tokevenGemini · Fast / Budget · 1.0M context window
Gemini 3.5 Flash-Lite pricing for api generation
$0.0159 per call at 3,000 input / 6,000 output tokens.
Per call
$0.0159
10K calls/mo
$159
Cache savings
90% off input
Batch savings
50% off all
Calculate your Gemini 3.5 Flash-Lite costs
Adjust token counts, volume, and discount toggles to model your api generation spend. Prices verified daily against provider pricing pages.
Configure your usage
Estimated cost
Quick start
Call Gemini 3.5 Flash-Lite with the Google Generative AI SDK:
import google.generativeai as genai
model = genai.GenerativeModel("gemini-3.5-flash-lite")
response = model.generate_content("Your prompt here")
# Cost: ~$0.0159 per call at standard rates
# Input: $0.30/MTok
# Output: $2.50/MTokHow Gemini 3.5 Flash-Lite compares on cost
Per-call cost for all models scoring 50+ on api generation benchmarks. Hover for details.
Highest-quality affordable option: Claude Haiku 4.5 at $0.0330/call (2.1x the cost, 72/100 quality). Gemini 3.5 Flash-Lite is already the cheapest choice for api generation.
What drives api generation cost
Endpoint generation is the most output-heavy code task tracked here: 3K in for the spec, 6K out for handlers, types, validation, and error paths. Output pricing is therefore the whole ballgame, and the gap between a flagship and a mid-tier model at 6K output tokens compounds fast across a large API surface. Generating one resource at a time costs less than one giant multi-resource prompt.
For Gemini 3.5 Flash-Lite specifically, that means output tokens cost 8.3x more than input, at $2.50 vs $0.30 per MTok. At this use case’s 3,000/6,000 token split, output accounts for 94% of the $0.0159 per-call cost.
Complete Gemini 3.5 Flash-Lite pricing breakdown
Standard token rates
| Direction | $/MTok | Tokens per call |
|---|---|---|
| Input | $0.30 | 3,000 |
| Output | $2.50 | 6,000 |
Prompt caching: 90% off input tokens
Caching drops input cost from $0.30 to $0.03/MTok. For repeated system prompts, that saves $0.000810 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 | $0.0159 | $159 | $150.9 | $8.1 |
| 50,000 calls | $0.0159 | $795 | $754.5 | $40.5 |
| 100,000 calls | $0.0159 | $1,590 | $1,509 | $81 |
| 500,000 calls | $0.0159 | $7,950 | $7,545 | $405 |
| 1,000,000 calls | $0.0159 | $15,900 | $15,090 | $810 |
Gemini 3.5 Flash-Lite quality benchmarks for api generation
Consider alternatives for api generation
Scores 58/100 (rank #23 of 88). Better options exist at similar price points for api generation.
Top-ranked: Claude Opus 5.5 (79/100) at $0.1320/call
Performance across all task types
Gemini 3.5 Flash-Lite scores by task type. API Generation highlighted.
| Task type | Confidence score | Rank out of 88 |
|---|---|---|
| Classification | 85/100 | #4 |
| Q&A | 78/100 | #6 |
| Extraction | 69/100 | #30 |
| Summarization | 67/100 | #16 |
| Creative Writing | 67/100 | #23 |
| Reasoning | 60/100 | #30 |
| Code Generation(current page) | 58/100 | #23 |
| Code Review | 52/100 | #8 |
Confidence scores are a third-party benchmark snapshot from week 26 of 2026. This snapshot is 17 weeks old, so treat the scores as directional and validate against your own evals.
Alternative models for api generation
5 models score 80+ on api generation benchmarks, sorted by input rate. Cheapest: Claude Haiku 4.5 (108% more, 72/100 quality).
| Model | Provider | Input $/MTok | Output $/MTok | Quality | Per call | vs Gemini |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | Claude | $1.00 | $5.00 | 72/100 | $0.0330 | 108% more |
| Claude Opus 5.5 | Claude | $4.00 | $20.00 | 79/100 | $0.1320 | 730% more |
| Claude Opus 5 | Claude | $5.00 | $25.00 | 72/100 | $0.1650 | 938% more |
| Claude Fable 5.1 | Claude | $10.00 | $50.00 | 74/100 | $0.3300 | 1975% more |
| Claude Fable 5 | Claude | $10.00 | $50.00 | 72/100 | $0.3300 | 1975% more |
About Gemini 3.5 Flash-Lite
Provider
Gemini
Tier
Fast / Budget
Context
1.0M tokens
Released
Jun 2026
Other models from Gemini
| Model | Tier | Input $/MTok | Output $/MTok | Context |
|---|---|---|---|---|
| Gemini 3.1 Pro | Mid-tier | $2.00 | $12.00 | 1.0M |
| Gemini 3.5 Flash | Fast / Budget | $1.50 | $9.00 | 1.0M |
| Gemini 3 Flash | Fast / Budget | $0.50 | $3.00 | 1.0M |
| Gemini 2.5 Computer Use | Fast / Budget | $1.25 | $10.00 | 128K |
| Gemini 2.5 Flash | Fast / Budget | $0.30 | $2.50 | 1.0M |
| Gemini 2.5 Flash-Lite | Fast / Budget | $0.10 | $0.40 | 1.0M |
| Gemini 2.5 Pro | Mid-tier | $1.25 | $10.00 | 1.0M |
| Gemini 3.1 Flash-Lite | Fast / Budget | $0.25 | $1.50 | 1.0M |
| Gemini 3.1 Pro Custom Tools | Mid-tier | $2.00 | $12.00 | 1.0M |
| Gemini 3.6 Flash | Fast / Budget | $0.75 | $3.75 | 1.0M |
| Gemini 3.7 Flash | Fast / Budget | $0.75 | $3.75 | 1.0M |
| Gemini 3.8 Flash | Fast / Budget | $0.75 | $3.75 | 1.0M |
| Gemini Omni 1.1 Flash | Fast / Budget | $1.50 | $9.00 | 1.0M |
| Gemini Omni Flash | Fast / Budget | $1.50 | $9.00 | 1.0M |
| Gemini Robotics ER 2 | Fast / Budget | $1.00 | $5.00 | 131K |
You can compare Gemini 3.5 Flash-Lite 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-Lite pricing for other use cases
See how Gemini 3.5 Flash-Lite costs change across different workload types.
