tokevenGemini · Fast / Budget · 1,048.576K context window
Gemini 2.5 Flash-Lite pricing for chain of thought
$0.002300 per call at 3,000 input / 5,000 output tokens.
Per call
$0.002300
10K calls/mo
$23
Cache savings
90% off input
Batch savings
50% off all
Calculate your Gemini 2.5 Flash-Lite costs
Adjust token counts, volume, and discount toggles to model your chain of thought spend. Prices verified daily against provider pricing pages.
Configure your usage
Estimated cost
Quick start
Call Gemini 2.5 Flash-Lite with the Google Generative AI SDK:
import google.generativeai as genai
model = genai.GenerativeModel("gemini-2.5-flash-lite")
response = model.generate_content("Your prompt here")
# Cost: ~$0.002300 per call at standard rates
# Input: $0.10/MTok
# Output: $0.40/MTokHow Gemini 2.5 Flash-Lite compares on cost
Per-call cost for all models scoring 50+ on chain of thought benchmarks. Hover for details.
Cheapest viable option: Claude Sonnet 5 at $0.0560/call (-2335% less, 90/100 quality).
What drives chain of thought cost
Reasoning tasks invert the usual ratio: the model produces far more tokens than it consumes, because the intermediate steps are the work. Output pricing dominates completely, and models that reason at length cost more than their headline rate suggests. Comparing reasoning models on input price is actively misleading; compare them on output.
For Gemini 2.5 Flash-Lite specifically, that means output tokens cost 4.0x more than input, at $0.40 vs $0.10 per MTok. At this use case’s 3,000/5,000 token split, output accounts for 87% of the $0.002300 per-call cost.
Complete Gemini 2.5 Flash-Lite pricing breakdown
Standard token rates
| Direction | $/MTok | Tokens per call |
|---|---|---|
| Input | $0.10 | 3,000 |
| Output | $0.40 | 5,000 |
Prompt caching: 90% off input tokens
Caching drops input cost from $0.10 to $0.01/MTok. For repeated system prompts, that saves $0.000270 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 | $0.002300 | $23 | $20.3 | $2.7 |
| 50,000 calls | $0.002300 | $115 | $101.5 | $13.5 |
| 100,000 calls | $0.002300 | $230 | $203 | $27 |
| 500,000 calls | $0.002300 | $1,150 | $1,015 | $135 |
| 1,000,000 calls | $0.002300 | $2,300 | $2,030 | $270 |
Gemini 2.5 Flash-Lite quality benchmarks for chain of thought
Benchmark data for chain of thought is pending for Gemini 2.5 Flash-Lite. Test against your own evaluation suite before moving to production.
Performance across all task types
Gemini 2.5 Flash-Lite scores by task type. Chain of Thought highlighted.
| Task type | Confidence score | Rank out of 72 |
|---|
Confidence scores are a third-party benchmark snapshot from week 29 of 2026. This snapshot is 10 weeks old, so treat the scores as directional and validate against your own evals.
Alternative models for chain of thought
6 models score 80+ on chain of thought benchmarks, sorted by input rate. Cheapest: Claude Sonnet 5 (-2335% less, 90/100 quality).
| Model | Provider | Input $/MTok | Output $/MTok | Quality | Per call | vs Gemini |
|---|---|---|---|---|---|---|
| Claude Sonnet 5 | Claude | $2.00 | $10.00 | 90/100 | $0.0560 | 2335% more |
| Gemini 3.1 Pro | Gemini | $2.00 | $12.00 | 90/100 | $0.0660 | 2770% more |
| GPT 5.6 Sol | GPT | $4.00 | $20.00 | 96/100 | $0.1120 | 4770% more |
| Claude Opus 4.8 | Claude | $5.00 | $25.00 | 97/100 | $0.1400 | 5987% more |
| GPT 5.5 | GPT | $5.00 | $30.00 | 95/100 | $0.1650 | 7074% more |
| Claude Fable 5 | Claude | $10.00 | $50.00 | 98/100 | $0.2800 | 12074% more |
About Gemini 2.5 Flash-Lite
Provider
Gemini
Tier
Fast / Budget
Context
1,048.576K tokens
Released
Not published
Backfilled on 2026-09-23. Prices confirmed by the provider pricing page and the LiteLLM cross-check. Release date not published in a machine-readable source. Not yet benchmarked, so never recommended.
