Gemini 3.1 Pro Preview
by Google · google/gemini-3.1-pro-preview · #358 cheapest of 422 paid models
Prices updated Sep 20, 2026, 12:34 AM UTC · refreshed hourly
Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$2.00
per 1M tokens
Output
$12.00
per 1M tokens
Blended (3:1)
$4.50
3 input : 1 output
Cache read
$0.20
per 1M cached tokens
Cache write
$0.375
per 1M tokens
Cache & batch economics
Effective prices for Gemini 3.1 Pro Preview with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $4.50 | $0.216 | — |
| 50% | $3.83 | $0.126 | −42% |
| 90% | $3.29 | $0.054 | −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 | $0.0046 | $4.60 |
| Document summary | 8,000 | 1,000 | $0.028 | $28.00 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.084 | $84.00 |
| Long-context analysis | 150,000 | 5,000 | $0.36 | $360.00 |
Performance
Intelligence Index
29.7
AA composite quality
Coding Index
68.8
Math Index
—
Agentic Index
10.3
Output speed
132 tok/s
median
Time to first token
24.64s
median
Time to first answer
24.64s
after reasoning tokens
Artificial Analysis benchmarks
| Benchmark | Score |
|---|---|
| GPQA Diamond | 94.1% |
| Humanity's Last Exam | 47.0% |
| SciCode | 58.7% |
| IFBench | 77.1% |
| AA-LCR (Long Context Reasoning) | 82.0% |
| Terminal-Bench Hard | 53.8% |
| Terminal-Bench 2.1 | 73.8% |
| τ²-Bench (Telecom) | 95.6% |
| τ³-Bench Banking | 21.4% |
Design Arena Elo
| Category | Elo |
|---|---|
| Website | 1,265 |
| Web apps | 1,141 |
| Full-stack | 1,078 |
| Mobile apps | 1,121 |
| Android native | 1,063 |
| UI components | 1,295 |
| Data viz | 1,253 |
| SVG | 1,310 |
| 3D | 1,263 |
| Game dev | 1,226 |
| Agentic game dev | 1,114 |
| Godot game dev | 1,236 |
| HTML slides | 1,155 |
| PPTX slides | 1,110 |
| Python→PPTX slides | 1,109 |
| Agentic slides | 1,112 |
| Agentic HTML slides | 1,226 |
| Agentic slides (HTML) | 1,219 |
| Agentic slides (Python PPTX) | 1,107 |
| Code categories | 1,259 |
| ASCII art | 1,289 |
Specs
Context window
1.05M
tokens
Max output
66K
tokens
Input modalities
audio, file, image, text, video
Tokenizer
Gemini