Skip to main content
TC
TokenCost

Gemini 2.5 Flash vs Gemini 2.5 Flash-Lite

Complete pricing and performance comparison between Google's Gemini 2.5 Flash and Google's Gemini 2.5 Flash-Lite.

Quick Verdict

Cheaper
Gemini 2.5 Flash-Lite
3.0x cheaper input, 6.3x cheaper output
Larger Context
Gemini 2.5 Flash
1.0M vs 1.0M
Higher Quality
Gemini 2.5 Flash
Score: 21 vs 13
Faster
Gemini 2.5 Flash-Lite
336 vs 231 tok/s

Pricing Comparison

SpecGemini 2.5 FlashGemini 2.5 Flash-LiteDifference
ProviderGoogleGoogle
Input / 1M tokens$0.3$0.1Gemini 2.5 Flash-Lite is 67% more expensive
Output / 1M tokens$2.5$0.4Gemini 2.5 Flash-Lite is 84% more expensive
Context Window1.0M1.0MSame
Max Output66K66K

Performance Benchmarks

MetricGemini 2.5 FlashGemini 2.5 Flash-LiteWinner
Quality Index2113Gemini 2.5 Flash
Output Speed231 tok/s336 tok/sGemini 2.5 Flash-Lite
Time to First Token0.42s0.27sGemini 2.5 Flash-Lite
Value (Quality/$)68.7127.0Higher = better value

Benchmark data from Artificial Analysis. Quality Index is a composite score across reasoning, coding, and knowledge tasks.

Cost at Scale

Estimated cost at different usage levels (3:1 input-to-output token ratio, typical for chat).

UsageGemini 2.5 FlashGemini 2.5 Flash-LiteSavings
Single request
1K in / 300 out
$0.0010$0.0002Same
10 requests
10K in / 3K out
$0.010$0.0022Gemini 2.5 Flash-Lite saves $0.0083
100 requests
100K in / 30K out
$0.105$0.022Gemini 2.5 Flash-Lite saves $0.083
1,000 requests
1M in / 300K out
$1.05$0.220Gemini 2.5 Flash-Lite saves $0.830
10,000 requests
10M in / 3M out
$10.50$2.20Gemini 2.5 Flash-Lite saves $8.30
1M requests/mo
1B in / 300M out
$1050.00$220.00Gemini 2.5 Flash-Lite saves $830.00

Pros & Cons

Gemini 2.5 Flash Strengths

  • +Higher quality score (21 vs 13)

Gemini 2.5 Flash-Lite Strengths

  • +Cheaper input tokens
  • +Cheaper output tokens
  • +Faster output (336 vs 231 tok/s)
  • +Lower latency (faster first token)

When to Use Each Model

Choose Gemini 2.5 Flash for

  • →Tasks requiring maximum accuracy and reasoning

Choose Gemini 2.5 Flash-Lite for

  • →Budget-conscious projects where cost is the primary factor
  • →Real-time applications, chat, or autocomplete

Frequently Asked Questions

Which is cheaper, Gemini 2.5 Flash or Gemini 2.5 Flash-Lite?
For input tokens, Gemini 2.5 Flash-Lite is 3.0x cheaper at $0.1/1M tokens. For output tokens, Gemini 2.5 Flash-Lite is 6.3x cheaper at $0.4/1M tokens. At typical usage (1M input + 300K output), Gemini 2.5 Flash costs $1.05 vs Gemini 2.5 Flash-Lite at $0.220.
What's the context window difference?
Gemini 2.5 Flash supports 1.0M context (1,048,576 tokens), while Gemini 2.5 Flash-Lite supports 1.0M (1,048,576 tokens). Gemini 2.5 Flash-Lite can handle 1x more context in a single request.
Which model has better benchmarks?
Quality Index: Gemini 2.5 Flash scores 21 vs Gemini 2.5 Flash-Lite at 13. Speed: Gemini 2.5 Flash generates 231 tok/s vs Gemini 2.5 Flash-Lite at 336 tok/s. Time to first token: Gemini 2.5 Flash at 0.42s vs Gemini 2.5 Flash-Lite at 0.27s.
When should I choose Gemini 2.5 Flash over Gemini 2.5 Flash-Lite?
Choose Gemini 2.5 Flash when you need: Higher quality score (21 vs 13). Choose Gemini 2.5 Flash-Lite when you need: Cheaper input tokens, Cheaper output tokens, Faster output (336 vs 231 tok/s), Lower latency (faster first token).
How much would 10,000 API requests cost?
At 1K input + 300 output tokens per request (typical chat): Gemini 2.5 Flash = $10.50, Gemini 2.5 Flash-Lite = $2.20. At 10K input + 1K output per request (longer conversations): Gemini 2.5 Flash = $55.00, Gemini 2.5 Flash-Lite = $14.00.

Related Comparisons

Gemini 2.5 Flash vs GPT-5.4
$0.3 vs $2.5 per 1M input
Gemini 2.5 Flash-Lite vs GPT-5.4
$0.1 vs $2.5 per 1M input
Gemini 2.5 Flash vs GPT-5.4 Mini
$0.3 vs $0.75 per 1M input
Gemini 2.5 Flash-Lite vs GPT-5.4 Mini
$0.1 vs $0.75 per 1M input
Gemini 2.5 Flash vs GPT-5.4 Nano
$0.3 vs $0.2 per 1M input
Gemini 2.5 Flash-Lite vs GPT-5.4 Nano
$0.1 vs $0.2 per 1M input
Gemini 2.5 Flash DetailsGemini 2.5 Flash-Lite DetailsFull Pricing TableCost Calculator