Gemini 2.5 Flash Lite
by Google · google/gemini-2.5-flash-lite · #55 cheapest of 325 paid models
Prices updated Jul 22, 2026, 1:36 AM UTC · refreshed hourly
Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.10
per 1M tokens
Output
$0.40
per 1M tokens
Blended (3:1)
$0.175
3 input : 1 output
Cache read
$0.01
per 1M cached tokens
Cache write
$0.083
per 1M tokens
Cache & batch economics
Effective prices for Gemini 2.5 Flash Lite with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.175 | $0.0106 | — |
| 50% | $0.141 | $0.0061 | −42% |
| 90% | $0.114 | $0.0025 | −76% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates for this provider’s batch API. Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.00017 | $0.17 |
| Document summary | 8,000 | 1,000 | $0.0012 | $1.20 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.0038 | $3.80 |
| Long-context analysis | 150,000 | 5,000 | $0.017 | $17.00 |
Performance
Intelligence Index
6.9
AA composite quality
Coding Index
—
Math Index
35.3
Agentic Index
—
Output speed
247 tok/s
median
Time to first token
0.32s
median
Time to first answer
0.32s
after reasoning tokens
Artificial Analysis benchmarks
| Benchmark | Score |
|---|---|
| MMLU-Pro | 72.4% |
| GPQA Diamond | 47.4% |
| Humanity's Last Exam | 3.7% |
| LiveCodeBench | 40.0% |
| SciCode | 17.7% |
| MATH-500 | 92.6% |
| AIME | 50.0% |
| AIME 2025 | 35.3% |
| IFBench | 31.5% |
| AA-LCR (Long Context Reasoning) | 31.3% |
| Terminal-Bench Hard | 2.3% |
| τ²-Bench (Telecom) | 19.0% |
Specs
Context window
1.05M
tokens
Max output
66K
tokens
Input modalities
text, image, file, audio, video
Tokenizer
Gemini