a short question against a fixed knowledge base, with a short answer. Because the knowledge base never changes between calls, cache reads apply to nearly the entire input, and the effective cost per answer falls well below the list rate. A fast-tier model is usually sufficient when the answers are already written.
For Gemini 3.5 Flash specifically, that means output tokens cost 6.0x more than input, at $9.00 vs $1.50 per MTok. At this use case’s 1,500/800 token split, output accounts for 76% of the $0.009450 per-call cost.
Complete Gemini 3.5 Flash pricing breakdown
Standard token rates
| Direction | $/MTok | Tokens per call |
|---|---|---|
| Input | $1.50 | 1,500 |
| Output | $9.00 | 800 |
Prompt caching: 90% off input tokens
Caching drops input cost from $1.50 to $0.15/MTok. For repeated system prompts, that saves $0.002025 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 | $0.009450 | $94.5 | $74.25 | $20.25 |
| 50,000 calls | $0.009450 | $472.5 | $371.25 | $101.25 |
| 100,000 calls | $0.009450 | $945 | $742.5 | $202.5 |
| 500,000 calls | $0.009450 | $4,725 | $3,712.5 | $1,012.5 |
| 1,000,000 calls | $0.009450 | $9,450 | $7,425 | $2,025 |
Gemini 3.5 Flash quality benchmarks for faq bot
Gemini 3.5 Flash is a solid pick for faq bot
Scores 84/100 (rank #5 of 20). Good balance of quality and cost for faq bot.
Top-ranked: GPT 5.6 Terra (92/100) at $0.0126/call
Performance across all task types
Gemini 3.5 Flash scores by task type. FAQ Bot highlighted.
| Task type | Confidence score | Rank out of 20 |
|---|---|---|
| Classification | 92/100 | #1 |
| Extraction | 90/100 | #1 |
| Summarization | 85/100 | #3 |
| Q&A(current page) | 84/100 | #5 |
| Code Generation | 68/100 | #7 |
| Code Review | 65/100 | #6 |
| Reasoning | 60/100 | #6 |
| Creative Writing | 55/100 | #6 |
Confidence scores are a third-party benchmark snapshot from week 29 of 2026. This snapshot is 8 weeks old, so treat the scores as directional and validate against your own evals.
Alternative models for faq bot
12 models score 80+ on faq bot benchmarks, sorted by input rate. Cheapest: GPT 5.6 Luna (87% less, 85/100 quality).
| Model | Provider | Input $/MTok | Output $/MTok | Quality | Per call | vs Gemini |
|---|---|---|---|---|---|---|
| GPT 5.6 Luna | GPT | $0.20 | $1.20 | 85/100 | $0.001260 | 87% cheaper |
| Gemini 3 Flash | Gemini | $0.50 | $3.00 | 82/100 | $0.003150 | 67% cheaper |
| Claude Haiku 4.5 | Claude | $1.00 | $5.00 | 86/100 | $0.005500 | 42% cheaper |
| Claude Sonnet 5 | Claude | $2.00 | $10.00 | 89/100 | $0.0110 | 16% more |
| GPT 5.6 Terra | GPT | $2.00 | $12.00 | 92/100 | $0.0126 | 33% more |
| Gemini 3.1 Pro | Gemini | $2.00 | $12.00 | 87/100 | $0.0126 | 33% more |
| GPT 5.4 | GPT | $2.50 | $15.00 | 91/100 | $0.0158 | 67% more |
| Claude Sonnet 4.6 | Claude | $3.00 | $15.00 | 88/100 | $0.0165 | 75% more |
| GPT 5.6 Sol | GPT | $4.00 | $20.00 | 91/100 | $0.0220 | 133% more |
| Claude Opus 4.8 | Claude | $5.00 | $25.00 | 85/100 | $0.0275 | 191% more |
| GPT 5.5 | GPT | $5.00 | $30.00 | 90/100 | $0.0315 | 233% more |
| Claude Fable 5 | Claude | $10.00 | $50.00 | 88/100 | $0.0550 | 482% more |
About Gemini 3.5 Flash
Provider
Gemini
Tier
Fast / Budget
Context
1,000K tokens
Released
May 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 Flash | Fast / Budget | $0.50 | $3.00 | 1,000K |
| Gemini 3.5 Flash-Lite | Fast / Budget | $0.30 | $2.50 | 1,000K |
You can compare Gemini 3.5 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 3.5 Flash pricing for other use cases
See how Gemini 3.5 Flash costs change across different workload types.