Other models from Gemini
| Model | Tier | Input $/MTok | Output $/MTok | Context |
|---|---|---|---|---|
| Gemini 3.1 Pro | Mid-tier | $2.00 | $12.00 | 1,048.576K |
| Gemini 3.5 Flash | Fast / Budget | $1.50 | $9.00 | 1,048.576K |
| Gemini 3 Flash | Fast / Budget | $0.50 | $3.00 | 1,048.576K |
| Gemini 3.5 Flash-Lite | Fast / Budget | $0.30 | $2.50 | 1,048.576K |
| Gemini 2.5 Computer Use | Fast / Budget | $1.25 | $10.00 | 128K |
| Gemini 2.5 Flash | Fast / Budget | $0.30 | $2.50 | 1,048.576K |
| Gemini 2.5 Pro | Mid-tier | $1.25 | $10.00 | 1,048.576K |
| Gemini 3.1 Flash-Lite | Fast / Budget | $0.25 | $1.50 | 1,048.576K |
| Gemini 3.1 Pro Custom Tools | Mid-tier | $2.00 | $12.00 | 1,048.576K |
| Gemini 3.6 Flash | Fast / Budget | $0.75 | $3.75 | 1,048.576K |
| Gemini 3.7 Flash | Fast / Budget | $0.75 | $3.75 | 1,048.576K |
| Gemini 3.8 Flash | Fast / Budget | $0.75 | $3.75 | 1,048.576K |
| Gemini Omni 1.1 Flash | Fast / Budget | $1.50 | $9.00 | 1,048.576K |
| Gemini Omni Flash | Fast / Budget | $1.50 | $9.00 | 1,048.576K |
| Gemini Robotics ER 2 | Fast / Budget | $1.00 | $5.00 | 131.072K |
You can compare Gemini 2.5 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 2.5 Flash-Lite pricing for other use cases
See how Gemini 2.5 Flash-Lite costs change across different workload types.
Code Generation
$0.001800/call
Unit Test Generation
$0.002300/call
SQL Generation
$0.000550/call
API Generation
$0.002700/call
Code Refactoring
$0.002000/call
Code Review
$0.001300/call
PR Review
$0.002000/call
Security Review
$0.001600/call
Bug Detection
$0.001300/call
Document Summarization
$0.001400/call
PDF Summarization
$0.002100/call
Meeting Notes
$0.001600/call
Email Summarization
$0.000500/call
Chatbot
$0.000600/call
RAG Pipeline
$0.001200/call
Customer Support Bot
$0.000700/call
FAQ Bot
$0.000470/call
Data Extraction
$0.000800/call
JSON Extraction
$0.000620/call
Invoice Parsing
$0.000440/call
Resume Parsing
$0.000570/call
Legal Analysis
$0.002600/call
Math Reasoning
$0.001350/call
Financial Analysis
$0.002400/call
Content Moderation
$0.000090/call
Sentiment Analysis
$0.000090/call
Categorization
$0.000140/call
Intent Detection
$0.000070/call
Copywriting
$0.000850/call
Blog Writing
$0.003300/call
Marketing Copy
$0.001280/call
Product Descriptions
$0.000650/call
Related pages
Frequently asked questions
How much does Gemini 2.5 Flash-Lite cost for chain of thought per API call?
A typical chain of thought call using Gemini 2.5 Flash-Lite costs about $0.002300 per call. This estimate uses 3,000 input tokens and 5,000 output tokens at standard rates. Standard rates are $0.10 per million input tokens and $0.40 per million output tokens.
Is Gemini 2.5 Flash-Lite the best model for chain of thought?
Our benchmark data does not yet include a chain of thought ranking for Gemini 2.5 Flash-Lite. We recommend testing it against your own evaluation criteria before production usage.
What is the cheapest model for chain of thought with good quality?
The most affordable model for chain of thought above 80/100 quality is Claude Sonnet 5. It comes from Claude at $2.00 per million input tokens. Output costs $10.00 per million tokens with a quality score of 90/100. Switching from Gemini 2.5 Flash-Lite to Claude Sonnet 5 saves about -2335% per API call.
How can I reduce my Gemini 2.5 Flash-Lite costs for chain of thought?
Three strategies lower Gemini 2.5 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 $0.002300 to about $0.000115 per call.
How does Gemini 2.5 Flash-Lite pricing compare to other Gemini models?
Gemini has 15 other models alongside Gemini 2.5 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 3.5 Flash-Lite at $0.30/$2.50 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 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 chain of thought workload prioritizes quality, cost, or speed.
What context window does Gemini 2.5 Flash-Lite support?
Gemini 2.5 Flash-Lite supports a context window of 1,048.576K tokens per API call. This sets the maximum combined length of your input prompt and generated response. For chain of thought, typical calls use 3,000 input and 5,000 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.