Gemini 3.8 Flash
by Google · google/gemini-3.8-flash · #282 cheapest of 457 paid models
Prices updated Nov 18, 2026, 5:43 AM UTC · refreshed nightly
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
$0.825
per 1M tokens
Output
$4.13
per 1M tokens
Blended (3:1)
$1.65
3 input : 1 output
Cache read
$0.083
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% | $1.65 | $0.0883 | — |
| 50% | $1.37 | $0.0512 | −42% |
| 90% | $1.15 | $0.0215 | −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 | $0.00165 | $1.65 |
| Document summary | 8,000 | 1,000 | $0.0107 | $10.73 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.033 | $33.00 |
| Long-context analysis | 150,000 | 5,000 | $0.1444 | $144.38 |
Performance
Intelligence Index
30.8
AA composite quality
Coding Index
76.3
Math Index
—
Agentic Index
40.2
Output speed
—
median
Time to first token
—
median
Time to first answer
—
after reasoning tokens
Design Arena Elo
| Category | Elo |
|---|---|
| Website | 1,291 |
| Web apps | 1,216 |
| Full-stack | 1,216 |
| Mobile apps | 1,225 |
| Android native | 1,087 |
| UI components | 1,302 |
| Data viz | 1,274 |
| SVG | 1,289 |
| 3D | 1,275 |
| Game dev | 1,296 |
| Godot game dev | 1,242 |
| Python→PPTX slides | 1,149 |
| Code categories | 1,291 |
| ASCII art | 1,259 |
| blender3d | 1,158 |
| codetovideo | 1,203 |
| 1,210 | |
| spreadsheet | 1,028 |
Specs
Context window
1.05M
tokens
Max output
66K
tokens
Input modalities
text, image, video, file, audio
Tokenizer
Gemini