Code Generation
$0.0390/call
Unit Test Generation
$0.0495/call
SQL Generation
$0.0113/call
API Generation
$0.0585/call
Code Refactoring
$0.0420/call
Code Review
$0.0255/call
PR Review
$0.0390/call
Security Review
$0.0315/call
Bug Detection
$0.0255/call
Document Summarization
$0.0240/call
PDF Summarization
$0.0360/call
Meeting Notes
$0.0300/call
Email Summarization
$0.009000/call
Chatbot
$0.0120/call
RAG Pipeline
$0.0225/call
Customer Support Bot
$0.0135/call
Data Extraction
$0.0150/call
JSON Extraction
$0.0117/call
Invoice Parsing
$0.008400/call
Resume Parsing
$0.0110/call
Chain of Thought
$0.0495/call
Legal Analysis
$0.0510/call
Math Reasoning
$0.0292/call
Financial Analysis
$0.0480/call
Content Moderation
$0.001650/call
Sentiment Analysis
$0.001650/call
Categorization
$0.002550/call
Intent Detection
$0.001350/call
Copywriting
$0.0188/call
Blog Writing
$0.0735/call
Marketing Copy
$0.0282/call
Product Descriptions
$0.0143/call
Related pages
Frequently asked questions
How much does Gemini 3.5 Flash cost for faq bot per API call?
A typical faq bot call using Gemini 3.5 Flash costs about $0.009450 per call. This estimate uses 1,500 input tokens and 800 output tokens at standard rates. Standard rates are $1.50 per million input tokens and $9.00 per million output tokens.
Is Gemini 3.5 Flash the best model for faq bot?
Gemini 3.5 Flash scores 84 out of 100 on faq bot benchmarks overall. It ranks #5 across all 20 models in our cross-provider registry. The highest-ranked model for this task is GPT 5.6 Terra from GPT. That model scores 92/100 on this task type. Confidence scores are a third-party benchmark snapshot from week 29 of 2026. This snapshot is 8 weeks old, so treat the scores as directional and validate against your own evals.
What is the cheapest model for faq bot with good quality?
The most affordable model for faq bot above 80/100 quality is GPT 5.6 Luna. It comes from GPT at $0.20 per million input tokens. Output costs $1.20 per million tokens with a quality score of 85/100. Switching from Gemini 3.5 Flash to GPT 5.6 Luna saves about 87% per API call.
How can I reduce my Gemini 3.5 Flash costs for faq bot?
Three strategies lower Gemini 3.5 Flash costs for this task type effectively. Prompt caching gives a 90% discount on input tokens when reusing system prompts. The batch API gives 50% off all tokens for asynchronous processing workloads. Prompt optimization reduces token counts through more concise instructions and context windows. Combining caching with batching brings your cost from $0.009450 to about $0.000473 per call.
How does Gemini 3.5 Flash pricing compare to other Gemini models?
Gemini has 3 other models alongside Gemini 3.5 Flash today: Gemini 3.1 Pro at $2.00/$12.00 per million tokens (mid-tier), Gemini 3 Flash at $0.50/$3.00 per million tokens (fast / budget), Gemini 3.5 Flash-Lite at $0.30/$2.50 per million tokens (fast / budget). The right choice depends on whether your faq bot workload prioritizes quality, cost, or speed.
What context window does Gemini 3.5 Flash support?
Gemini 3.5 Flash supports a context window of 1,000K tokens per API call. This sets the maximum combined length of your input prompt and generated response. For faq bot, typical calls use 1,500 input and 800 output tokens. That is well within this limit, leaving room for longer prompts or multi-turn conversations.
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.