Gemini 3.1 Flash Lite (batch)
by Google · google/gemini-3.1-flash-lite:batch · #109 cheapest of 422 paid models
Prices updated Sep 19, 2026, 6:21 PM UTC · refreshed hourly
Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.125
per 1M tokens
Output
$0.75
per 1M tokens
Blended (3:1)
$0.281
3 input : 1 output
Cache read
$0.012
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for Gemini 3.1 Flash Lite (batch) with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.281 | $0.0135 | — |
| 50% | $0.239 | $0.007875 | −42% |
| 90% | $0.205 | $0.003375 | −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 | $0.000287 | $0.2875 |
| Document summary | 8,000 | 1,000 | $0.00175 | $1.75 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.00525 | $5.25 |
| Long-context analysis | 150,000 | 5,000 | $0.0225 | $22.50 |
Performance
Intelligence Index
16
AA composite quality
Coding Index
34.7
Math Index
—
Agentic Index
—
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 | 82.2% |
| Humanity's Last Exam | 17.2% |
| SciCode | 43.4% |
| IFBench | 77.2% |
| AA-LCR (Long Context Reasoning) | 74.3% |
| Terminal-Bench Hard | 24.2% |
| Terminal-Bench 2.1 | 31.1% |
| τ²-Bench (Telecom) | 31.3% |
| τ³-Bench Banking | 9.7% |
Specs
Context window
1.05M
tokens
Max output
66K
tokens
Input modalities
text, image, video, file, audio
Tokenizer
Gemini