Gemini 3.8 Flash
by Google · google/gemini-3.8-flash · #267 cheapest of 422 paid models
Prices updated Sep 20, 2026, 12:34 AM UTC · refreshed hourly
Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.75
per 1M tokens
Output
$3.75
per 1M tokens
Blended (3:1)
$1.50
3 input : 1 output
Cache read
$0.075
per 1M cached tokens
Cache write
$0.042
per 1M tokens
Cache & batch economics
Effective prices for Gemini 3.8 Flash with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $1.50 | $0.0803 | — |
| 50% | $1.25 | $0.0465 | −42% |
| 90% | $1.04 | $0.0195 | −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 | $0.0015 | $1.50 |
| Document summary | 8,000 | 1,000 | $0.00975 | $9.75 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.03 | $30.00 |
| Long-context analysis | 150,000 | 5,000 | $0.1312 | $131.25 |
Performance
Intelligence Index
40.9
AA composite quality
Coding Index
76.3
Math Index
—
Agentic Index
41.1
Output speed
327 tok/s
median
Time to first token
11.27s
median
Time to first answer
11.27s
after reasoning tokens
Artificial Analysis benchmarks
| Benchmark | Score |
|---|---|
| GPQA Diamond | 95.3% |
| Humanity's Last Exam | 47.8% |
| SciCode | 56.6% |
| AA-LCR (Long Context Reasoning) | 81.3% |
| Terminal-Bench 2.1 | 87.6% |
| τ³-Bench Banking | 44.9% |
Design Arena Elo
| Category | Elo |
|---|---|
| Website | 1,315 |
| Web apps | 1,256 |
| Full-stack | 1,250 |
| Mobile apps | 1,259 |
| UI components | 1,340 |
| Data viz | 1,265 |
| 3D | 1,323 |
| Game dev | 1,339 |
| Python→PPTX slides | 1,176 |
| Code categories | 1,324 |
Specs
Context window
1.05M
tokens
Max output
66K
tokens
Input modalities
text, image, video, file, audio
Tokenizer
Gemini