Code Generation
$0.0106/call
Unit Test Generation
$0.0134/call
SQL Generation
$0.002950/call
Code Refactoring
$0.0112/call
Code Review
$0.006500/call
PR Review
$0.009900/call
Security Review
$0.008050/call
Bug Detection
$0.006500/call
Document Summarization
$0.005500/call
PDF Summarization
$0.008250/call
Meeting Notes
$0.007400/call
Email Summarization
$0.002150/call
Chatbot
$0.003100/call
RAG Pipeline
$0.005550/call
Customer Support Bot
$0.003400/call
FAQ Bot
$0.002450/call
Data Extraction
$0.003700/call
JSON Extraction
$0.002900/call
Invoice Parsing
$0.002100/call
Resume Parsing
$0.002750/call
Chain of Thought
$0.0134/call
Legal Analysis
$0.0130/call
Math Reasoning
$0.007950/call
Financial Analysis
$0.0124/call
Content Moderation
$0.000400/call
Sentiment Analysis
$0.000400/call
Categorization
$0.000615/call
Intent Detection
$0.000340/call
Copywriting
$0.005150/call
Blog Writing
$0.0203/call
Marketing Copy
$0.007740/call
Product Descriptions
$0.003900/call
Related pages
Frequently asked questions
How much does Gemini 3.5 Flash-Lite cost for api generation per API call?
A typical api generation call using Gemini 3.5 Flash-Lite costs about $0.0159 per call. This estimate uses 3,000 input tokens and 6,000 output tokens at standard rates. Standard rates are $0.30 per million input tokens and $2.50 per million output tokens.
Is Gemini 3.5 Flash-Lite the best model for api generation?
Gemini 3.5 Flash-Lite scores 58 out of 100 on api generation benchmarks overall. It ranks #23 across all 88 models in our cross-provider registry. The highest-ranked model for this task is Claude Opus 5.5 from Claude. That model scores 79/100 on this task type. Confidence scores are a third-party benchmark snapshot from week 26 of 2026. This snapshot is 17 weeks old, so treat the scores as directional and validate against your own evals.
What is the cheapest model for api generation with good quality?
The most affordable model for api generation above 80/100 quality is Claude Haiku 4.5. It comes from Claude at $1.00 per million input tokens. Output costs $5.00 per million tokens with a quality score of 72/100. Claude Haiku 4.5 costs more per call than Gemini 3.5 Flash-Lite but scores higher on quality benchmarks for this task type.
How can I reduce my Gemini 3.5 Flash-Lite costs for api generation?
Three strategies lower Gemini 3.5 Flash-Lite 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 $0.0159 to about $0.000795 per call.
How does Gemini 3.5 Flash-Lite pricing compare to other Gemini models?
Gemini has 15 other models alongside Gemini 3.5 Flash-Lite today: Gemini 3.1 Pro at $2.00/$12.00 per million tokens (mid-tier), Gemini 3.5 Flash at $1.50/$9.00 per million tokens (fast / budget), Gemini 3 Flash at $0.50/$3.00 per million tokens (fast / budget), Gemini 2.5 Computer Use at $1.25/$10.00 per million tokens (fast / budget), Gemini 2.5 Flash at $0.30/$2.50 per million tokens (fast / budget), Gemini 2.5 Flash-Lite at $0.10/$0.40 per million tokens (fast / budget), Gemini 2.5 Pro at $1.25/$10.00 per million tokens (mid-tier), Gemini 3.1 Flash-Lite at $0.25/$1.50 per million tokens (fast / budget), Gemini 3.1 Pro Custom Tools at $2.00/$12.00 per million tokens (mid-tier), Gemini 3.6 Flash at $0.75/$3.75 per million tokens (fast / budget), Gemini 3.7 Flash at $0.75/$3.75 per million tokens (fast / budget), Gemini 3.8 Flash at $0.75/$3.75 per million tokens (fast / budget), Gemini Omni 1.1 Flash at $1.50/$9.00 per million tokens (fast / budget), Gemini Omni Flash at $1.50/$9.00 per million tokens (fast / budget), Gemini Robotics ER 2 at $1.00/$5.00 per million tokens (fast / budget). The right choice depends on whether your api generation workload prioritizes quality, cost, or speed.
What context window does Gemini 3.5 Flash-Lite support?
Gemini 3.5 Flash-Lite supports a context window of 1.0M tokens per API call. This sets the maximum combined length of your input prompt and generated response. For api generation, typical calls use 3,000 input and 6,000 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.