Gemini 3.5 Flash
by Google · google/gemini-3.5-flash · #331 cheapest of 422 paid models
Prices updated Sep 20, 2026, 12:34 AM UTC · refreshed hourly
Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$1.50
per 1M tokens
Output
$9.00
per 1M tokens
Blended (3:1)
$3.38
3 input : 1 output
Cache read
$0.15
per 1M cached tokens
Cache write
$0.083
per 1M tokens
Cache & batch economics
Effective prices for Gemini 3.5 Flash with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $3.38 | $0.162 | — |
| 50% | $2.87 | $0.0945 | −42% |
| 90% | $2.46 | $0.0405 | −75% |
*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 | $0.00345 | $3.45 |
| Document summary | 8,000 | 1,000 | $0.021 | $21.00 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.063 | $63.00 |
| Long-context analysis | 150,000 | 5,000 | $0.27 | $270.00 |
Performance
Intelligence Index
32.6
AA composite quality
Coding Index
70.1
Math Index
—
Agentic Index
27.3
Output speed
0 tok/s
median
Time to first token
0s
median
Time to first answer
0s
after reasoning tokens
Artificial Analysis benchmarks
| Benchmark | Score |
|---|---|
| GPQA Diamond | 92.2% |
| Humanity's Last Exam | 42.7% |
| SciCode | 53.9% |
| IFBench | 76.3% |
| AA-LCR (Long Context Reasoning) | 73.3% |
| Terminal-Bench Hard | 40.9% |
| Terminal-Bench 2.1 | 78.7% |
| τ²-Bench (Telecom) | 95.3% |
| τ³-Bench Banking | 32.2% |
Design Arena Elo
| Category | Elo |
|---|---|
| Website | 1,275 |
| Web apps | 1,219 |
| Full-stack | 1,208 |
| Mobile apps | 1,201 |
| Android native | 1,196 |
| UI components | 1,287 |
| Data viz | 1,248 |
| SVG | 1,278 |
| 3D | 1,271 |
| Game dev | 1,288 |
| Agentic game dev | 1,180 |
| Godot game dev | 1,108 |
| HTML slides | 1,145 |
| PPTX slides | 1,244 |
| Python→PPTX slides | 1,247 |
| Agentic slides | 1,244 |
| Agentic HTML slides | 1,162 |
| Agentic slides (HTML) | 1,162 |
| Agentic slides (Python PPTX) | 1,242 |
| Code categories | 1,278 |
| ASCII art | 1,274 |
Specs
Context window
1.05M
tokens
Max output
66K
tokens
Input modalities
text, image, video, file, audio
Tokenizer
Gemini